%%% -*-BibTeX-*- %%% ==================================================================== %%% BibTeX-file{ %%% author = "Nelson H. F. Beebe", %%% version = "1.35", %%% date = "14 June 2025", %%% time = "09:25:56 MDT", %%% filename = "topc.bib", %%% address = "University of Utah %%% Department of Mathematics, 110 LCB %%% 155 S 1400 E RM 233 %%% Salt Lake City, UT 84112-0090 %%% USA", %%% telephone = "+1 801 581 5254", %%% URL = "https://www.math.utah.edu/~beebe", %%% checksum = "21815 10005 53206 497808", %%% email = "beebe at math.utah.edu, beebe at acm.org, %%% beebe at computer.org (Internet)", %%% codetable = "ISO/ASCII", %%% keywords = "ACM Transactions on Parallel Computing %%% (TOPC); bibliography; BibTeX", %%% license = "public domain", %%% supported = "yes", %%% docstring = "This is a COMPLETE BibTeX bibliography for %%% ACM Transactions on Parallel Computing (TOPC) %%% (CODEN ????, ISSN 2329-4949 (print), %%% 2329-4957 (electronic)). The journal appears %%% quarterly, and publication began with volume %%% 1, number 1, in September 2014. %%% %%% At version 1.35, the COMPLETE journal %%% coverage looked like this: %%% %%% 2014 ( 8) 2018 ( 22) 2022 ( 16) %%% 2015 ( 29) 2019 ( 29) 2023 ( 22) %%% 2016 ( 25) 2020 ( 27) 2024 ( 18) %%% 2017 ( 16) 2021 ( 23) 2025 ( 6) %%% %%% Article: 241 %%% %%% Total entries: 241 %%% %%% The journal Web page can be found at: %%% %%% http://topc.acm.org/ %%% %%% The journal table of contents page is at: %%% %%% http://dl.acm.org/pub.cfm?id=J1496 %%% http://dl.acm.org/citation.cfm?id=2632163 %%% %%% Qualified subscribers can retrieve the full %%% text of recent articles in PDF form. %%% %%% The initial draft was extracted from the ACM %%% Web pages. %%% %%% ACM copyrights explicitly permit abstracting %%% with credit, so article abstracts, keywords, %%% and subject classifications have been %%% included in this bibliography wherever %%% available. Article reviews have been %%% omitted, until their copyright status has %%% been clarified. %%% %%% bibsource keys in the bibliography entries %%% below indicate the entry originally came %%% from the computer science bibliography %%% archive, even though it has likely since %%% been corrected and updated. %%% %%% URL keys in the bibliography point to %%% World Wide Web locations of additional %%% information about the entry. %%% %%% BibTeX citation tags are uniformly chosen %%% as name:year:abbrev, where name is the %%% family name of the first author or editor, %%% year is a 4-digit number, and abbrev is a %%% 3-letter condensation of important title %%% words. Citation tags were automatically %%% generated by software developed for the %%% BibNet Project. %%% %%% In this bibliography, entries are sorted in %%% publication order, using ``bibsort -byvolume.'' %%% %%% The checksum field above contains a CRC-16 %%% checksum as the first value, followed by the %%% equivalent of the standard UNIX wc (word %%% count) utility output of lines, words, and %%% characters. This is produced by Robert %%% Solovay's checksum utility.", %%% } %%% ==================================================================== @Preamble{"\input bibnames.sty" # "\def \TM {${}^{\sc TM}$}" } %%% ==================================================================== %%% Acknowledgement abbreviations: @String{ack-nhfb = "Nelson H. F. Beebe, University of Utah, Department of Mathematics, 110 LCB, 155 S 1400 E RM 233, Salt Lake City, UT 84112-0090, USA, Tel: +1 801 581 5254, e-mail: \path|beebe@math.utah.edu|, \path|beebe@acm.org|, \path|beebe@computer.org| (Internet), URL: \path|https://www.math.utah.edu/~beebe/|"} %%% ==================================================================== %%% Journal abbreviations: @String{j-TOPC = "ACM Transactions on Parallel Computing (TOPC)"} %%% ==================================================================== %%% Bibliography entries: @Article{Gibbons:2014:ATP, author = "Phillip B. Gibbons", title = "{ACM Transactions on Parallel Computing}: an introduction", journal = j-TOPC, volume = "1", number = "1", pages = "1:1--1:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2661651", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Techniques", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lilja:2014:I, author = "David J. Lilja", title = "Introduction", journal = j-TOPC, volume = "1", number = "1", pages = "2:1--2:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2609798", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Rane:2014:EPO, author = "Ashay Rane and James Browne", title = "Enhancing Performance Optimization of Multicore\slash Multichip Nodes with Data Structure Metrics", journal = j-TOPC, volume = "1", number = "1", pages = "3:1--3:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2588788", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Program performance optimization is usually based solely on measurements of execution behavior of code segments using hardware performance counters. However, memory access patterns are critical performance limiting factors for today's multicore chips where performance is highly memory bound. Therefore diagnoses and selection of optimizations based only on measurements of the execution behavior of code segments are incomplete because they do not incorporate knowledge of memory access patterns and behaviors. This article presents a low-overhead tool (MACPO) that captures memory traces and computes metrics for the memory access behavior of source-level (C, C++, Fortran) data structures. MACPO explicitly targets the measurement and metrics important to performance optimization for multicore chips. The article also presents a complete process for integrating measurement and analyses of code execution with measurements and analyses of memory access patterns and behaviors for performance optimization, specifically targeting multicore chips and multichip nodes of clusters. MACPO uses more realistic cache models for computation of latency metrics than those used by previous tools. Evaluation of the effectiveness of adding memory access behavior characteristics of data structures to performance optimization was done on subsets of the ASCI, NAS and Rodinia parallel benchmarks and two versions of one application program from a domain not represented in these benchmarks. Adding characteristics of the behavior of data structures enabled easier diagnoses of bottlenecks and more accurate selection of appropriate optimizations than with only code centric behavior measurements. The performance gains ranged from a few percent to 38 percent.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jimenez:2014:APP, author = "V{\'\i}ctor Jim{\'e}nez and Francisco J. Cazorla and Roberto Gioiosa and Alper Buyuktosunoglu and Pradip Bose and Francis P. O'Connell and Bruce G. Mealey", title = "Adaptive Prefetching on {POWER7}: Improving Performance and Power Consumption", journal = j-TOPC, volume = "1", number = "1", pages = "4:1--4:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2588889", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Hardware data prefetch engines are integral parts of many general purpose server-class microprocessors in the field today. Some prefetch engines allow users to change some of their parameters. But, the prefetcher is usually enabled in a default configuration during system bring-up, and dynamic reconfiguration of the prefetch engine is not an autonomic feature of current machines. Conceptually, however, it is easy to infer that commonly used prefetch algorithms---when applied in a fixed mode---will not help performance in many cases. In fact, they may actually degrade performance due to useless bus bandwidth consumption and cache pollution, which in turn, will also waste power. We present an adaptive prefetch scheme that dynamically modifies the prefetch settings in order to adapt to workloads' requirements. We use a commercial processor, namely the IBM POWER7 as a vehicle for our study. First we characterize---in terms of performance and power consumption---the prefetcher in that processor using microbenchmarks and SPEC CPU2006. We then present our adaptive prefetch mechanism showing performance improvements with respect to the default prefetch setting up to 2.7X and 1.3X for single-threaded and multiprogrammed workloads, respectively. Adaptive prefetching is also able to reduce power consumption in some cases. Finally, we also evaluate our mechanism with SPECjbb2005, improving both performance and power consumption.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Heil:2014:APH, author = "Timothy Heil and Anil Krishna and Nicholas Lindberg and Farnaz Toussi and Steven Vanderwiel", title = "Architecture and Performance of the Hardware Accelerators in {IBM}'s {PowerEN} Processor", journal = j-TOPC, volume = "1", number = "1", pages = "5:1--5:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2588888", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Computation at the edge of a datacenter has unique characteristics. It deals with streaming data from multiple sources, going to multiple destinations, often requiring repeated application of one or more of several standard algorithmic kernels. These kernels, related to encryption, compression, XML Parsing and regular expression searching on the data, demand a high data processing rate and power efficiency. This suggests the use of hardware acceleration for key functions. However, robust general purpose processing support is necessary to orchestrate the flow of data between accelerators, as well as perform tasks that are not suited to acceleration. Further, these accelerators must be tightly integrated with the general purpose computation in order to keep invocation overhead and latency low. The accelerators must be easy for software to use, and the system must be flexible enough to support evolving networking standards. In this article, we describe and evaluate the architecture of IBM's PowerEN processor, with a focus on PowerEN's architectural enhancements and its on-chip hardware accelerators. PowerEN unites the throughput of application-specific accelerators with the programmability of general purpose cores on a single coherent memory architecture. Hardware acceleration improves throughput by orders of magnitude in some cases compared to equivalent computation on the general purpose cores. By offloading work to the accelerators, general purpose cores are freed to simultaneously work on computation less suited to acceleration.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Wu:2014:MAG, author = "Xing Wu and Frank Mueller and Scott Pakin", title = "A methodology for automatic generation of executable communication specifications from parallel {MPI} applications", journal = j-TOPC, volume = "1", number = "1", pages = "6:1--6:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2660249", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Portable parallel benchmarks are widely used for performance evaluation of HPC systems. However, because these are manually produced, they generally represent a greatly simplified view of application behavior, missing the subtle but important-to-performance nuances that may exist in a complete application. This work contributes novel methods to automatically generate highly portable and customizable communication benchmarks from HPC applications. We utilize ScalaTrace, a lossless yet scalable parallel-application tracing framework to collect selected aspects of the run-time behavior of HPC applications, including communication operations and computation time, while abstracting away the details of the computation proper. We subsequently generate benchmarks with nearly identical run-time behavior to the original applications. Results demonstrate that the generated benchmarks are in fact able to preserve the run-time behavior (including both the communication pattern and the execution time) of the original applications. Such automated benchmark generation is without precedent and particularly valuable for proprietary, export-controlled, or classified application codes.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ravishankar:2014:APC, author = "Mahesh Ravishankar and John Eisenlohr and Louis-No{\"e}l Pouchet and J. Ramanujam and Atanas Rountev and P. Sadayappan", title = "Automatic parallelization of a class of irregular loops for distributed memory systems", journal = j-TOPC, volume = "1", number = "1", pages = "7:1--7:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2660251", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Many scientific applications spend significant time within loops that are parallel, except for dependences from associative reduction operations. However these loops often contain data-dependent control-flow and array-access patterns. Traditional optimizations that rely on purely static analysis fail to generate parallel code in such cases. This article proposes an approach for automatic parallelization for distributed memory environments, using both static and runtime analysis. We formalize the computations that are targeted by this approach and develop algorithms to detect such computations. We also describe algorithms to generate a parallel inspector that performs a runtime analysis of control-flow and array-access patterns, and a parallel executor to take advantage of this information. The effectiveness of the approach is demonstrated on several benchmarks that were automatically transformed using a prototype compiler. For these, the inspector overheads and performance of the executor code were measured. The benefit on real-world applications was also demonstrated through similar manual transformations of an atmospheric modeling software.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Shun:2014:SPC, author = "Julian Shun and Guy E. Blelloch", title = "A simple parallel {Cartesian} tree algorithm and its application to parallel suffix tree construction", journal = j-TOPC, volume = "1", number = "1", pages = "8:1--8:??", month = sep, year = "2014", CODEN = "????", DOI = "https://doi.org/10.1145/2661653", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Oct 17 12:28:03 MDT 2014", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present a simple linear work and space, and polylogarithmic time parallel algorithm for generating multiway Cartesian trees. We show that bottom-up traversals of the multiway Cartesian tree on the interleaved suffix array and longest common prefix array of a string can be used to answer certain string queries. By adding downward pointers in the tree (e.g. using a hash table), we can also generate suffix trees from suffix arrays on arbitrary alphabets in the same bounds. In conjunction with parallel suffix array algorithms, such as the skew algorithm, this gives a rather simple linear work parallel, $ O(n \epsilon) $ time $ (0 < \epsilon < 1) $, algorithm for generating suffix trees over an integer alphabet $ \Sigma \{ 1, \ldots {}, n \} $, where $n$ is the length of the input string. It also gives a linear work parallel algorithm requiring $ O(\log_2 n) $ time with high probability for constant-sized alphabets. More generally, given a sorted sequence of strings and the longest common prefix lengths between adjacent elements, the algorithm will generate a patricia tree (compacted trie) over the strings. Of independent interest, we describe a work-efficient parallel algorithm for solving the all nearest smaller values problem using Cartesian trees, which is much simpler than the work-efficient parallel algorithm described in previous work. We also present experimental results comparing the performance of the algorithm to existing sequential implementations and a second parallel algorithm that we implement. We present comparisons for the Cartesian tree algorithm on its own and for constructing a suffix tree. The results show that on a variety of strings our algorithm is competitive with the sequential version on a single processor and achieves good speedup on multiple processors. We present experiments for three applications that require only the Cartesian tree, and also for searching using the suffix tree.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pingali:2015:ISI, author = "Keshav Pingali and J. Ramanujam and P. Sadayappan", title = "Introduction to the Special Issue on {PPoPP'12}", journal = j-TOPC, volume = "1", number = "2", pages = "9:1--9:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2716343", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bouteiller:2015:ABF, author = "Aurelien Bouteiller and Thomas Herault and George Bosilca and Peng Du and Jack Dongarra", title = "Algorithm-Based Fault Tolerance for Dense Matrix Factorizations, Multiple Failures and Accuracy", journal = j-TOPC, volume = "1", number = "2", pages = "10:1--10:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2686892", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/bibnet/authors/d/dongarra-jack-j.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Dense matrix factorizations, such as LU, Cholesky and QR, are widely used for scientific applications that require solving systems of linear equations, eigenvalues and linear least squares problems. Such computations are normally carried out on supercomputers, whose ever-growing scale induces a fast decline of the Mean Time To Failure (MTTF). This article proposes a new hybrid approach, based on Algorithm-Based Fault Tolerance (ABFT), to help matrix factorizations algorithms survive fail-stop failures. We consider extreme conditions, such as the absence of any reliable node and the possibility of losing both data and checksum from a single failure. We will present a generic solution for protecting the right factor, where the updates are applied, of all above mentioned factorizations. For the left factor, where the panel has been applied, we propose a scalable checkpointing algorithm. This algorithm features high degree of checkpointing parallelism and cooperatively utilizes the checksum storage leftover from the right factor protection. The fault-tolerant algorithms derived from this hybrid solution is applicable to a wide range of dense matrix factorizations, with minor modifications. Theoretical analysis shows that the fault tolerance overhead decreases inversely to the scaling in the number of computing units and the problem size. Experimental results of LU and QR factorization on the Kraken (Cray XT5) supercomputer validate the theoretical evaluation and confirm negligible overhead, with- and without-errors. Applicability to tolerate multiple failures and accuracy after multiple recovery is also considered.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ballard:2015:ACS, author = "Grey Ballard and James Demmel and Nicholas Knight", title = "Avoiding Communication in Successive Band Reduction", journal = j-TOPC, volume = "1", number = "2", pages = "11:1--11:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2686877", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The running time of an algorithm depends on both arithmetic and communication (i.e., data movement) costs, and the relative costs of communication are growing over time. In this work, we present sequential and distributed-memory parallel algorithms for tridiagonalizing full symmetric and symmetric band matrices that asymptotically reduce communication compared to previous approaches. The tridiagonalization of a symmetric band matrix is a key kernel in solving the symmetric eigenvalue problem for both full and band matrices. In order to preserve structure, tridiagonalization routines use annihilate-and-chase procedures that previously have suffered from poor data locality and high parallel latency cost. We improve both by reorganizing the computation and obtain asymptotic improvements. We also propose new algorithms for reducing a full symmetric matrix to band form in a communication-efficient manner. In this article, we consider the cases of computing eigenvalues only and of computing eigenvalues and all eigenvectors.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sack:2015:CAM, author = "Paul Sack and William Gropp", title = "Collective Algorithms for Multiported Torus Networks", journal = j-TOPC, volume = "1", number = "2", pages = "12:1--12:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2686882", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Modern supercomputers with torus networks allow each node to simultaneously pass messages on all of its links. However, most collective algorithms are designed to only use one link at a time. In this work, we present novel multiported algorithms for the scatter, gather, all-gather, and reduce-scatter operations. Our algorithms can be combined to create multiported reduce, all-reduce, and broadcast algorithms. Several of these algorithms involve a new technique where we relax the MPI message-ordering constraints to achieve high performance and restore the correct ordering using an additional stage of redundant communication. According to our models, on an $n$-dimensional torus, our algorithms should allow for nearly a $ 2 n$-fold improvement in communication performance compared to known, single-ported torus algorithms. In practice, we have achieved nearly $ 6 \times $ better performance on a 32k-node 3-dimensional torus.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dice:2015:LCG, author = "David Dice and Virendra J. Marathe and Nir Shavit", title = "Lock Cohorting: a General Technique for Designing {NUMA} Locks", journal = j-TOPC, volume = "1", number = "2", pages = "13:1--13:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2686884", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Multicore machines are quickly shifting to NUMA and CC-NUMA architectures, making scalable NUMA-aware locking algorithms, ones that take into account the machine's nonuniform memory and caching hierarchy, ever more important. This article presents lock cohorting, a general new technique for designing NUMA-aware locks that is as simple as it is powerful. Lock cohorting allows one to transform any spin-lock algorithm, with minimal nonintrusive changes,into a scalable NUMA-aware spin-lock. Our new cohorting technique allows us to easily create NUMA-aware versions of the TATAS-Backoff, CLH, MCS, and ticket locks, to name a few. Moreover, it allows us to derive a CLH-based cohort abortable lock, the first NUMA-aware queue lock to support abortability. We empirically compared the performance of cohort locks with prior NUMA-aware and classic NUMA-oblivious locks on a synthetic micro-benchmark, a real world key-value store application memcached, as well as the libc memory allocator. Our results demonstrate that cohort locks perform as well or better than known locks when the load is low and significantly out-perform them as the load increases.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Merrill:2015:HPS, author = "Duane Merrill and Michael Garland and Andrew Grimshaw", title = "High-Performance and Scalable {GPU} Graph Traversal", journal = j-TOPC, volume = "1", number = "2", pages = "14:1--14:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2717511", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Breadth-First Search (BFS) is a core primitive for graph traversal and a basis for many higher-level graph analysis algorithms. It is also representative of a class of parallel computations whose memory accesses and work distribution are both irregular and data dependent. Recent work has demonstrated the plausibility of GPU sparse graph traversal, but has tended to focus on asymptotically inefficient algorithms that perform poorly on graphs with nontrivial diameter. We present a BFS parallelization focused on fine-grained task management constructed from efficient prefix sum computations that achieves an asymptotically optimal O(|V| + |E|) gd work complexity. Our implementation delivers excellent performance on diverse graphs, achieving traversal rates in excess of 3.3 billion and 8.3 billion traversed edges per second using single- and quad-GPU configurations, respectively. This level of performance is several times faster than state-of-the-art implementations on both CPU and GPU platforms.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kramer:2015:SET, author = "Stephan C. Kramer and Johannes Hagemann", title = "{SciPAL}: Expression Templates and Composition Closure Objects for High Performance Computational Physics with {CUDA} and {OpenMP}", journal = j-TOPC, volume = "1", number = "2", pages = "15:1--15:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2686886", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present SciPAL (scientific parallel algorithms library), a C ++-based, hardware-independent open-source library. Its core is a domain-specific embedded language for numerical linear algebra. The main fields of application are finite element simulations, coherent optics and the solution of inverse problems. Using SciPAL algorithms can be stated in a mathematically intuitive way in terms of matrix and vector operations. Existing algorithms can easily be adapted to GPU-based computing by proper template specialization. Our library is compatible with the finite element library deal.II and provides a port of deal.II's most frequently used linear algebra classes to CUDA (NVidia's extension of the programming languages C and C ++ for programming their GPUs). SciPAL 's operator-based API for BLAS operations particularly aims at simplifying the usage of NVidia's CUBLAS. For non-BLAS array arithmetic SciPAL 's expression templates are able to generate CUDA kernels at compile time. We demonstrate the benefits of SciPAL using the iterative principal component analysis as example which is the core algorithm for the spike-sorting problem in neuroscience.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Totoni:2015:PME, author = "Ehsan Totoni and Nikhil Jain and Laxmikant V. Kale", title = "Power Management of Extreme-Scale Networks with On\slash Off Links in Runtime Systems", journal = j-TOPC, volume = "1", number = "2", pages = "16:1--16:??", month = jan, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2687001", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Feb 18 16:46:00 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Networks are among major power consumers in large-scale parallel systems. During execution of common parallel applications, a sizeable fraction of the links in the high-radix interconnects are either never used or are underutilized. We propose a runtime system based adaptive approach to turn off unused links, which has various advantages over the previously proposed hardware and compiler based approaches. We discuss why the runtime system is the best system component to accomplish this task, and test the effectiveness of our approach using real applications (including NAMD, MILC), and application benchmarks (including NAS Parallel Benchmarks, Stencil). These codes are simulated on representative topologies such as 6-D Torus and multilevel directly connected network (similar to IBM PERCS in Power 775 and Dragonfly in Cray Aries). For common applications with near-neighbor communication pattern, our approach can save up to 20\% of total machine's power and energy, without any performance penalty.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Herlihy:2015:GEI, author = "Maurice Herlihy", title = "{Guest Editor} Introduction", journal = j-TOPC, volume = "2", number = "1", pages = "1:1--1:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2716306", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Degener:2015:LCS, author = "Bastian Degener and Barbara Kempkes and Peter Kling and Friedhelm {Meyer Auf Der Heide}", title = "Linear and Competitive Strategies for Continuous Robot Formation Problems", journal = j-TOPC, volume = "2", number = "1", pages = "2:1--2:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742341", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We study a scenario in which n mobile robots with a limited viewing range are distributed in the Euclidean plane and have to solve a formation problem. The formation problems we consider are the Gathering problem and the Chain-Formation problem. In the Gathering problem, the robots have to gather in one (not predefined) point, while in the Chain-Formation problem they have to form a connected communication chain of minimal length between two stationary base stations. Each robot may base its decisions where to move only on the current relative positions of neighboring robots (that are within its viewing range); that is, besides having a limited viewing range, the robots are oblivious (they do not use information from the past), have none or only very limited identities, and they do not have a common sense of direction. Variants of these problems (especially for the Gathering problem) have been studied extensively in different discrete time models. In contrast, our work focuses on a continuous time model; that is, the robots continuously sense the positions of other robots within their viewing range and continuously adapt their speed and direction according to some simple, local rules. Hereby, we assume that the robots have a maximum movement speed of one. We show that this idealized idea of continuous sensing allows us to solve the mentioned formation problems in linear time $ O(n) $ (which, given the maximum speed of one, immediately yields a maximum traveled distance of $ O(n)$). Note that in the more classical discrete time models, the best known strategies need at least $ \Theta (n^2)$ or even $ \Theta (n^2 \log n)$ timesteps to solve these problems. For the Gathering problem, our analysis solves a problem left open by Gordon et al. [2004], where the authors could prove that gathering in a continuous model is possible in finite time, but were not able to give runtime bounds. Apart from these linear bounds, we also provide runtime bounds for both formation problems that relate the runtime of our strategies to the runtime of an optimal, global algorithm. Specifically, we show that our strategy for the Gathering problem is log OPT-competitive and the strategy for the Chain-Formation problem is $ \log n$ competitive. Here, by $c$-competitive, we mean that our (local) strategy is asymptotically by at most a factor of $c$ slower than an optimal, global strategy.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jain:2015:NOS, author = "Navendu Jain and Ishai Menache and Joseph (Seffi) Naor and Jonathan Yaniv", title = "Near-Optimal Scheduling Mechanisms for Deadline-Sensitive Jobs in Large Computing Clusters", journal = j-TOPC, volume = "2", number = "1", pages = "3:1--3:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742343", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We consider a market-based resource allocation model for batch jobs in cloud computing clusters. In our model, we incorporate the importance of the due date of a job rather than the number of servers allocated to it at any given time. Each batch job is characterized by the work volume of total computing units (e.g., CPU hours) along with a bound on maximum degree of parallelism. Users specify, along with these job characteristics, their desired due date and a value for finishing the job by its deadline. Given this specification, the primary goal is to determine the scheduling of cloud computing instances under capacity constraints in order to maximize the social welfare (i.e., sum of values gained by allocated users). Our main result is a new (CC-kcss-1)-approximation algorithm for this objective, where $C$ denotes cloud capacity, $k$ is the maximal bound on parallelized execution (in practical settings, $ k < C$) and $s$ is the slackness on the job completion time, that is, the minimal ratio between a specified deadline and the earliest finish time of a job. Our algorithm is based on utilizing dual fitting arguments over a strengthened linear program to the problem. Based on the new approximation algorithm, we construct truthful allocation and pricing mechanisms, in which reporting the true value and other properties of the job (deadline, work volume, and the parallelism bound) is a dominant strategy for all users. To that end, we extend known results for single-value settings to provide a general framework for transforming allocation algorithms into truthful mechanisms in domains of single-value and multi-properties. We then show that the basic mechanism can be extended under proper Bayesian assumptions to the objective of maximizing revenues, which is important for public clouds. We empirically evaluate the benefits of our approach through simulations on data-center job traces, and show that the revenues obtained under our mechanism are comparable with an ideal fixed-price mechanism, which sets an on-demand price using oracle knowledge of users' valuations. Finally, we discuss how our model can be extended to accommodate uncertainties in job work volumes, which is a practical challenge in cloud settings.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Feldman:2015:HCG, author = "Moran Feldman and Liane Lewin-Eytan and Joseph (Seffi) Naor", title = "Hedonic Clustering Games", journal = j-TOPC, volume = "2", number = "1", pages = "4:1--4:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742345", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Clustering, the partitioning of objects with respect to a similarity measure, has been extensively studied as a global optimization problem. We investigate clustering from a game-theoretic approach, and consider the class of hedonic clustering games. Here, a self-organized clustering is obtained via decisions made by independent players, corresponding to the elements clustered. Being a hedonic setting, the utility of each player is determined by the identity of the other members of her cluster. This class of games seems to be quite robust, as it fits with rather different, yet commonly used, clustering criteria. Specifically, we investigate hedonic clustering games in two different models: fixed clustering, which subdivides into $k$-median and $k$-center, and correlation clustering. We provide a thorough analysis of these games, characterizing Nash equilibria, and proving upper and lower bounds on the price of anarchy and price of stability. For fixed clustering we focus on the existence of a Nash equilibrium, as it is a rather nontrivial issue in this setting. We study it both for general metrics and special cases, such as line and tree metrics. In the correlation clustering model, we study both minimization and maximization variants, and provide almost tight bounds on both the price of anarchy and price of stability.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jahn:2015:RRA, author = "Janmartin Jahn and Santiago Pagani and Sebastian Kobbe and Jian-Jia Chen and J{\"o}rg Henkel", title = "Runtime Resource Allocation for Software Pipelines", journal = j-TOPC, volume = "2", number = "1", pages = "5:1--5:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742347", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Efficiently allocating the computational resources of many-core systems is one of the most prominent challenges, especially when resource requirements may vary unpredictably at runtime. This is even more challenging when facing unreliable cores --- a scenario that becomes common as the number of cores increases and integration sizes shrink. To address this challenge, this article presents an optimal method for the allocation of the resources to software-pipelined applications. Here we show how runtime observations of the resource requirements of tasks can be used to adapt resource allocations. Furthermore, we show how the optimum can be traded for a high degree of scalability by clustering applications in a distributed, hierarchical manner. To diminish the negative effects of unreliable cores, this article shows how self-organization can effectively restore the integrity of such a hierarchy when it is corrupted by a failing core. Experiments on Intel's 48-core Single-Chip Cloud Computer and in a many-core simulator show that a significant improvement in system throughput can be achieved over the current state of the art.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Xu:2015:SVC, author = "Yi Xu and Bo Zhao and Youtao Zhang and Jun Yang", title = "Simple Virtual Channel Allocation for High-Throughput and High-Frequency On-Chip Routers", journal = j-TOPC, volume = "2", number = "1", pages = "6:1--6:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742349", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Packet-switched network-on-chip (NoC) has provided a scalable solution to the communications for tiled multicore processors. However, the virtual channel (VC) buffers in the NoC consume significant dynamic and leakage power. To improve the energy efficiency of the router design, it is advantageous to use small buffer sizes while still maintaining throughput of the network. This article proposes two new virtual channel allocation (VA) mechanisms, termed fixed VC assignment with dynamic VC allocation (FVADA) and adjustable VC assignment with dynamic VC allocation (AVADA). VCs are designated to output ports and allocated to packets according to such assignment. This can help to reduce the head-of-line blocking. Such VC-output port assignment can also be adjusted dynamically to accommodate traffic changes. Simulation results show that both mechanisms can improve network throughput by 41\% on average. Real traffic evaluation shows a network latency reduction of up to 66\%. In addition, AVADA can outperform the baseline in throughput with only half of the buffer size. Finally, we are able to achieve comparable or better throughput than a previous dynamic VC allocator while reducing its critical path delay by 57\%. Hence, the proposed VA mechanisms are suitable for low-power, high-throughput, and high-frequency NoC designs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hammouda:2015:NTE, author = "Adam Hammouda and Andrew R. Siegel and Stephen F. Siegel", title = "Noise-Tolerant Explicit Stencil Computations for Nonuniform Process Execution Rates", journal = j-TOPC, volume = "2", number = "1", pages = "7:1--7:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742351", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Next-generation HPC computing platforms are likely to be characterized by significant, unpredictable nonuniformities in execution time among compute nodes and cores. The resulting load imbalances from this nonuniformity are expected to arise from a variety of sources-manufacturing discrepancies, dynamic power management, runtime component failure, OS jitter, software-mediated resiliency, and TLB/- cache performance variations, for example. It is well understood that existing algorithms with frequent points of bulk synchronization will perform relatively poorly in the presence of these sources of process nonuniformity. Thus, recasting classic bulk synchronous algorithms into more asynchronous, coarse-grained parallelism is a critical area of research for next-generation computing. We propose a class of parallel algorithms for explicit stencil computations that can tolerate these nonuniformities by decoupling per process communication and computation in order for each process to progress asynchronously while maintaining solution correctness. These algorithms are benchmarked with a $1$D domain decomposed (``slabbed'') implementation of the $2$D heat equation as a model problem, and are tested in the presence of simulated nonuniform process execution rates. The resulting performance is compared to a classic bulk synchronous implementation of the model problem. Results show that the runtime of this article's algorithm on a machine with simulated process nonuniformities is 5--99\% slower than the runtime of its classic counterpart on a machine free of nonuniformities. However, when both algorithms are run on a machine with comparable synthetic process nonuniformities, this article's algorithm is 1--37 times faster than its classic counterpart.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{McCreesh:2015:SST, author = "Ciaran McCreesh and Patrick Prosser", title = "The Shape of the Search Tree for the Maximum Clique Problem and the Implications for Parallel Branch and Bound", journal = j-TOPC, volume = "2", number = "1", pages = "8:1--8:??", month = may, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2742359", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu May 21 16:27:00 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Finding a maximum clique in a given graph is one of the fundamental NP-hard problems. We compare two multicore thread-parallel adaptations of a state-of-the-art branch-and-bound algorithm for the maximum clique problem and provide a novel explanation as to why they are successful. We show that load balance is sometimes a problem but that the interaction of parallel search order and the most likely location of solutions within the search space is often the dominating consideration. We use this explanation to propose a new low-overhead, scalable work-splitting mechanism. Our approach uses explicit early diversity to avoid strong commitment to the weakest heuristic advice and late resplitting for balance. More generally, we argue that, for branch-and-bound, parallel algorithm design should not be performed independently of the underlying sequential algorithm.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hoefler:2015:RMA, author = "Torsten Hoefler and James Dinan and Rajeev Thakur and Brian Barrett and Pavan Balaji and William Gropp and Keith Underwood", title = "Remote Memory Access Programming in {MPI-3}", journal = j-TOPC, volume = "2", number = "2", pages = "9:1--9:??", month = jul, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2780584", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Aug 7 10:22:35 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The Message Passing Interface (MPI) 3.0 standard, introduced in September 2012, includes a significant update to the one-sided communication interface, also known as remote memory access (RMA). In particular, the interface has been extended to better support popular one-sided and global-address-space parallel programming models to provide better access to hardware performance features and enable new data-access modes. We present the new RMA interface and specify formal axiomatic models for data consistency and access semantics. Such models can help users reason about details of the semantics that are hard to extract from the English prose in the standard. It also fosters the development of tools and compilers, enabling them to automatically analyze, optimize, and debug RMA programs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Maldonado:2015:STB, author = "Walther Maldonado and Patrick Marlier and Pascal Felber and Julia Lawall and Gilles Muller and Etienne Rivi{\`e}re", title = "Supporting Time-Based {QoS} Requirements in Software Transactional Memory", journal = j-TOPC, volume = "2", number = "2", pages = "10:1--10:??", month = jul, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2779621", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Aug 7 10:22:35 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Software transactional memory (STM) is an optimistic concurrency control mechanism that simplifies parallel programming. However, there has been little interest in its applicability to reactive applications in which there is a required response time for certain operations. We propose supporting such applications by allowing programmers to associate time with atomic blocks in the form of deadlines and quality-of-service (QoS) requirements. Based on statistics of past executions, we adjust the execution mode of transactions by decreasing the level of optimism as the deadline approaches. In the presence of concurrent deadlines, we propose different conflict resolution policies. Execution mode switching mechanisms allow the meeting of multiple deadlines in a consistent manner, with potential QoS degradations being split fairly among several threads as contention increases, and avoiding starvation. Our implementation consists of extensions to an STM runtime that allow gathering statistics and switching execution modes. We also propose novel contention managers adapted to transactional workloads subject to deadlines. The experimental evaluation shows that our approaches significantly improve the likelihood of a transaction meeting its deadline and QoS requirement, even in cases where progress is hampered by conflicts and other concurrent transactions with deadlines.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kestor:2015:TPD, author = "Gokcen Kestor and Osman S. Unsal and Adrian Cristal and Serdar Tasiran", title = "{TRADE}: Precise Dynamic Race Detection for Scalable Transactional Memory Systems", journal = j-TOPC, volume = "2", number = "2", pages = "11:1--11:??", month = jul, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2786021", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Aug 7 10:22:35 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "As other multithreaded programs, transactional memory (TM) programs are prone to race conditions. Previous work focuses on extending existing definitions of data race for lock-based applications to TM applications, which requires all transactions to be totally ordered ``as if'' serialized by a global lock. This approach poses implementation constraints on the STM that severely limits TM applications' performance. This article shows that forcing total ordering among all running transactions, while sufficient, is not necessary. We introduce an alternative data race definition, relaxed transactional data race, that requires ordering of only conflicting transactions. The advantages of our relaxed definition are twofold: First, unlike the previous definition, this definition can be applied to a wide range of TMs, including those that do not enforce transaction total ordering. Second, within a single execution, it exposes a higher number of data races, which considerably reduces debugging time. Based on this definition, we propose a novel and precise race detection tool for C/C++ TM applications (TRADE), which detects data races by tracking happens-before edges among conflicting transactions. Our experiments reveal that TRADE precisely detects data races for STAMP applications running on modern STMs with overhead comparable to state-of-the-art race detectors for lock-based applications. Our experiments also show that in a single run, TRADE identifies several races not discovered by 10 separate runs of a race detection tool based on the previous data race definition.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Diegues:2015:TWE, author = "Nuno Diegues and Paolo Romano", title = "{Time-Warp}: Efficient Abort Reduction in Transactional Memory", journal = j-TOPC, volume = "2", number = "2", pages = "12:1--12:??", month = jul, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2775435", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Aug 7 10:22:35 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The multicore revolution that took place one decade ago has turned parallel programming into a major concern for the mainstream software development industry. In this context, Transactional Memory (TM) has emerged as a simpler and attractive alternative to that of lock-based synchronization, whose complexity and error-proneness are widely recognized. The notion of permissiveness in TM translates to only aborting a transaction when it cannot be accepted in any history that guarantees a target correctness criterion. This theoretically powerful property is often neglected by state-of-the-art TMs because it imposes considerable algorithmic costs. Instead, these TMs opt to maximize their implementation's efficiency by aborting transactions under overly conservative conditions. As a result, they risk rejecting a significant number of safe executions. In this article, we seek to identify a sweet spot between permissiveness and efficiency by introducing the Time-Warp Multiversion (TWM) algorithm. TWM is based on the key idea of allowing an update transaction that has performed stale reads (i.e., missed the writes of concurrently committed transactions) to be serialized by ``committing it in the past,'' which we call a time-warp commit. At its core, TWM uses a novel, lightweight validation mechanism with little computational overhead. TWM also guarantees that read-only transactions can never be aborted. Further, TWM guarantees Virtual World Consistency, a safety property that is deemed as particularly relevant in the context of TM. We demonstrate the practicality of this approach through an extensive experimental study: we compare TWM with five other TMs, representative of typical alternative design choices, and on a wide variety of benchmarks. This study shows an average performance improvement across all considered workloads and TMs of 65\% in high concurrency scenarios, with gains extending up to $ 9 \times $ with the most favorable benchmarks. These results are a consequence of TWM's ability to achieve drastic reduction of aborts in scenarios of nonminimal contention, while introducing little overhead (approximately 10\%) in worst-case, synthetically designed scenarios (i.e., no contention or contention patterns that cannot be optimized using TWM).", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Eyraud-Dubois:2015:PST, author = "Lionel Eyraud-Dubois and Loris Marchal and Oliver Sinnen and Fr{\'e}d{\'e}ric Vivien", title = "Parallel Scheduling of Task Trees with Limited Memory", journal = j-TOPC, volume = "2", number = "2", pages = "13:1--13:??", month = jul, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2779052", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Aug 7 10:22:35 MDT 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "This article investigates the execution of tree-shaped task graphs using multiple processors. Each edge of such a tree represents some large data. A task can only be executed if all input and output data fit into memory, and a data can only be removed from memory after the completion of the task that uses it as an input data. Such trees arise in the multifrontal method of sparse matrix factorization. The peak memory needed for the processing of the entire tree depends on the execution order of the tasks. With one processor, the objective of the tree traversal is to minimize the required memory. This problem was well studied, and optimal polynomial algorithms were proposed. Here, we extend the problem by considering multiple processors, which is of obvious interest in the application area of matrix factorization. With multiple processors comes the additional objective to minimize the time needed to traverse the tree-that is, to minimize the makespan. Not surprisingly, this problem proves to be much harder than the sequential one. We study the computational complexity of this problem and provide inapproximability results even for unit weight trees. We design a series of practical heuristics achieving different trade-offs between the minimization of peak memory usage and makespan. Some of these heuristics are able to process a tree while keeping the memory usage under a given memory limit. The different heuristics are evaluated in an extensive experimental evaluation using realistic trees.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dinitz:2015:ISI, author = "Michael Dinitz and Torsten Hoefler", title = "Introduction to the Special Issue on {SPAA 2013}", journal = j-TOPC, volume = "2", number = "3", pages = "14:1--14:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809923", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14e", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kumar:2015:FGA, author = "Ravi Kumar and Benjamin Moseley and Sergei Vassilvitskii and Andrea Vattani", title = "Fast Greedy Algorithms in {MapReduce} and Streaming", journal = j-TOPC, volume = "2", number = "3", pages = "14:1--14:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809814", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Greedy algorithms are practitioners' best friends---they are intuitive, are simple to implement, and often lead to very good solutions. However, implementing greedy algorithms in a distributed setting is challenging since the greedy choice is inherently sequential, and it is not clear how to take advantage of the extra processing power. Our main result is a powerful sampling technique that aids in parallelization of sequential algorithms. Armed with this primitive, we then adapt a broad class of greedy algorithms to the MapReduce paradigm; this class includes maximum cover and submodular maximization subject to p -system constraint problems. Our method yields efficient algorithms that run in a logarithmic number of rounds while obtaining solutions that are arbitrarily close to those produced by the standard sequential greedy algorithm. We begin with algorithms for modular maximization subject to a matroid constraint and then extend this approach to obtain approximation algorithms for submodular maximization subject to knapsack or p -system constraints.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sanders:2015:WEM, author = "Peter Sanders and Jochen Speck and Raoul Steffen", title = "Work-Efficient Matrix Inversion in Polylogarithmic Time", journal = j-TOPC, volume = "2", number = "3", pages = "15:1--15:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809812", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present an algorithm for inversion of symmetric positive definite matrices that combines the practical requirement of an optimal number of arithmetic operations and the theoretical goal of a polylogarithmic critical path length. The algorithm reduces inversion to matrix multiplication. It uses Strassen's recursion scheme, but on the critical path it breaks the recursion early, switching to an asymptotically inefficient yet fast use of Newton's method. We also show that the algorithm is numerically stable. Overall, we get a candidate for a massively parallel algorithm that scales to exascale systems even on relatively small inputs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Gilbert:2015:SBO, author = "Seth Gilbert and Chaodong Zheng", title = "{SybilCast}: Broadcast on the Open Airwaves", journal = j-TOPC, volume = "2", number = "3", pages = "16:1--16:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809810", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Consider a scenario where many wireless users are attempting to download data from a single base station. While most of the users are honest, some users may be malicious and attempt to obtain more than their fair share of the bandwidth. One possible strategy for attacking the system is to simulate multiple fake identities, each of which is given its own equal share of the bandwidth. Such an attack is often referred to as a sybil attack. To counter such behavior, we propose SybilCast, a protocol for multichannel wireless networks that limits the number of fake identities and, in doing so, ensures that each honest user gets at least a constant fraction of his or her fair share of the bandwidth. As a result, each honest user can complete his or her data download in asymptotically optimal time. A key aspect of this protocol is balancing the rate at which new identities are admitted and the maximum number of fake identities that can coexist while keeping the overhead low. Besides sybil attacks, our protocol can also tolerate spoofing and jamming.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lee:2015:FPP, author = "I-Ting Angelina Lee and Charles E. Leiserson and Tao B. Schardl and Zhunping Zhang and Jim Sukha", title = "On-the-Fly Pipeline Parallelism", journal = j-TOPC, volume = "2", number = "3", pages = "17:1--17:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809808", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Pipeline parallelism organizes a parallel program as a linear sequence of stages. Each stage processes elements of a data stream, passing each processed data element to the next stage, and then taking on a new element before the subsequent stages have necessarily completed their processing. Pipeline parallelism is used especially in streaming applications that perform video, audio, and digital signal processing. Three out of 13 benchmarks in PARSEC, a popular software benchmark suite designed for shared-memory multiprocessors, can be expressed as pipeline parallelism. Whereas most concurrency platforms that support pipeline parallelism use a ``construct-and-run'' approach, this article investigates ``on-the-fly'' pipeline parallelism, where the structure of the pipeline emerges as the program executes rather than being specified a priori. On-the-fly pipeline parallelism allows the number of stages to vary from iteration to iteration and dependencies to be data dependent. We propose simple linguistics for specifying on-the-fly pipeline parallelism and describe a provably efficient scheduling algorithm, the P iper algorithm, which integrates pipeline parallelism into a work-stealing scheduler, allowing pipeline and fork-join parallelism to be arbitrarily nested. The Piper algorithm automatically throttles the parallelism, precluding ``runaway'' pipelines. Given a pipeline computation with $ T_1 $ work and $ T_\infty $ span (critical-path length), Piper executes the computation on $P$ processors in $ T_P \leq T_1 / P + O(T \infty + \lg P)$ expected time. Piper also limits stack space, ensuring that it does not grow unboundedly with running time. We have incorporated on-the-fly pipeline parallelism into a Cilk-based work-stealing runtime system. Our prototype Cilk-P implementation exploits optimizations such as ``lazy enabling'' and ``dependency folding.'' We have ported the three PARSEC benchmarks that exhibit pipeline parallelism to run on Cilk-P. One of these, x264, cannot readily be executed by systems that support only construct-and-run pipeline parallelism. Benchmark results indicate that Cilk-P has low serial overhead and good scalability. On x264, for example, Cilk-P exhibits a speedup of 13.87 over its respective serial counterpart when running on 16 processors.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Eikel:2015:IRI, author = "Martina Eikel and Christian Scheideler", title = "{IRIS}: a Robust Information System Against Insider {DoS} Attacks", journal = j-TOPC, volume = "2", number = "3", pages = "18:1--18:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809806", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this work, we present the first scalable distributed information system, that is, a system with low storage overhead, that is provably robust against denial-of-service (DoS) attacks by a current insider. We allow a current insider to have complete knowledge about the information system and to have the power to block any \varepsilon-fraction of its servers by a DoS attack, where \varepsilon can be chosen up to a constant. The task of the system is to serve any collection of lookup requests with at most one per nonblocked server in an efficient way despite this attack. Previously, scalable solutions were only known for DoS attacks of past insiders, where a past insider only has complete knowledge about some past time point $ t_0 $ of the information system. Scheideler et al. [Awerbuch and Scheideler 2007; Baumgart et al. 2009] showed that in this case, it is possible to design an information system so that any information that was inserted or last updated after $ t_0 $ is safe against a DoS attack. But their constructions would not work at all for a current insider. The key idea behind our IRIS system is to make extensive use of coding. More precisely, we present two alternative distributed coding strategies with an at most logarithmic storage overhead that can handle up to a constant fraction of blocked servers.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kling:2015:PSM, author = "Peter Kling and Peter Pietrzyk", title = "Profitable Scheduling on Multiple Speed-Scalable Processors", journal = j-TOPC, volume = "2", number = "3", pages = "19:1--19:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2809872", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present a new online algorithm for profit-oriented scheduling on multiple speed-scalable processors and provide a tight analysis of the algorithm's competitiveness. Our results generalize and improve upon work by Chan et al. [2010], which considers a single speed-scalable processor. Using significantly different techniques, we can not only extend their model to multiprocessors but also prove an enhanced and tight competitive ratio for our algorithm. In our scheduling problem, jobs arrive over time and are preemptable. They have different workloads, values, and deadlines. The scheduler may decide not to finish a job but instead to suffer a loss equaling the job's value. However, to process a job's workload until its deadline the scheduler must invest a certain amount of energy. The cost of a schedule is the sum of lost values and invested energy. In order to finish a job, the scheduler has to determine which processors to use and set their speeds accordingly. A processor's energy consumption is power $ P_\alpha (s) $ integrated over time, where $ P_\alpha (s) = s^\alpha $ is the power consumption when running at speed $s$. Since we consider the online variant of the problem, the scheduler has no knowledge about future jobs. This problem was introduced by Chan et al. [2010] for the case of a single processor. They presented an online algorithm that is $ \alpha^\alpha + 2 e \alpha $-competitive. We provide an online algorithm for the case of multiple processors with an improved competitive ratio of $ \alpha^\alpha $.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dutta:2015:CBR, author = "Chinmoy Dutta and Gopal Pandurangan and Rajmohan Rajaraman and Scott Roche", title = "Coalescing-Branching Random Walks on Graphs", journal = j-TOPC, volume = "2", number = "3", pages = "20:1--20:??", month = oct, year = "2015", CODEN = "????", DOI = "https://doi.org/10.1145/2817830", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Nov 3 07:30:42 MST 2015", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We study a distributed randomized information propagation mechanism in networks we call the coalescing-branching random walk (cobra walk, for short). A cobra walk is a generalization of the well-studied ``standard'' random walk, and is useful in modeling and understanding the Susceptible-Infected- Susceptible (SIS)-type of epidemic processes in networks. It can also be helpful in performing light-weight information dissemination in resource-constrained networks. A cobra walk is parameterized by a branching factor $k$. The process starts from an arbitrary vertex, which is labeled active for step 1. In each step of a cobra walk, each active vertex chooses $k$ random neighbors to become active for the next step (``branching''). A vertex is active for step $ t + 1$ only if it is chosen by an active vertex in step $t$ (``coalescing''). This results in a stochastic process in the underlying network with properties that are quite different from both the standard random walk (which is equivalent to the cobra walk with branching factor 1) as well as other gossip-based rumor spreading mechanisms. We focus on the cover time of the cobra walk, which is the number of steps for the walk to reach all the vertices, and derive almost-tight bounds for various graph classes. We show an $ O(\log^2 n)$ high probability bound for the cover time of cobra walks on expanders, if either the expansion factor or the branching factor is sufficiently large; we also obtain an $ O(\log n)$ high probability bound for the partial cover time, which is the number of steps needed for the walk to reach at least a constant fraction of the vertices. We also show that the cover time of the cobra walk is, with high probability, $ O(n \log n)$ on any $n$-vertex tree for $ k \geq 2$, $ {\~ O}(n^{1 / d})$ on a $d$-dimensional grid for $ k \geq 2$, and $ O(\log n)$ on the complete graph.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Larus:2016:ISI, author = "James Larus and Sandhya Dwarkadas and Jos{\'e} Moreira and Andrew Lumsdaine", title = "Introduction to the Special Issue on {PPoPP'14}", journal = j-TOPC, volume = "2", number = "4", pages = "21:1--21:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2856513", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Herlihy:2016:WSF, author = "Maurice Herlihy and Zhiyu Liu", title = "Well-Structured Futures and Cache Locality", journal = j-TOPC, volume = "2", number = "4", pages = "22:1--22:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2858650", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In fork-join parallelism, a sequential program is split into a directed acyclic graph of tasks linked by directed dependency edges, and the tasks are executed, possibly in parallel, in an order consistent with their dependencies. A popular and effective way to extend fork-join parallelism is to allow threads to create futures. A thread creates a future to hold the results of a computation, which may or may not be executed in parallel. That result is returned when some thread touches that future, blocking if necessary until the result is ready. Recent research has shown that although futures can, of course, enhance parallelism in a structured way, they can have a deleterious effect on cache locality. In the worst case, futures can incur $ \Omega (P T_\infty + t T_\infty) $ deviations, which implies $ \Omega (C P T_\infty + C t T_\infty) $ additional cache misses, where $C$ is the number of cache lines, $P$ is the number of processors, $t$ is the number of touches, and $ T_\infty $ is the computation span. Since cache locality has a large impact on software performance on modern multicores, this result is troubling. In this article, we show that if futures are used in a simple, disciplined way, then the situation is much better: if each future is touched only once, either by the thread that created it or by a later descendant of the thread that created it, then parallel executions with work stealing can incur at most $ O(C P T^2_\infty)$ additional cache misses-a substantial improvement. This structured use of futures is characteristic of many (but not all) parallel applications.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Thomson:2016:CTU, author = "Paul Thomson and Alastair F. Donaldson and Adam Betts", title = "Concurrency Testing Using Controlled Schedulers: an Empirical Study", journal = j-TOPC, volume = "2", number = "4", pages = "23:1--23:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2858651", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present an independent empirical study on concurrency testing using controlled schedulers. We have gathered 49 buggy concurrent software benchmarks, drawn from public code bases, which we call SCTBench. We applied a modified version of an existing concurrency testing tool to SCTBench, testing five controlled scheduling techniques: depth-first search, preemption bounding, delay bounding, a controlled random scheduler, and probabilistic concurrency testing (PCT). We attempt to answer several research questions: Which technique performs the best, in terms of bug finding ability? How effective are the two main schedule bounding techniques-preemption bounding and delay bounding-at finding bugs? What challenges are associated with applying concurrency testing techniques to existing code? Can we classify certain benchmarks as trivial or nontrivial? Overall, we found that PCT (with parameter d = 3) was the most effective technique in terms of bug finding; it found all bugs found by the other techniques, plus an additional three, and it missed only one bug. Surprisingly, we found that the naive controlled random scheduler, which randomly chooses one thread to execute at each scheduling point, performs well, finding more bugs than preemption bounding and just two fewer bugs than delay bounding. Our findings confirm that delay bounding is superior to preemption bounding and that schedule bounding is superior to an unbounded depth-first search. The majority of bugs in SCTBench can be exposed using a small schedule bound (1--2), supporting previous claims, although one benchmark requires five preemptions. We found that the need to remove nondeterminism and control all synchronization (as is required for systematic concurrency testing) can be nontrivial. There were eight distinct programs that could not easily be included in out study, such as those that perform network and interprocess communication. We report various properties about the benchmarks tested, such as the fact that the bugs in 18 benchmarks were exposed 50\% of the time when using random scheduling. We note that future work should not use the benchmarks that we classify as trivial when presenting new techniques, other than as a minimum baseline. We have made SCTBench and our tools publicly available for reproducibility and use in future work.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "23", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Petrovic:2016:LHM, author = "Darko Petrovi{\'c} and Thomas Ropars and Andr{\'e} Schiper", title = "Leveraging Hardware Message Passing for Efficient Thread Synchronization", journal = j-TOPC, volume = "2", number = "4", pages = "24:1--24:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2858652", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "As the level of parallelism in manycore processors keeps increasing, providing efficient mechanisms for thread synchronization in concurrent programs is becoming a major concern. On cache-coherent shared-memory processors, synchronization efficiency is ultimately limited by the performance of the underlying cache coherence protocol. This article studies how hardware support for message passing can improve synchronization performance. Considering the ubiquitous problem of mutual exclusion, we devise novel algorithms for (i) classic locking, where application threads obtain exclusive access to a shared resource prior to executing their critical sections (CSes), and (ii) delegation, where CSes are executed by special threads. For classic locking, our HybLock algorithm uses a mix of shared memory and hardware message passing, which introduces the idea of hybrid synchronization algorithms. For delegation, we propose mp-server and HybComb: the former is a straightforward adaptation of the server approach to hardware message passing, whereas the latter is a novel hybrid combining algorithm. Evaluation on Tilera's TILE-Gx processor shows that HybLock outperforms the best known classic locks. Furthermore, mp-server can execute contended CSes with unprecedented throughput, as stalls related to cache coherence are removed from the critical path. HybComb can achieve comparable performance while avoiding the need to dedicate server cores. Consequently, our queue and stack implementations, based on the new synchronization algorithms, largely outperform their most efficient shared-memory-only counterparts.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "24", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Tardieu:2016:XAP, author = "Olivier Tardieu and Benjamin Herta and David Cunningham and David Grove and Prabhanjan Kambadur and Vijay Saraswat and Avraham Shinnar and Mikio Takeuchi and Mandana Vaziri and Wei Zhang", title = "{X10} and {APGAS} at Petascale", journal = j-TOPC, volume = "2", number = "4", pages = "25:1--25:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2894746", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "X10 is a high-performance, high-productivity programming language aimed at large-scale distributed and shared-memory parallel applications. It is based on the Asynchronous Partitioned Global Address Space (APGAS) programming model, supporting the same fine-grained concurrency mechanisms within and across shared-memory nodes. We demonstrate that X10 delivers solid performance at petascale by running (weak scaling) eight application kernels on an IBM Power--775 supercomputer utilizing up to 55,680 Power7 cores (for 1.7Pflop/s of theoretical peak performance). For the four HPC Class 2 Challenge benchmarks, X10 achieves 41\% to 87\% of the system's potential at scale (as measured by IBM's HPCC Class 1 optimized runs). We also implement K-Means, Smith-Waterman, Betweenness Centrality, and Unbalanced Tree Search (UTS) for geometric trees. Our UTS implementation is the first to scale to petaflop systems. We describe the advances in distributed termination detection, distributed load balancing, and use of high-performance interconnects that enable X10 to scale out to tens of thousands of cores. We discuss how this work is driving the evolution of the X10 language, core class libraries, and runtime systems.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "25", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Maleki:2016:LRM, author = "Saeed Maleki and Madanlal Musuvathi and Todd Mytkowicz", title = "Low-Rank Methods for Parallelizing Dynamic Programming Algorithms", journal = j-TOPC, volume = "2", number = "4", pages = "26:1--26:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2884065", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "This article proposes efficient parallel methods for an important class of dynamic programming problems that includes Viterbi, Needleman--Wunsch, Smith--Waterman, and Longest Common Subsequence. In dynamic programming, the subproblems that do not depend on each other, and thus can be computed in parallel, form stages or wavefronts. The methods presented in this article provide additional parallelism allowing multiple stages to be computed in parallel despite dependencies among them. The correctness and the performance of the algorithm relies on rank convergence properties of matrix multiplication in the tropical semiring, formed with plus as the multiplicative operation and max as the additive operation. This article demonstrates the efficiency of the parallel algorithm by showing significant speedups on a variety of important dynamic programming problems. In particular, the parallel Viterbi decoder is up to $ 24 \times $ faster (with 64 processors) than a highly optimized commercial baseline.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "26", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Yuan:2016:FCN, author = "Xin Yuan and Wickus Nienaber and Santosh Mahapatra", title = "On Folded-{Clos} Networks with Deterministic Single-Path Routing", journal = j-TOPC, volume = "2", number = "4", pages = "27:1--27:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2858654", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Folded-Clos networks, also known as fat-trees, have been widely used as interconnects in large-scale high-performance computing clusters. Although users often treat such interconnects as replacements of nonblocking crossbar switches that can carry out any permutation communication without contention, the networking capability of such interconnects without a centralized controller in computer communication environments is not well understood. In this article, we investigate nonblocking two-level folded-Clos networks with deterministic single-path routing, but no centralized controller, and establish the nonblocking condition. The results indicate that nonblocking two-level folded-Clos networks without a centralized controller are much more expensive to construct than the traditional nonblocking networks in the telecommunication environment. Practical two-level folded-Clos based interconnects are blocking. For such interconnects, we establish the lower bound for worst-case contention for permutations with any deterministic single-path routing scheme, show that existing routing schemes perform poorly in terms of worst-case contention for permutations, present a routing scheme that achieves the theoretical optimal, and empirically compare the performance of existing schemes with the optimal routing scheme. The techniques developed for two-level folded-Clos networks are further extended for the general fat-trees of any heights.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "27", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{Sandes:2016:MMA, author = "Edans F. De O. Sandes and Guillermo Miranda and Xavier Martorell and Eduard Ayguade and George Teodoro and Alba C. M. A. {De Melo}", title = "{MASA}: a Multiplatform Architecture for Sequence Aligners with Block Pruning", journal = j-TOPC, volume = "2", number = "4", pages = "28:1--28:??", month = mar, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2858656", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 19 08:11:13 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Biological sequence alignment is a very popular application in Bioinformatics, used routinely worldwide. Many implementations of biological sequence alignment algorithms have been proposed for multicores, GPUs, FPGAs and CellBEs. These implementations are platform-specific; porting them to other systems requires considerable programming effort. This article proposes and evaluates MASA, a flexible and customizable software architecture that enables the execution of biological sequence alignment applications with three variants (local, global, and semiglobal) in multiple hardware/software platforms with block pruning, which is able to reduce significantly the amount of data processed. To attain our flexibility goals, we also propose a generic version of block pruning and developed multiple parallelization strategies as building blocks, including a new asynchronous dataflow-based parallelization, which may be combined to implement efficient aligners in different platforms. We provide four MASA aligner implementations for multicores (OmpSs and OpenMP), GPU (CUDA), and Intel Phi (OpenMP), showing that MASA is very flexible. The evaluation of our generic block pruning strategy shows that it significantly outperforms the previously proposed block pruning, being able to prune up to 66.5\% of the cells when using the new dataflow-based parallelization strategy.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "28", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", remark = "Special Issue on PPoPP'14 conference.", } @Article{MeyeraufderHeide:2016:ISI, author = "Friedhelm {Meyer auf der Heide} and Peter Sanders and Nodari Sitchinava", title = "Introduction to the Special Issue on {SPAA 2014}", journal = j-TOPC, volume = "3", number = "1", pages = "1:1--1:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2936716", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kaler:2016:EDD, author = "Tim Kaler and William Hasenplaugh and Tao B. Schardl and Charles E. Leiserson", title = "Executing Dynamic Data-Graph Computations Deterministically Using Chromatic Scheduling", journal = j-TOPC, volume = "3", number = "1", pages = "2:1--2:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2896850", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "A data-graph computation-popularized by such programming systems as Galois, Pregel, GraphLab, PowerGraph, and GraphChi-is an algorithm that performs local updates on the vertices of a graph. During each round of a data-graph computation, an update function atomically modifies the data associated with a vertex as a function of the vertex's prior data and that of adjacent vertices. A dynamic data-graph computation updates only an active subset of the vertices during a round, and those updates determine the set of active vertices for the next round. This article introduces Prism, a chromatic-scheduling algorithm for executing dynamic data-graph computations. Prism uses a vertex coloring of the graph to coordinate updates performed in a round, precluding the need for mutual-exclusion locks or other nondeterministic data synchronization. A multibag data structure is used by Prism to maintain a dynamic set of active vertices as an unordered set partitioned by color. We analyze Prism using work-span analysis. Let $ G = (V, E) $ be a degree-$ \Delta $ graph colored with \chi colors, and suppose that $ Q \subseteq V $ is the set of active vertices in a round. Define $ {\rm size} (Q) = | Q | + \Sigma_{v \in Q} {\rm deg}(v) $, which is proportional to the space required to store the vertices of $Q$ using a sparse-graph layout. We show that a $P$-processor execution of Prism performs updates in $Q$ using $ O(\chi (l g (Q / \chi) + l g \Delta)) + l g P$ span and $ \Theta (s i z e (Q) + P)$ work. These theoretical guarantees are matched by good empirical performance. To isolate the effect of the scheduling algorithm on performance, we modified GraphLab to incorporate Prism and studied seven application benchmarks on a 12-core multicore machine. Prism executes the benchmarks 1.2 to 2.1 times faster than GraphLab's nondeterministic lock-based scheduler while providing deterministic behavior. This article also presents Prism-R, a variation of Prism that executes dynamic data-graph computations deterministically even when updates modify global variables with associative operations. Prism-R satisfies the same theoretical bounds as Prism, but its implementation is more involved, incorporating a multivector data structure to maintain a deterministically ordered set of vertices partitioned by color. Despite its additional complexity, Prism-R is only marginally slower than Prism. On the seven application benchmarks studied, Prism-R incurs a 7\% geometric mean overhead relative to Prism.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Im:2016:CST, author = "Sungjin Im and Benjamin Moseley and Kirk Pruhs and Eric Torng", title = "Competitively Scheduling Tasks with Intermediate Parallelizability", journal = j-TOPC, volume = "3", number = "1", pages = "4:1--4:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2938378", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We introduce a scheduling algorithm Intermediate-SRPT, and show that it is $ O (\log P)$-competitive with respect to average flow time when scheduling jobs whose parallelizability is intermediate between being fully parallelizable and sequential. Here, the parameter P denotes the ratio between the maximum job size to the minimum. We also show a general matching lower bound on the competitive ratio. Our analysis builds on an interesting combination of potential function and local competitiveness arguments.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bercea:2016:CMI, author = "Ioana O. Bercea and Navin Goyal and David G. Harris and Aravind Srinivasan", title = "On Computing Maximal Independent Sets of Hypergraphs in Parallel", journal = j-TOPC, volume = "3", number = "1", pages = "5:1--5:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2938436", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Whether or not the problem of finding maximal independent sets (MIS) in hypergraphs is in (R)NC is one of the fundamental problems in the theory of parallel computing. Essentially, the challenge is to design (randomized) algorithms in which the number of processors used is polynomial and the (expected) runtime is polylogarithmic in the size of the input. Unlike the well-understood case of MIS in graphs, for the hypergraph problem, our knowledge is quite limited despite considerable work. It is known that the problem is in RNC when the edges of the hypergraph have constant size. For general hypergraphs with n vertices and m edges, the fastest previously known algorithm works in time $ O(\sqrt n) $ with $ \poly (m, n) $ processors. In this article, we give an EREW PRAM randomized algorithm that works in time $ n^{o (1)} $ with $ O(n + m \log n) $ processors on general hypergraphs satisfying $ m \leq n^{o (1) \log \log n / \log \log \log n} $. We also give an EREW PRAM deterministic algorithm that runs in time $ n^\epsilon $ on a graph with $ m \leq n^{1 / \delta } $ edges, for any constants $ \delta $, $ \epsilon $; the number of processors is polynomial in $m$, $n$ for a fixed choice of $ \delta $, $ \epsilon $. Our algorithms are based on a sampling idea that reduces the dimension of the hypergraph and employs the algorithm for constant dimension hypergraphs as a subroutine.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bilo:2016:LBN, author = "Davide Bil{\`o} and Luciano Gual{\`a} and Stefano Leucci and Guido Proietti", title = "Locality-Based Network Creation Games", journal = j-TOPC, volume = "3", number = "1", pages = "6:1--6:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2938426", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Network creation games have been extensively studied, both by economists and computer scientists, due to their versatility in modeling individual-based community formation processes. These processes, in turn, are the theoretical counterpart of several economics, social, and computational applications on the Internet. In their several variants, these games model the tension of a player between the player's two antagonistic goals: to be as close as possible to the other players and to activate a cheapest possible set of links. However, the generally adopted assumption is that players have a common and complete information about the ongoing network, which is quite unrealistic in practice. In this article, we consider a more compelling scenario in which players have only limited information about the network in which they are embedded. More precisely, we explore the game-theoretic and computational implications of assuming that players have a complete knowledge of the network structure only up to a given radius k, which is one of the most qualified local-knowledge models used in distributed computing. In this respect, we define a suitable equilibrium concept, and we provide a comprehensive set of upper and lower bounds to the price of anarchy for the entire range of values of k and for the two classic variants of the game, namely, those in which a player's cost-besides the activation cost of the owned links-depends on the maximum/sum of all distances to the other nodes in the network, respectively. These bounds are assessed through an extensive set of experiments.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jiang:2016:PPA, author = "Jiayang Jiang and Michael Mitzenmacher and Justin Thaler", title = "Parallel Peeling Algorithms", journal = j-TOPC, volume = "3", number = "1", pages = "7:1--7:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2938412", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The analysis of several algorithms and data structures can be framed as a peeling process on a random hypergraph: vertices with degree less than k are removed until there are no vertices of degree less than k left. The remaining hypergraph is known as the k core. In this article, we analyze parallel peeling processes, in which in each round, all vertices of degree less than k are removed. It is known that, below a specific edge-density threshold, the k -core is empty with high probability. We show that, with high probability, below this threshold, only $ 1 / \log ((k - 1) (r - 1)) \log \log n + O (1) $ rounds of peeling are needed to obtain the empty $k$-core for $ 4 b r$-uniform hypergraphs. This bound is tight up to an additive constant. Interestingly, we show that, above this threshold, $ \Omega (\log n)$ rounds of peeling are required to find the nonempty $k$-core. Since most algorithms and data structures aim to peel to an empty $k$-core, this asymmetry appears fortunate. We verify the theoretical results both with simulation and with a parallel implementation using graphics processing units (GPUs). Our implementation provides insights into how to structure parallel peeling algorithms for efficiency in practice.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Simhadri:2016:EAS, author = "Harsha Vardhan Simhadri and Guy E. Blelloch and Jeremy T. Fineman and Phillip B. Gibbons and Aapo Kyrola", title = "Experimental Analysis of Space-Bounded Schedulers", journal = j-TOPC, volume = "3", number = "1", pages = "8:1--8:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2938389", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:51 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The running time of nested parallel programs on shared-memory machines depends in significant part on how well the scheduler mapping the program to the machine is optimized for the organization of caches and processor cores on the machine. Recent work proposed ``space-bounded schedulers'' for scheduling such programs on the multilevel cache hierarchies of current machines. The main benefit of this class of schedulers is that they provably preserve locality of the program at every level in the hierarchy, which can result in fewer cache misses and better use of bandwidth than the popular work-stealing scheduler. On the other hand, compared to work stealing, space-bounded schedulers are inferior at load balancing and may have greater scheduling overheads, raising the question as to the relative effectiveness of the two schedulers in practice. In this article, we provide the first experimental study aimed at addressing this question. To facilitate this study, we built a flexible experimental framework with separate interfaces for programs and schedulers. This enables a head-to-head comparison of the relative strengths of schedulers in terms of running times and cache miss counts across a range of benchmarks. (The framework is validated by comparisons with the Intel{\reg} CilkTM Plus work-stealing scheduler.) We present experimental results on a 32-core Xeon{\reg} 7560 comparing work stealing, hierarchy-minded work stealing, and two variants of space-bounded schedulers on both divide-and-conquer microbenchmarks and some popular algorithmic kernels. Our results indicate that space-bounded schedulers reduce the number of L3 cache misses compared to work-stealing schedulers by 25\% to 65\% for most of the benchmarks, but incur up to 27\% additional scheduler and load-imbalance overhead. Only for memory-intensive benchmarks can the reduction in cache misses overcome the added overhead, resulting in up to a 25\% improvement in running time for synthetic benchmarks and about 20\% improvement for algorithmic kernels. We also quantify runtime improvements varying the available bandwidth per core (the ``bandwidth gap'') and show up to 50\% improvements in the running times of kernels as this gap increases fourfold. As part of our study, we generalize prior definitions of space-bounded schedulers to allow for more practical variants (while still preserving their guarantees) and explore implementation tradeoffs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sheikh:2016:SHJ, author = "Hafiz Fahad Sheikh and Ishfaq Ahmad", title = "Sixteen Heuristics for Joint Optimization of Performance, Energy, and Temperature in Allocating Tasks to Multi-Cores", journal = j-TOPC, volume = "3", number = "2", pages = "9:1--9:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2948973", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Three-way joint optimization of performance ( P ), energy ( E ), and temperature ( T ) in scheduling parallel tasks to multiple cores poses a challenge that is staggering in its computational complexity. The goal of the PET optimized scheduling ( PETOS ) problem is to minimize three quantities: the completion time of a task graph, the total energy consumption, and the peak temperature of the system. Algorithms based on conventional multi-objective optimization techniques can be designed for solving the PETOS problem. But their execution times are exceedingly high and hence their applicability is restricted merely to problems of modest size. Exacerbating the problem is the solution space that is typically a Pareto front since no single solution can be strictly best along all three objectives. Thus, not only is the absolute quality of the solutions important but ``the spread of the solutions'' along each objective and the distribution of solutions within the generated tradeoff front are also desired. A natural alternative is to design efficient heuristic algorithms that can generate good solutions as well as good spreads --- note that most of the prior work in energy-efficient task allocation is predominantly single- or dual-objective oriented. Given a directed acyclic graph (DAG) representing a parallel program, a heuristic encompasses policies as to what tasks should go to what cores and at what frequency should that core operate. Various policies, such as greedy, iterative, and probabilistic, can be employed. However, the choice and usage of these policies can influence a heuristic towards a particular objective and can also profoundly impact its performance. This article proposes 16 heuristics that utilize various methods for task-to-core allocation and frequency selection. This article also presents a methodical classification scheme which not only categorizes the proposed heuristics but can also accommodate additional heuristics. Extensive simulation experiments compare these algorithms while shedding light on their strengths and tradeoffs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Blanchard:2016:SMO, author = "Jeffrey D. Blanchard and Erik Opavsky and Emircan Uysaler", title = "Selecting Multiple Order Statistics with a Graphics Processing Unit", journal = j-TOPC, volume = "3", number = "2", pages = "10:1--10:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2948974", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Extracting a set of multiple order statistics from a huge data set provides important information about the distribution of the values in the full set of data. This article introduces an algorithm, bucketMultiSelect, for simultaneously selecting multiple order statistics with a graphics processing unit (GPU). Typically, when a large set of order statistics is desired, the vector is sorted. When the sorted version of the vector is not needed, bucketMultiSelect significantly reduces computation time by eliminating a large portion of the unnecessary operations involved in sorting. For large vectors, bucketMultiSelect returns thousands of order statistics in less time than sorting the vector while typically using less memory. For vectors containing $ 2^{28} $ values of type double, bucketMultiSelect selects the 101 percentile order statistics in less than 95ms and is more than $ 8 \times $ faster than sorting the vector with a GPU optimized merge sort.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bohme:2016:IRC, author = "David B{\"o}hme and Markus Geimer and Lukas Arnold and Felix Voigtlaender and Felix Wolf", title = "Identifying the Root Causes of Wait States in Large-Scale Parallel Applications", journal = j-TOPC, volume = "3", number = "2", pages = "11:1--11:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2934661", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Driven by growing application requirements and accelerated by current trends in microprocessor design, the number of processor cores on modern supercomputers is increasing from generation to generation. However, load or communication imbalance prevents many codes from taking advantage of the available parallelism, as delays of single processes may spread wait states across the entire machine. Moreover, when employing complex point-to-point communication patterns, wait states may propagate along far-reaching cause-effect chains that are hard to track manually and that complicate an assessment of the actual costs of an imbalance. Building on earlier work by Meira, Jr., et al., we present a scalable approach that identifies program wait states and attributes their costs in terms of resource waste to their original cause. By replaying event traces in parallel both forward and backward, we can identify the processes and call paths responsible for the most severe imbalances, even for runs with hundreds of thousands of processes.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dathathri:2016:CAL, author = "Roshan Dathathri and Ravi Teja Mullapudi and Uday Bondhugula", title = "Compiling Affine Loop Nests for a Dynamic Scheduling Runtime on Shared and Distributed Memory", journal = j-TOPC, volume = "3", number = "2", pages = "12:1--12:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2948975", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Current de-facto parallel programming models like OpenMP and MPI make it difficult to extract task-level dataflow parallelism as opposed to bulk-synchronous parallelism. Task parallel approaches that use point-to-point synchronization between dependent tasks in conjunction with dynamic scheduling dataflow runtimes are thus becoming attractive. Although good performance can be extracted for both shared and distributed memory using these approaches, there is little compiler support for them. In this article, we describe the design of compiler--runtime interaction to automatically extract coarse-grained dataflow parallelism in affine loop nests for both shared and distributed-memory architectures. We use techniques from the polyhedral compiler framework to extract tasks and generate components of the runtime that are used to dynamically schedule the generated tasks. The runtime includes a distributed decentralized scheduler that dynamically schedules tasks on a node. The schedulers on different nodes cooperate with each other through asynchronous point-to-point communication, and all of this is achieved by code automatically generated by the compiler. On a set of six representative affine loop nest benchmarks, while running on 32 nodes with 8 threads each, our compiler-assisted runtime yields a geometric mean speedup of $ 143.6 \times $ ($ 70.3 \times $ to $ 474.7 \times $) over the sequential version and a geometric mean speedup of $ 1.64 \times $ ($ 1.04 \times $ to $ 2.42 \times $) over the state-of-the-art automatic parallelization approach that uses bulk synchronization. We also compare our system with past work that addresses some of these challenges on shared memory, and an emerging runtime (Intel Concurrent Collections) that demands higher programmer input and effort in parallelizing. To the best of our knowledge, ours is also the first automatic scheme that allows for dynamic scheduling of affine loop nests on a cluster of multicores.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Benoit:2016:AGP, author = "Anne Benoit and Aur{\'e}lien Cavelan and Yves Robert and Hongyang Sun", title = "Assessing General-Purpose Algorithms to Cope with Fail-Stop and Silent Errors", journal = j-TOPC, volume = "3", number = "2", pages = "13:1--13:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2897189", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this article, we combine the traditional checkpointing and rollback recovery strategies with verification mechanisms to cope with both fail-stop and silent errors. The objective is to minimize makespan and/or energy consumption. For divisible load applications, we use first-order approximations to find the optimal checkpointing period to minimize execution time, with an additional verification mechanism to detect silent errors before each checkpoint, hence extending the classical formula by Young and Daly for fail-stop errors only. We further extend the approach to include intermediate verifications, and to consider a bicriteria problem involving both time and energy (linear combination of execution time and energy consumption). Then, we focus on application workflows whose dependence graph is a linear chain of tasks. Here, we determine the optimal checkpointing and verification locations, with or without intermediate verifications, for the bicriteria problem. Rather than using a single speed during the whole execution, we further introduce a new execution scenario, which allows for changing the execution speed via Dynamic Voltage and Frequency Scaling (DVFS). In this latter scenario, we determine the optimal checkpointing and verification locations, as well as the optimal speed pairs for each task segment between any two consecutive checkpoints. Finally, we conduct an extensive set of simulations to support the theoretical study, and to assess the performance of each algorithm, showing that the best overall performance is achieved under the most flexible scenario using intermediate verifications and different speeds.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Koutis:2016:SPD, author = "Ioannis Koutis and Shen Chen Xu", title = "Simple Parallel and Distributed Algorithms for Spectral Graph Sparsification", journal = j-TOPC, volume = "3", number = "2", pages = "14:1--14:??", month = aug, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2948062", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 23 15:24:52 MDT 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We describe simple algorithms for spectral graph sparsification, based on iterative computations of weighted spanners and sampling. Leveraging the algorithms of Baswana and Sen for computing spanners, we obtain the first distributed spectral sparsification algorithm in the CONGEST model. We also obtain a parallel algorithm with improved work and time guarantees, as well as other natural distributed implementations. Combining this algorithm with the parallel framework of Peng and Spielman for solving symmetric diagonally dominant linear systems, we get a parallel solver that is significantly more efficient in terms of the total work.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dorier:2016:DAP, author = "Matthieu Dorier and Gabriel Antoniu and Franck Cappello and Marc Snir and Robert Sisneros and Orcun Yildiz and Shadi Ibrahim and Tom Peterka and Leigh Orf", title = "{Damaris}: Addressing Performance Variability in Data Management for Post-Petascale Simulations", journal = j-TOPC, volume = "3", number = "3", pages = "15:1--15:??", month = dec, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2987371", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Dec 26 17:40:41 MST 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "With exascale computing on the horizon, reducing performance variability in data management tasks (storage, visualization, analysis, etc.) is becoming a key challenge in sustaining high performance. This variability significantly impacts the overall application performance at scale and its predictability over time. In this article, we present Damaris, a system that leverages dedicated cores in multicore nodes to offload data management tasks, including I/O, data compression, scheduling of data movements, in situ analysis, and visualization. We evaluate Damaris with the CM1 atmospheric simulation and the Nek5000 computational fluid dynamic simulation on four platforms, including NICS's Kraken and NCSA's Blue Waters. Our results show that (1) Damaris fully hides the I/O variability as well as all I/O-related costs, thus making simulation performance predictable; (2) it increases the sustained write throughput by a factor of up to 15 compared with standard I/O approaches; (3) it allows almost perfect scalability of the simulation up to over 9,000 cores, as opposed to state-of-the-art approaches that fail to scale; and (4) it enables a seamless connection to the VisIt visualization software to perform in situ analysis and visualization in a way that impacts neither the performance of the simulation nor its variability. In addition, we extended our implementation of Damaris to also support the use of dedicated nodes and conducted a thorough comparison of the two approaches-dedicated cores and dedicated nodes-for I/O tasks with the aforementioned applications.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Gao:2016:AOM, author = "Jiaquan Gao and Yu Wang and Jun Wang and Ronghua Liang", title = "Adaptive Optimization Modeling of Preconditioned Conjugate Gradient on Multi-{GPUs}", journal = j-TOPC, volume = "3", number = "3", pages = "16:1--16:??", month = dec, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/2990849", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Dec 26 17:40:41 MST 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The preconditioned conjugate gradient (PCG) algorithm is a well-known iterative method for solving sparse linear systems in scientific computations. GPU-accelerated PCG algorithms for large-sized problems have attracted considerable attention recently. However, on a specific multi-GPU platform, producing a highly parallel PCG implementation for any large-sized problem requires significant time because several manual steps are involved in adjusting the related parameters and selecting an appropriate storage format for the matrix block that is assigned to each GPU. This motivates us to propose adaptive optimization modeling of PCG on multi-GPUs, which mainly involves the following parts: (1) an optimization multi-GPU parallel framework of PCG and (2) the profile-based optimization modeling for each one of the main components of the PCG algorithm, including vector operation, inner product, and sparse matrix-vector multiplication (SpMV). Our model does not construct a new storage format or kernel but automatically and rapidly generates an optimal parallel PCG algorithm for any problem on a specific multi-GPU platform by integrating existing storage formats and kernels. We take a vector operation kernel, an inner-product kernel, and five popular SpMV kernels for an example to present the idea of constructing the model. Given that our model is general, independent of the problems, and dependent on the resources of devices, this model is constructed only once for each type of GPU. The experiments validate the high efficiency of our proposed model.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Creech:2016:TSS, author = "Timothy Creech and Rajeev Barua", title = "Transparently Space Sharing a Multicore Among Multiple Processes", journal = j-TOPC, volume = "3", number = "3", pages = "17:1--17:??", month = dec, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/3001910", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Dec 26 17:40:41 MST 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "As hardware becomes increasingly parallel and the availability of scalable parallel software improves, the problem of managing multiple multithreaded applications (processes) becomes important. Malleable processes, which can vary the number of threads used as they run, enable sophisticated and flexible resource management. Although many existing applications parallelized for SMPs with parallel runtimes are in fact already malleable, deployed runtime environments provide no interface nor any strategy for intelligently allocating hardware threads or even preventing oversubscription. Prior research methods either depend on profiling applications ahead of time to make good decisions about allocations or do not account for process efficiency at all, leading to poor performance. None of these prior methods have been adapted widely in practice. This article presents the Scheduling and Allocation with Feedback (SCAF) system: a drop-in runtime solution that supports existing malleable applications in making intelligent allocation decisions based on observed efficiency without any changes to semantics, program modification, offline profiling, or even recompilation. Our existing implementation can control most unmodified OpenMP applications. Other malleable threading libraries can also easily be supported with small modifications without requiring application modification or recompilation. In this work, we present the SCAF daemon and a SCAF-aware port of the GNU OpenMP runtime. We present a new technique for estimating process efficiency purely at runtime using available hardware counters and demonstrate its effectiveness in aiding allocation decisions. We evaluated SCAF using NAS NPB parallel benchmarks on five commodity parallel platforms, enumerating architectural features and their effects on our scheme. We measured the benefit of SCAF in terms of sum of speedups improvement (a common metric for multiprogrammed environments) when running all benchmark pairs concurrently compared to equipartitioning-the best existing competing scheme in the literature. We found that SCAF improves on equipartitioning on four out of five machines, showing a mean improvement factor in sum of speedups of 1.04 to 1.11x for benchmark pairs, depending on the machine, and 1.09x on average. Since we are not aware of any widely available tool for equipartitioning, we also compare SCAF against multiprogramming using unmodified OpenMP, which is the only environment available to end users today. SCAF improves on the unmodified OpenMP runtimes for all five machines, with a mean improvement of 1.08 to 2.07x, depending on the machine, and 1.59x on average.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ballard:2016:HPS, author = "Grey Ballard and Alex Druinsky and Nicholas Knight and Oded Schwartz", title = "Hypergraph Partitioning for Sparse Matrix--Matrix Multiplication", journal = j-TOPC, volume = "3", number = "3", pages = "18:1--18:??", month = dec, year = "2016", CODEN = "????", DOI = "https://doi.org/10.1145/3015144", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Dec 26 17:40:41 MST 2016", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We propose a fine-grained hypergraph model for sparse matrix-matrix multiplication (SpGEMM), a key computational kernel in scientific computing and data analysis whose performance is often communication bound. This model correctly describes both the interprocessor communication volume along a critical path in a parallel computation and also the volume of data moving through the memory hierarchy in a sequential computation. We show that identifying a communication-optimal algorithm for particular input matrices is equivalent to solving a hypergraph partitioning problem. Our approach is nonzero structure dependent, meaning that we seek the best algorithm for the given input matrices. In addition to our three-dimensional fine-grained model, we also propose coarse-grained one-dimensional and two-dimensional models that correspond to simpler SpGEMM algorithms. We explore the relations between our models theoretically, and we study their performance experimentally in the context of three applications that use SpGEMM as a key computation. For each application, we find that at least one coarse-grained model is as communication efficient as the fine-grained model. We also observe that different applications have affinities for different algorithms. Our results demonstrate that hypergraphs are an accurate model for reasoning about the communication costs of SpGEMM as well as a practical tool for exploring the SpGEMM algorithm design space.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Grove:2017:ISS, author = "David Grove", title = "Introduction to the Special Section on {PPoPP'15}", journal = j-TOPC, volume = "3", number = "4", pages = "19:1--19:??", month = mar, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3040224", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 25 07:55:06 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Majo:2017:LPC, author = "Zoltan Majo and Thomas R. Gross", title = "A Library for Portable and Composable Data Locality Optimizations for {NUMA} Systems", journal = j-TOPC, volume = "3", number = "4", pages = "20:1--20:??", month = mar, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3040222", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 25 07:55:06 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Many recent multiprocessor systems are realized with a nonuniform memory architecture (NUMA) and accesses to remote memory locations take more time than local memory accesses. Optimizing NUMA memory system performance is difficult and costly for three principal reasons: (1) Today's programming languages/libraries have no explicit support for NUMA systems, (2) NUMA optimizations are not portable, and (3) optimizations are not composable (i.e., they can become ineffective or worsen performance in environments that support composable parallel software). This article presents TBB-NUMA, a parallel programming library based on Intel Threading Building Blocks (TBB) that supports portable and composable NUMA-aware programming. TBB-NUMA provides a model of task affinity that captures a programmer's insights on mapping tasks to resources. NUMA-awareness affects all layers of the library (i.e., resource management, task scheduling, and high-level parallel algorithm templates) and requires close coupling between all these layers. Optimizations implemented with TBB-NUMA (for a set of standard benchmark programs) result in up to 44\% performance improvement over standard TBB. But more important, optimized programs are portable across different NUMA architectures and preserve data locality also when composed with other parallel computations sharing the same resource management layer.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Golan-Gueta:2017:ASA, author = "Guy Golan-Gueta and G. Ramalingam and Mooly Sagiv and Eran Yahav", title = "Automatic Scalable Atomicity via Semantic Locking", journal = j-TOPC, volume = "3", number = "4", pages = "21:1--21:??", month = mar, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3040223", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 25 07:55:06 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this article, we consider concurrent programs in which the shared state consists of instances of linearizable abstract data types (ADTs). We present an automated approach to concurrency control that addresses a common need: the need to atomically execute a code fragment, which may contain multiple ADT operations on multiple ADT instances. We present a synthesis algorithm that automatically enforces atomicity of given code fragments (in a client program) by inserting pessimistic synchronization that guarantees atomicity and deadlock-freedom (without using any rollback mechanism). Our algorithm takes a commutativity specification as an extra input. This specification indicates for every pair of ADT operations the conditions under which the operations commute. Our algorithm enables greater parallelism by permitting commuting operations to execute concurrently. We have implemented the synthesis algorithm in a Java compiler and applied it to several Java programs. Our results show that our approach produces efficient and scalable synchronization.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Izraelevitz:2017:GSN, author = "Joseph Izraelevitz and Michael L. Scott", title = "Generality and Speed in Nonblocking Dual Containers", journal = j-TOPC, volume = "3", number = "4", pages = "22:1--22:??", month = mar, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3040220", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 25 07:55:06 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Nonblocking dual data structures extend traditional notions of nonblocking progress to accommodate partial methods, both by bounding the number of steps that a thread can execute after its preconditions have been satisfied and by ensuring that a waiting thread performs no remote memory accesses that could interfere with the execution of other threads. A nonblocking dual container, in particular, is designed to hold either data or requests. An insert operation either adds data to the container or removes and satisfies a request; a remove operation either takes data out of the container or inserts a request. We present the first general-purpose construction for nonblocking dual containers, allowing any nonblocking container for data to be paired with almost any nonblocking container for requests. We also present new custom algorithms, based on the LCRQ of Morrison and Afek, that outperform the fastest previously known dual containers by factors of four to six.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cole:2017:ROS, author = "Richard Cole and Vijaya Ramachandran", title = "Resource Oblivious Sorting on Multicores", journal = j-TOPC, volume = "3", number = "4", pages = "23:1--23:??", month = mar, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3040221", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Mar 25 07:55:06 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present a deterministic sorting algorithm, Sample, Partition, and Merge Sort (SPMS), that interleaves the partitioning of a sample sort with merging. Sequentially, it sorts $n$ elements in $ O(n \log n)$ time cache-obliviously with an optimal number of cache misses. The parallel complexity (or critical path length) of the algorithm is $ O(\log n \log \log n)$, which improves on previous bounds for deterministic sample sort. The algorithm also has low false sharing costs. When scheduled by a work-stealing scheduler in a multicore computing environment with a global shared memory and p cores, each having a cache of size $M$ organized in blocks of size $B$, the costs of the additional cache misses and false sharing misses due to this parallel execution are bounded by the cost of $ O(S \cdot M / B)$ and $ O(S \cdot B)$ cache misses, respectively, where $S$ is the number of steals performed during the execution. Finally, SPMS is resource oblivious in that the dependence on machine parameters appear only in the analysis of its performance and not within the algorithm itself.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "23", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ballard:2017:GEIa, author = "Grey Ballard and Mary Hall and Tim Harris and Brandon Lucia", title = "{Guest Editor} Introduction {PPoPP 2016}, Special Issue 2 of 2", journal = j-TOPC, volume = "4", number = "1", pages = "1:1--1:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108141", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ashkiani:2017:GME, author = "Saman Ashkiani and Andrew Davidson and Ulrich Meyer and John D. Owens", title = "{GPU Multisplit}: an Extended Study of a Parallel Algorithm", journal = j-TOPC, volume = "4", number = "1", pages = "2:1--2:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108139", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Multisplit is a broadly useful parallel primitive that permutes its input data into contiguous buckets or bins, where the function that categorizes an element into a bucket is provided by the programmer. Due to the lack of an efficient multisplit on Graphics Processing Units (GPUs), programmers often choose to implement multisplit with a sort. One way is to first generate an auxiliary array of bucket IDs and then sort input data based on it. In case smaller indexed buckets possess smaller valued keys, another way for multisplit is to directly sort input data. Both methods are inefficient and require more work than necessary: The former requires more expensive data movements while the latter spends unnecessary effort in sorting elements within each bucket. In this work, we provide a parallel model and multiple implementations for the multisplit problem. Our principal focus is multisplit for a small (up to 256) number of buckets. We use warp-synchronous programming models and emphasize warpwide communications to avoid branch divergence and reduce memory usage. We also hierarchically reorder input elements to achieve better coalescing of global memory accesses. On a GeForce GTX 1080 GPU, we can reach a peak throughput of 18.93Gkeys/s (or 11.68Gpairs/s) for a key-only (or key-value) multisplit. Finally, we demonstrate how multisplit can be used as a building block for radix sort. In our multisplit-based sort implementation, we achieve comparable performance to the fastest GPU sort routines, sorting 32-bit keys (and key-value pairs) with a throughput of 3.0Gkeys/s (and 2.1Gpair/s).", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Wang:2017:GGG, author = "Yangzihao Wang and Yuechao Pan and Andrew Davidson and Yuduo Wu and Carl Yang and Leyuan Wang and Muhammad Osama and Chenshan Yuan and Weitang Liu and Andy T. Riffel and John D. Owens", title = "{Gunrock}: {GPU} Graph Analytics", journal = j-TOPC, volume = "4", number = "1", pages = "3:1--3:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108140", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "For large-scale graph analytics on the GPU, the irregularity of data access and control flow, and the complexity of programming GPUs, have presented two significant challenges to developing a programmable high-performance graph library. ``Gunrock,'' our graph-processing system designed specifically for the GPU, uses a high-level, bulk-synchronous, data-centric abstraction focused on operations on a vertex or edge frontier. Gunrock achieves a balance between performance and expressiveness by coupling high-performance GPU computing primitives and optimization strategies with a high-level programming model that allows programmers to quickly develop new graph primitives with small code size and minimal GPU programming knowledge. We characterize the performance of various optimization strategies and evaluate Gunrock's overall performance on different GPU architectures on a wide range of graph primitives that span from traversal-based algorithms and ranking algorithms, to triangle counting and bipartite-graph-based algorithms. The results show that on a single GPU, Gunrock has on average at least an order of magnitude speedup over Boost and PowerGraph, comparable performance to the fastest GPU hardwired primitives and CPU shared-memory graph libraries, such as Ligra and Galois, and better performance than any other GPU high-level graph library.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chowdhury:2017:AAD, author = "Rezaul Chowdhury and Pramod Ganapathi and Stephen Tschudi and Jesmin Jahan Tithi and Charles Bachmeier and Charles E. Leiserson and Armando Solar-Lezama and Bradley C. Kuszmaul and Yuan Tang", title = "{Autogen}: Automatic Discovery of Efficient Recursive Divide-\&-Conquer Algorithms for Solving Dynamic Programming Problems", journal = j-TOPC, volume = "4", number = "1", pages = "4:1--4:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3125632", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present Autogen --- an algorithm that for a wide class of dynamic programming (DP) problems automatically discovers highly efficient cache-oblivious parallel recursive divide-and-conquer algorithms from inefficient iterative descriptions of DP recurrences. Autogen analyzes the set of DP table locations accessed by the iterative algorithm when run on a DP table of small size and automatically identifies a recursive access pattern and a corresponding provably correct recursive algorithm for solving the DP recurrence. We use Autogen to autodiscover efficient algorithms for several well-known problems. Our experimental results show that several autodiscovered algorithms significantly outperform parallel looping and tiled loop-based algorithms. Also, these algorithms are less sensitive to fluctuations of memory and bandwidth compared with their looping counterparts, and their running times and energy profiles remain relatively more stable. To the best of our knowledge, Autogen is the first algorithm that can automatically discover new nontrivial divide-and-conquer algorithms.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Steele:2017:AAC, author = "Guy L. {Steele Jr.} and Jean-Baptiste Tristan", title = "Adding Approximate Counters", journal = j-TOPC, volume = "4", number = "1", pages = "5:1--5:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3132167", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We describe a general framework for adding the values of two approximate counters to produce a new approximate counter value whose expected estimated value is equal to the sum of the expected estimated values of the given approximate counters. (To the best of our knowledge, this is the first published description of any algorithm for adding two approximate counters.) We then work out implementation details for five different kinds of approximate counter and provide optimized pseudocode. For three of them, we present proofs that the variance of a counter value produced by adding two counter values in this way is bounded, and in fact is no worse, or not much worse, than the variance of the value of a single counter to which the same total number of increment operations have been applied. Addition of approximate counters is useful in massively parallel divide-and-conquer algorithms that use a distributed representation for large arrays of counters. We describe two machine-learning algorithms for topic modeling that use millions of integer counters and confirm that replacing the integer counters with approximate counters is effective, speeding up a GPU-based implementation by over 65\% and a CPU-based implementation by nearly 50\%, as well as reducing memory requirements, without degrading their statistical effectiveness.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ballard:2017:GEIb, author = "Grey Ballard and Mary Hall and Tim Harris and Brandon Lucia", title = "{Guest Editor} Introduction {PPoPP 2016}, Special Issue 2 of 2", journal = j-TOPC, volume = "4", number = "2", pages = "6:1--6:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108142", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kalikar:2017:DNM, author = "Saurabh Kalikar and Rupesh Nasre", title = "{DomLock}: a New Multi-Granularity Locking Technique for Hierarchies", journal = j-TOPC, volume = "4", number = "2", pages = "7:1--7:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3127584", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We present efficient locking mechanisms for hierarchical data structures. Several applications work on an abstract hierarchy of objects, and a parallel execution on this hierarchy necessitates synchronization across workers operating on different parts of the hierarchy. Existing synchronization mechanisms are too coarse, too inefficient, or too ad hoc, resulting in reduced or unpredictable amount of concurrency. We propose a new locking approach based on the structural properties of the underlying hierarchy. We show that the developed techniques are efficient even when the hierarchy is an arbitrary graph. Theoretically, we present our approach as a locking-cost-minimizing instance of a generic algebraic model of synchronization for hierarchies. Using STMBench7, we illustrate considerable reduction in the locking cost, resulting in an average throughput improvement of 42\%.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Haider:2017:LRA, author = "Syed Kamran Haider and William Hasenplaugh and Dan Alistarh", title = "{Lease\slash Release}: Architectural Support for Scaling Contended Data Structures", journal = j-TOPC, volume = "4", number = "2", pages = "8:1--8:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3132168", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "High memory contention is generally agreed to be a worst-case scenario for concurrent data structures. There has been a significant amount of research effort spent investigating designs that minimize contention, and several programming techniques have been proposed to mitigate its effects. However, there are currently few architectural mechanisms to allow scaling contended data structures at high thread counts. In this article, we investigate hardware support for scalable contended data structures. We propose Lease/Release, a simple addition to standard directory-based MESI cache coherence protocols, allowing participants to lease memory, at the granularity of cache lines, by delaying coherence messages for a short, bounded period of time. Our analysis shows that Lease/Release can significantly reduce the overheads of contention for both non-blocking (lock-free) and lock-based data structure implementations while ensuring that no deadlocks are introduced. We validate Lease/Release empirically on the Graphite multiprocessor simulator on a range of data structures, including queue, stack, and priority queue implementations, as well as on transactional applications. Results show that Lease/Release consistently improves both throughput and energy usage, by up to 5x, both for lock-free and lock-based data structure designs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cao:2017:HRD, author = "Man Cao and Minjia Zhang and Aritra Sengupta and Swarnendu Biswas and Michael D. Bond", title = "Hybridizing and Relaxing Dependence Tracking for Efficient Parallel Runtime Support", journal = j-TOPC, volume = "4", number = "2", pages = "9:1--9:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108138", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "It is notoriously challenging to develop parallel software systems that are both scalable and correct. Runtime support for parallelism-such as multithreaded record and replay, data race detectors, transactional memory, and enforcement of stronger memory models-helps achieve these goals, but existing commodity solutions slow programs substantially to track (i.e., detect or control) an execution's cross-thread dependencies accurately. Prior work tracks cross-thread dependencies either ``pessimistically,'' slowing every program access, or ``optimistically,'' allowing for lightweight instrumentation of most accesses but dramatically slowing accesses that are conflicting (i.e., involved in cross-thread dependencies). This article presents two novel approaches that seek to improve the performance of dependence tracking. Hybrid tracking (HT) hybridizes pessimistic and optimistic tracking by overcoming a fundamental mismatch between these two kinds of tracking. HT uses an adaptive, profile-based policy to make runtime decisions about switching between pessimistic and optimistic tracking. Relaxed tracking (RT) attempts to reduce optimistic tracking's overhead on conflicting accesses by tracking dependencies in a ``relaxed'' way-meaning that not all dependencies are tracked accurately-while still preserving both program semantics and runtime support's correctness. To demonstrate the usefulness and potential of HT and RT, we build runtime support based on the two approaches. Our evaluation shows that both approaches offer performance advantages over existing approaches, but there exist challenges and opportunities for further improvement. HT and RT are distinct solutions to the same problem. It is easier to build runtime support based on HT than on RT, although RT does not incur the overhead of online profiling. This article presents the two approaches together to inform and inspire future designs for efficient parallel runtime support.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chatzopoulos:2017:EES, author = "Georgios Chatzopoulos and Aleksandar Dragojevi{\'c} and Rachid Guerraoui", title = "{ESTIMA}: Extrapolating {ScalabiliTy} of In-Memory Applications", journal = j-TOPC, volume = "4", number = "2", pages = "10:1--10:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3108137", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "This article presents estima, an easy-to-use tool for extrapolating the scalability of in-memory applications. estima is designed to perform a simple yet important task: Given the performance of an application on a small machine with a handful of cores, estima extrapolates its scalability to a larger machine with more cores, while requiring minimum input from the user. The key idea underlying estima is the use of stalled cycles (e.g., cycles that the processor spends waiting for missed cache line fetches or busy locks). estima measures stalled cycles on a few cores and extrapolates them to more cores, estimating the amount of waiting in the system. estima can be effectively used to predict the scalability of in-memory applications for bigger execution machines. For instance, using measurements of memcached and SQLite on a desktop machine, we obtain accurate predictions of their scalability on a server. Our extensive evaluation shows the effectiveness of estima on a large number of in-memory benchmarks.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Gulisano:2017:EDS, author = "Vincenzo Gulisano and Yiannis Nikolakopoulos and Daniel Cederman and Marina Papatriantafilou and Philippas Tsigas", title = "Efficient Data Streaming Multiway Aggregation through Concurrent Algorithmic Designs and New Abstract Data Types", journal = j-TOPC, volume = "4", number = "2", pages = "11:1--11:??", month = oct, year = "2017", CODEN = "????", DOI = "https://doi.org/10.1145/3131272", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Oct 10 17:42:07 MDT 2017", bibsource = "http://topc.acm.org/; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Data streaming relies on continuous queries to process unbounded streams of data in a real-time fashion. It is commonly demanding in computation capacity, given that the relevant applications involve very large volumes of data. Data structures act as articulation points and maintain the state of data streaming operators, potentially supporting high parallelism and balancing the work among them. Prompted by this fact, in this work we study and analyze parallelization needs of these articulation points, focusing on the problem of streaming multiway aggregation, where large data volumes are received from multiple input streams. The analysis of the parallelization needs, as well as of the use and limitations of existing aggregate designs and their data structures, leads us to identify needs for appropriate shared objects that can achieve low-latency and high-throughput multiway aggregation. We present the requirements of such objects as abstract data types and we provide efficient lock-free linearizable algorithmic implementations of them, along with new multiway aggregate algorithmic designs that leverage them, supporting both deterministic order-sensitive and order-insensitive aggregate functions. Furthermore, we point out future directions that open through these contributions. The article includes an extensive experimental study, based on a variety of continuous aggregation queries on two large datasets extracted from SoundCloud, a music social network, and from a Smart Grid network. In all the experiments, the proposed data structures and the enhanced aggregate operators improved the processing performance significantly, up to one order of magnitude, in terms of both throughput and latency, over the commonly used techniques based on queues.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Malas:2018:MIP, author = "Tareq M. Malas and Georg Hager and Hatem Ltaief and David E. Keyes", title = "Multidimensional Intratile Parallelization for Memory-Starved Stencil Computations", journal = j-TOPC, volume = "4", number = "3", pages = "12:1--12:??", month = apr, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3155290", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Optimizing the performance of stencil algorithms has been the subject of intense research over the last two decades. Since many stencil schemes have low arithmetic intensity, most optimizations focus on increasing the temporal data access locality, thus reducing the data traffic through the main memory interface with the ultimate goal of decoupling from this bottleneck. There are, however, only a few approaches that explicitly leverage the shared cache feature of modern multicore chips. If every thread works on its private, separate cache block, the available cache space can become too small, and sufficient temporal locality may not be achieved. We propose a flexible multidimensional intratile parallelization method for stencil algorithms on multicore CPUs with a shared outer-level cache. This method leads to a significant reduction in the required cache space without adverse effects from hardware prefetching or TLB shortage. Our Girih framework includes an autotuner to select optimal parameter configurations on the target hardware. We conduct performance experiments on two contemporary Intel processors and compare with the state-of-the-art stencil frameworks Pluto and Pochoir, using four corner-case stencil schemes and a wide range of problem sizes. Girih shows substantial performance advantages and best arithmetic intensity at almost all problem sizes, especially on low-intensity stencils with variable coefficients. We study in detail the performance behavior at varying grid sizes using phenomenological performance modeling. Our analysis of energy consumption reveals that our method can save energy through reduced DRAM bandwidth usage even at a marginal performance gain. It is thus well suited for future architectures that will be strongly challenged by the cost of data movement, be it in terms of performance or energy consumption.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Akbudak:2018:PMS, author = "Kadir Akbudak and Oguz Selvitopi and Cevdet Aykanat", title = "Partitioning Models for Scaling Parallel Sparse Matrix--Matrix Multiplication", journal = j-TOPC, volume = "4", number = "3", pages = "13:1--13:??", month = apr, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3155292", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We investigate outer-product--parallel, inner-product--parallel, and row-by-row-product--parallel formulations of sparse matrix-matrix multiplication (SpGEMM) on distributed memory architectures. For each of these three formulations, we propose a hypergraph model and a bipartite graph model for distributing SpGEMM computations based on one-dimensional (1D) partitioning of input matrices. We also propose a communication hypergraph model for each formulation for distributing communication operations. The computational graph and hypergraph models adopted in the first phase aim at minimizing the total message volume and balancing the computational loads of processors, whereas the communication hypergraph models adopted in the second phase aim at minimizing the total message count and balancing the message volume loads of processors. That is, the computational partitioning models reduce the bandwidth cost and the communication hypergraph models reduce the latency cost. Our extensive parallel experiments on up to 2048 processors for a wide range of realistic SpGEMM instances show that although the outer-product--parallel formulation scales better, the row-by-row-product--parallel formulation is more viable due to its significantly lower partitioning overhead and competitive scalability. For computational partitioning models, our experimental findings indicate that the proposed bipartite graph models are attractive alternatives to their hypergraph counterparts because of their lower partitioning overhead. Finally, we show that by reducing the latency cost besides the bandwidth cost through using the communication hypergraph models, the parallel SpGEMM time can be further improved up to 32\%.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bilardi:2018:LBT, author = "Gianfranco Bilardi and Michele Scquizzato and Francesco Silvestri", title = "A Lower Bound Technique for Communication in {BSP}", journal = j-TOPC, volume = "4", number = "3", pages = "14:1--14:??", month = apr, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3181776", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Communication is a major factor determining the performance of algorithms on current computing systems; it is therefore valuable to provide tight lower bounds on the communication complexity of computations. This article presents a lower bound technique for the communication complexity in the bulk-synchronous parallel (BSP) model of a given class of DAG computations. The derived bound is expressed in terms of the switching potential of a DAG, that is, the number of permutations that the DAG can realize when viewed as a switching network. The proposed technique yields tight lower bounds for the fast Fourier transform (FFT), and for any sorting and permutation network. A stronger bound is also derived for the periodic balanced sorting network, by applying this technique to suitable subnetworks. Finally, we demonstrate that the switching potential captures communication requirements even in computational models different from BSP, such as the I/O model and the LPRAM.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sahin:2018:CSC, author = "Semih Sahin and Bugra Gedik", title = "{C-Stream}: a Co-routine-Based Elastic Stream Processing Engine", journal = j-TOPC, volume = "4", number = "3", pages = "15:1--15:??", month = apr, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3184120", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Stream processing is a computational paradigm for on-the-fly processing of live data. This paradigm lends itself to implementations that can provide high throughput and low latency by taking advantage of various forms of parallelism that are naturally captured by the stream processing model of computation, such as pipeline, task, and data parallelism. In this article, we describe the design and implementation of C-Stream, which is an elastic stream processing engine. C-Stream encompasses three unique properties. First, in contrast to the widely adopted event-based interface for developing streaming operators, C-Stream provides an interface wherein each operator has its own driver loop and relies on data availability application programming interfaces (APIs) to decide when to perform its computations. This self-control-based model significantly simplifies the development of operators that require multiport synchronization. Second, C-Stream contains a dynamic scheduler that manages the multithreaded execution of the operators. The scheduler, which is customizable via plug-ins, enables the execution of the operators as co-routines, using any number of threads. The base scheduler implements back-pressure, provides data availability APIs, and manages preemption and termination handling. Last, C-Stream varies the degree of parallelism to resolve bottlenecks by both dynamically changing the number of threads used to execute an application and adjusting the number of replicas of data-parallel operators. We provide an experimental evaluation of C-Stream. The results show that C-Stream is scalable, highly customizable, and can resolve bottlenecks by dynamically adjusting the level of data parallelism used.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Agrawal:2018:ISI, author = "Kunal Agrawal and I-Ting Angelina Lee and Michael Spear", title = "Introduction to Special Issue on {SPAA'15}", journal = j-TOPC, volume = "4", number = "4", pages = "16:1--16:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3226041", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ahn:2018:ADN, author = "Kook Jin Ahn and Sudipto Guha", title = "Access to Data and Number of Iterations: Dual Primal Algorithms for Maximum Matching under Resource Constraints", journal = j-TOPC, volume = "4", number = "4", pages = "17:1--17:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3154855", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this article, we consider graph algorithms in models of computation where the space usage (random accessible storage, in addition to the read-only input) is sublinear in the number of edges $m$ and the access to input is constrained. These questions arise in many natural settings, and in particular in the analysis of streaming algorithms, MapReduce or similar algorithms, or message passing distributed computing that model constrained parallelism with sublinear central processing. We focus on weighted nonbipartite maximum matching in this article. For any constant $ p > 1$, we provide an iterative sampling-based algorithm for computing a $ (1 - \epsilon)$-approximation of the weighted nonbipartite maximum matching that uses $ O(p / \epsilon)$ rounds of sampling, and $ O(n^{1 + 1 / p})$ space. The results extend to $b$-Matching with small changes. This article combines adaptive sketching literature and fast primal-dual algorithms based on relaxed Dantzig--Wolfe decision procedures. Each round of sampling is implemented through linear sketches and can be executed in a single round of streaming or two rounds of MapReduce. The article also proves that nonstandard linear relaxations of a problem, in particular penalty-based formulations, are helpful in reducing the adaptive dependence of the iterations.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alistarh:2018:TAS, author = "Dan Alistarh and William Leiserson and Alexander Matveev and Nir Shavit", title = "{ThreadScan}: Automatic and Scalable Memory Reclamation", journal = j-TOPC, volume = "4", number = "4", pages = "18:1--18:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3201897", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The concurrent memory reclamation problem is that of devising a way for a deallocating thread to verify that no other concurrent threads hold references to a memory block being deallocated. To date, in the absence of automatic garbage collection, there is no satisfactory solution to this problem; existing tracking methods like hazard pointers, reference counters, or epoch-based techniques like RCU are either prohibitively expensive or require significant programming expertise to the extent that implementing them efficiently can be worthy of a publication. None of the existing techniques are automatic or even semi-automated. In this article, we take a new approach to concurrent memory reclamation. Instead of manually tracking access to memory locations as done in techniques like hazard pointers, or restricting shared accesses to specific epoch boundaries as in RCU, our algorithm, called ThreadScan, leverages operating system signaling to automatically detect which memory locations are being accessed by concurrent threads. Initial empirical evidence shows that ThreadScan scales surprisingly well and requires negligible programming effort beyond the standard use of Malloc and Free.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dimitrov:2018:RDT, author = "Dimitar Dimitrov and Martin Vechev and Vivek Sarkar", title = "Race Detection in Two Dimensions", journal = j-TOPC, volume = "4", number = "4", pages = "19:1--19:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3264618", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Dynamic race detection is a program analysis technique for detecting errors caused by undesired interleavings of concurrent tasks. A primary challenge when designing efficient race detection algorithms is to achieve manageable space requirements. State-of-the-art algorithms for unstructured parallelism require $ \Theta (n) $ space per monitored memory location, where n is the total number of tasks. This is a serious drawback when analyzing programs with many tasks. In contrast, algorithms for programs with a series-parallel (SP) structure require only $ \Theta (1) $ space. Unfortunately, it is currently not well understood if there are classes of parallelism beyond SP that can also benefit from and be analyzed with $ \Theta (1) $ space complexity. In this work, we show that structures richer than SP graphs, namely, that of two-dimensional (2D) lattices, can also be analyzed in $ \Theta (1) $ space. Toward that (a) we extend Tarjan's algorithm for finding lowest common ancestors to handle 2D lattices; (b) from that extension we derive a serial algorithm for race detection that can analyze arbitrary task graphs with a 2D lattice structure; (c) we present a restriction to fork-join that admits precisely the 2D lattices as task graphs (e.g., it can express pipeline parallelism). Our work generalizes prior work on structured race detection and aims to provide a deeper understanding of the interplay between structured parallelism and program analysis efficiency.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lee:2018:ERD, author = "I-Ting Angelina Lee and Tao B. Schardl", title = "Efficient Race Detection for Reducer Hyperobjects", journal = j-TOPC, volume = "4", number = "4", pages = "20:1--20:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3205914", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:25 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "A multithreaded Cilk program that is ostensibly deterministic may nevertheless behave nondeterministically due to programming errors in the code. For a Cilk program that uses reducers-a general reduction mechanism supported in various Cilk dialects-such programming errors are especially challenging to debug, because the errors can expose the nondeterminism in how the Cilk runtime system manages reducers. We identify two unique types of races that arise from incorrect use of reducers in a Cilk program, and we present two algorithms to catch these races. The first algorithm, called the Peer-Set algorithm, detects view-read races, which occur when the program attempts to retrieve a value out of a reducer when the read may result in a nondeterministic value, such as before all previously spawned subcomputations that might update the reducer have necessarily returned. The second algorithm, called the SP+ algorithm, detects determinacy races-instances where a write to a memory location occurs logically in parallel with another access to that location-even when the raced-on memory locations relate to reducers. Both algorithms are provably correct, asymptotically efficient, and can be implemented efficiently in practice. We have implemented both algorithms in our prototype race detector, Rader. When running Peer-Set, Rader incurs a geometric-mean multiplicative overhead of 2.56 over running the benchmark without instrumentation. When running SP+, Rader incurs a geometric-mean multiplicative overhead of 16.94.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Gilbert:2018:ISI, author = "Seth Gilbert", title = "Introduction to the Special Issue for {SPAA 2016}", journal = j-TOPC, volume = "5", number = "1", pages = "1:1--1:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3230677", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Mitzenmacher:2018:BBC, author = "Michael Mitzenmacher and Rajmohan Rajaraman and Scott Roche", title = "Better Bounds for Coalescing-Branching Random Walks", journal = j-TOPC, volume = "5", number = "1", pages = "2:1--2:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3209688", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Coalescing-branching random walks, or cobra walks for short, are a natural variant of random walks on graphs that can model the spread of disease through contacts or the spread of information in networks. In a k -cobra walk, at each timestep, a subset of the vertices are active; each active vertex chooses k random neighbors (sampled independently and uniformly with replacement) that become active at the next step, and these are the only active vertices at the next step. A natural quantity to study for cobra walks is the cover time, which corresponds to the expected time when all nodes have become infected or received the disseminated information. In this article, we extend previous results for cobra walks in multiple ways. We show that the cover time for the 2-cobra walk on $ [0, n]^d $ is $ O(n) $ (where the order notation hides constant factors that depend on $d$); previous work had shown the cover time was $ O(n \cdot \polylog (n))$. We show that the cover time for a 2-cobra walk on an $n$-vertex $d$ regular graph with conductance $ \phi_G$ is $ O(d^4 \phis^{-2}_G \log^2 n)$, significantly generalizing a previous result that held only for expander graphs with sufficiently high expansion. And, finally, we show that the cover time for a 2-cobra walk on a graph with n vertices and m edges is always $ O(m n^{3 / 4} \log n)$; this is the first result showing that the bound of $ \Theta (n^3)$ for the worst-case cover time for random walks can be beaten using 2-cobra walks.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Liu:2018:RAN, author = "Mingmou Liu and Xiaoyin Pan and Yitong Yin", title = "Randomized Approximate Nearest Neighbor Search with Limited Adaptivity", journal = j-TOPC, volume = "5", number = "1", pages = "3:1--3:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3209884", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We study the complexity of parallel data structures for approximate nearest neighbor search in $d$-dimensional Hamming space $ \{ 0, 1 \}^d$. A classic model for static data structures is the cell-probe model [27]. We consider a cell-probe model with limited adaptivity, where given a $ k \geq 1$, a query is resolved by making at most $k$ rounds of parallel memory accesses to the data structure. We give two randomized algorithms that solve the approximate nearest neighbor search using $k$ rounds of parallel memory accesses: --- a simple algorithm with $ O(k (\log d)^{1 / k})$ total number of memory accesses for all $ k \geq 1$ --- an algorithm with $ O(k + (1 / k \log d)^{O(1 / k)})$ total number of memory accesses for all sufficiently large $k$. Both algorithms use data structures of polynomial size. We prove an $ \Omega (1 / k (\log d)^{1 / k})$ lower bound for the total number of memory accesses for any randomized algorithm solving the approximate nearest neighbor search within $ k \leq \log \log d / 2 \log \log \log d$ rounds of parallel memory accesses on any data structures of polynomial size. This lower bound shows that our first algorithm is asymptotically optimal when $ k = O(1)$. And our second algorithm achieves the asymptotically optimal tradeoff between number of rounds and total number of memory accesses. In the extremal case, when $ k = O(\log \log d / \log \log \log d)$ is big enough, our second algorithm matches the $ \Theta (\log \log d / \log \log \log d)$ tight bound for fully adaptive algorithms for approximate nearest neighbor search in [11].", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pandurangan:2018:FDA, author = "Gopal Pandurangan and Peter Robinson and Michele Scquizzato", title = "Fast Distributed Algorithms for Connectivity and {MST} in Large Graphs", journal = j-TOPC, volume = "5", number = "1", pages = "4:1--4:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3209689", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Motivated by the increasing need to understand the algorithmic foundations of distributed large-scale graph computations, we study a number of fundamental graph problems in a message-passing model for distributed computing where $ k \geq 2 $ machines jointly perform computations on graphs with $n$ nodes (typically, $ n \gg k$). The input graph is assumed to be initially randomly partitioned among the $k$ machines, a common implementation in many real-world systems. Communication is point-to-point, and the goal is to minimize the number of communication rounds of the computation. Our main result is an (almost) optimal distributed randomized algorithm for graph connectivity. Our algorithm runs in $ {\tilde O}(n / k^2)$ rounds ($ {\tilde O}$ notation hides a $ \polylog (n)$ factor and an additive $ \polylog (n)$ term). This improves over the best previously known bound of $ {\tilde O}(n / k)$ [Klauck et al., SODA 2015] and is optimal (up to a polylogarithmic factor) in light of an existing lower bound of $ \tilde \Omega (n / k^2)$. Our improved algorithm uses a bunch of techniques, including linear graph sketching, that prove useful in the design of efficient distributed graph algorithms. Using the connectivity algorithm as a building block, we then present fast randomized algorithms for computing minimum spanning trees, (approximate) min-cuts, and for many graph verification problems. All these algorithms take $ {\tilde O}(n / k^2)$ rounds and are optimal up to polylogarithmic factors. We also show an almost matching lower bound of $ \tilde \Omega (n / k^2)$ rounds for many graph verification problems by leveraging lower bounds in random-partition communication complexity.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Korupolu:2018:RPF, author = "Madhukar Korupolu and Rajmohan Rajaraman", title = "Robust and Probabilistic Failure-Aware Placement", journal = j-TOPC, volume = "5", number = "1", pages = "5:1--5:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3210367", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Motivated by the growing complexity and heterogeneity of modern data centers, and the prevalence of commodity component failures, this article studies the failure-aware placement problem of placing tasks of a parallel job on machines in the data center with the goal of increasing availability. We consider two models of failures: adversarial and probabilistic. In the adversarial model, each node has a weight (higher weight implying higher reliability) and the adversary can remove any subset of nodes of total weight at most a given bound W and our goal is to find a placement that incurs the least disruption against such an adversary. In the probabilistic model, each node has a probability of failure and we need to find a placement that maximizes the probability that at least K out of N tasks survive at any time. For adversarial failures, we first show that (i) the problems are in $ \Sigma_2 $, the second level of the polynomial hierarchy; (ii) a variant of the problem that we call RobustFap (for Robust Failure-Aware Placement) is co-NP-hard; and (iii) an all-or-nothing version of RobustFap is $ \Sigma_2$-complete. We then give a polynomial-time approximation scheme (PTAS) for RobustFap, a key ingredient of which is a solution that we design for a fractional version of RobustFap. We then study HierRobustFap, which is the fractional RobustFap problem over a hierarchical network, in which failures can occur at any subset of nodes in the hierarchy, and a failure at a node can adversely impact all of its descendants in the hierarchy. To solve HierRobustFap, we introduce a notion of hierarchical max-min fairness and a novel Generalized Spreading algorithm, which is simultaneously optimal for every upper bound W on the total weight of nodes that an adversary can fail. These generalize the classical notion of max-min fairness to work with nodes of differing capacities, differing reliability weights, and hierarchical structures. Using randomized rounding, we extend this to give an algorithm for integral HierRobustFap. For the probabilistic version, we first give an algorithm that achieves an additive $ \epsilon $ approximation in the failure probability for the single level version, called ProbFap, while giving up a $ (1 + \epsilon)$ multiplicative factor in the number of failures. We then extend the result to the hierarchical version, HierProbFap, achieving an \epsilon additive approximation in failure probability while giving up an $ (L + \epsilon)$ multiplicative factor in the number of failures, where $L$ is the number of levels in the hierarchy.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Zhang:2018:LFT, author = "Deli Zhang and Pierre Laborde and Lance Lebanoff and Damian Dechev", title = "Lock-Free Transactional Transformation for Linked Data Structures", journal = j-TOPC, volume = "5", number = "1", pages = "6:1--6:??", month = sep, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3209690", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Nonblocking data structures allow scalable and thread-safe access to shared data. They provide individual operations that appear to execute atomically. However, it is often desirable to execute multiple operations atomically in a transactional manner. Previous solutions, such as Software Transactional Memory (STM) and transactional boosting, manage transaction synchronization separately from the underlying data structure's thread synchronization. Although this reduces programming effort, it leads to overhead associated with additional synchronization and the need to rollback aborted transactions. In this work, we present a new methodology for transforming high-performance lock-free linked data structures into high-performance lock-free transactional linked data structures without revamping the data structures' original synchronization design. Our approach leverages the semantic knowledge of the data structure to eliminate the overhead of false conflicts and rollbacks. We encapsulate all operations, operands, and transaction status in a transaction descriptor, which is shared among the nodes accessed by the same transaction. We coordinate threads to help finish the remaining operations of delayed transactions based on their transaction descriptors. When a transaction fails, we recover the correct abstract state by reversely interpreting the logical status of a node. We also present an obstruction-free version of our algorithm that can be applied to dynamic execution scenarios and an example of our approach applied to a hash map. In our experimental evaluation using transactions with randomly generated operations, our lock-free transactional data structures outperform the transactional boosted ones by 70\% on average. They also outperform the alternative STM-based approaches by a factor of 2 to 13 across all scenarios. More importantly, we achieve 4,700 to 915,000 times fewer spurious aborts than the alternatives.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Muller:2018:NHP, author = "Michel M{\"u}ller and Takayuki Aoki", title = "New High Performance {GPGPU} Code Transformation Framework Applied to Large Production Weather Prediction Code", journal = j-TOPC, volume = "5", number = "2", pages = "7:1--7:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3291523", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/fortran3.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We introduce ``Hybrid Fortran,'' a new approach that allows a high-performance GPGPU port for structured grid Fortran codes. This technique only requires minimal changes for a CPU targeted codebase, which is a significant advancement in terms of productivity. It has been successfully applied to both dynamical core and physical processes of ASUCA, a Japanese mesoscale weather prediction model with more than 150k lines of code. By means of a minimal weather application that resembles ASUCA's code structure, Hybrid Fortran is compared to both a performance model as well as today's commonly used method, OpenACC. As a result, the Hybrid Fortran implementation is shown to deliver the same or better performance than OpenACC, and its performance agrees with the model both on CPU and GPU. In a full-scale production run, using an ASUCA grid with 1581 $ \times $ 1301 $ \times $ 58 cells and real-world weather data in 2km resolution, 24 NVIDIA Tesla P100 running the Hybrid Fortran-based GPU port are shown to replace more than fifty 18-core Intel Xeon Broadwell E5-2695 v4 running the reference implementation-an achievement comparable to more invasive GPGPU rewrites of other weather models.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Burtscher:2018:HQF, author = "Martin Burtscher and Sindhu Devale and Sahar Azimi and Jayadharini Jaiganesh and Evan Powers", title = "A High-Quality and Fast Maximal Independent Set Implementation for {GPUs}", journal = j-TOPC, volume = "5", number = "2", pages = "8:1--8:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3291525", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Computing a maximal independent set is an important step in many parallel graph algorithms. This article introduces ECL-MIS, a maximal independent set implementation that works well on GPUs. It includes key optimizations to speed up computation, reduce the memory footprint, and increase the set size. Its CUDA implementation requires fewer than 30 kernel statements, runs asynchronously, and produces a deterministic result. It outperforms the maximal independent set implementations of Pannotia, CUSP, and IrGL on each of the 16 tested graphs of various types and sizes. On a Titan X GPU, ECL-MIS is between 3.9 and 100 times faster (11.5 times, on average). ECL-MIS running on the GPU is also faster than the parallel CPU codes Ligra, Ligra+, and PBBS running on 20 Xeon cores, which it outperforms by 4.1 times, on average. At the same time, ECL-MIS produces maximal independent sets that are up to 52\% larger (over 10\%, on average) compared to these preexisting CPU and GPU implementations. Whereas these codes produce maximal independent sets that are, on average, about 15\% smaller than the largest possible such sets, ECL-MIS sets are less than 6\% smaller than the maximum independent sets.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Liu:2018:APR, author = "Junhong Liu and Guangming Tan and Yulong Luo and Jiajia Li and Zeyao Mo and Ninghui Sun", title = "An Autotuning Protocol to Rapidly Build Autotuners", journal = j-TOPC, volume = "5", number = "2", pages = "9:1--9:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3291527", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Automatic performance tuning (Autotuning) is an increasingly critical tuning technique for the high portable performance of Exascale applications. However, constructing an autotuner from scratch remains a challenge, even for domain experts. In this work, we propose a performance tuning and knowledge management suite (PAK) to help rapidly build autotuners. In order to accommodate existing autotuning techniques, we present an autotuning protocol that is composed of an extractor, producer, optimizer, evaluator, and learner. To achieve modularity and reusability, we also define programming interfaces for each protocol component as the fundamental infrastructure, which provides a customizable mechanism to deploy knowledge mining in the performance database. PAK's usability is demonstrated by studying two important computational kernels: stencil computation and sparse matrix-vector multiplication (SpMV). Our proposed autotuner based on PAK shows comparable performance and higher productivity than traditional autotuners by writing just a few tens of code using our autotuning protocol.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Anta:2018:SDP, author = "Antonio Fern{\'a}ndez Anta and Dariusz R. Kowalski and Miguel A. Mosteiro and Prudence W. H. Wong", title = "Scheduling Dynamic Parallel Workload of Mobile Devices with Access Guarantees", journal = j-TOPC, volume = "5", number = "2", pages = "10:1--10:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3291529", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We study a dynamic resource-allocation problem that arises in various parallel computing scenarios, such as mobile cloud computing, cloud computing systems, Internet of Things systems, and others. Generically, we model the architecture as client mobile devices and static base stations. Each client ``arrives'' to the system to upload data to base stations by radio transmissions and then ``leaves.'' The problem, called Station Assignment, is to assign clients to stations so that every client uploads their data under some restrictions, including a target subset of stations, a maximum delay between transmissions, a volume of data to upload, and a maximum bandwidth for each station. We study the solvability of Station Assignment under an adversary that controls the arrival and departure of clients, limited to maximum rate and burstiness of such arrivals. We show upper and lower bounds on the rate and burstiness for various client arrival schedules and protocol classes. To the best of our knowledge, this is the first time that Station Assignment is studied under adversarial arrivals and departures.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Mirhosseini:2018:BBA, author = "Amirhossein Mirhosseini and Mohammad Sadrosadati and Fatemeh Aghamohammadi and Mehdi Modarressi and Hamid Sarbazi-Azad", title = "{BARAN}: Bimodal Adaptive Reconfigurable-Allocator Network-on-Chip", journal = j-TOPC, volume = "5", number = "3", pages = "11:1--11:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3294049", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Virtual channels are employed to improve the throughput under high traffic loads in Networks-on-Chips (NoCs). However, they can impose non-negligible overheads on performance by prolonging clock cycle time, especially under low traffic loads where the impact of virtual channels on performance is trivial. In this article, we propose a novel architecture, called BARAN, that can either improve on-chip network performance or reduce its power consumption (depending on the specific implementation chosen), not both at the same time, when virtual channels are underutilized; that is, the average number of virtual channel allocation requests per cycle is lower than the number of total virtual channels. We also introduce a reconfigurable arbitration logic within the BARAN architecture that can be configured to have multiple latencies and, hence, multiple slack times. The increased slack times are then used to reduce the supply voltage of the routers or increase their clock frequency in order to reduce power consumption or improve the performance of the whole NoC system. The power-centric design of BARAN reduces NoC power consumption by 43.4\% and 40.6\% under CMP and GPU workloads, on average, respectively, compared to a baseline architecture while imposing negligible area and performance overheads. The performance-centric design of BARAN reduces the average packet latency by 45.4\% and 42.1\%, on average, under CMP and GPU workloads, respectively, compared to the baseline architecture while increasing power consumption by 39.7\% and 43.7\%, on average. Moreover, the performance-centric BARAN postpones the network saturation rate by 11.5\% under uniform random traffic compared to the baseline architecture.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Amer:2018:LCM, author = "Abdelhalim Amer and Huiwei Lu and Pavan Balaji and Milind Chabbi and Yanjie Wei and Jeff Hammond and Satoshi Matsuoka", title = "Lock Contention Management in Multithreaded {MPI}", journal = j-TOPC, volume = "5", number = "3", pages = "12:1--12:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3275443", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3275443", abstract = "In this article, we investigate contention management in lock-based thread-safe MPI libraries. Specifically, we make two assumptions: (1) locks are the only form of synchronization when protecting communication paths; and (2) contention occurs, and thus serialization is unavoidable. Our work distinguishes between lock acquisitions with respect to work being performed inside a critical section; productive vs. unproductive. Waiting for message reception without doing anything else inside a critical section is an example of unproductive lock acquisition. We show that the high-throughput nature of modern scalable locking protocols translates into better communication progress for throughput-intensive MPI communication but negatively impacts latency-sensitive communication because of overzealous unproductive lock acquisition. To reduce unproductive lock acquisitions, we devised a method that promotes threads with productive work using a generic two-level priority locking protocol. Our results show that using a high-throughput protocol for productive work and a fair protocol for less productive code paths ensures the best tradeoff for fine-grained communication, whereas a fair protocol is sufficient for more coarse-grained communication. Although these efforts have been rewarding, scalability degradation remains significant. We discuss techniques that diverge from the pure locking model and offer the potential to further improve scalability.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chen:2018:PDG, author = "Rong Chen and Jiaxin Shi and Yanzhe Chen and Binyu Zang and Haibing Guan and Haibo Chen", title = "{PowerLyra}: Differentiated Graph Computation and Partitioning on Skewed Graphs", journal = j-TOPC, volume = "5", number = "3", pages = "13:1--13:??", month = jan, year = "2018", CODEN = "????", DOI = "https://doi.org/10.1145/3298989", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Jan 23 16:12:26 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Natural graphs with skewed distributions raise unique challenges to distributed graph computation and partitioning. Existing graph-parallel systems usually use a ``one-size-fits-all'' design that uniformly processes all vertices, which either suffer from notable load imbalance and high contention for high-degree vertices (e.g., Pregel and GraphLab) or incur high communication cost and memory consumption even for low-degree vertices (e.g., PowerGraph and GraphX). In this article, we argue that skewed distributions in natural graphs also necessitate differentiated processing on high-degree and low-degree vertices. We then introduce PowerLyra, a new distributed graph processing system that embraces the best of both worlds of existing graph-parallel systems. Specifically, PowerLyra uses centralized computation for low-degree vertices to avoid frequent communications and distributes the computation for high-degree vertices to balance workloads. PowerLyra further provides an efficient hybrid graph partitioning algorithm (i.e., hybrid-cut) that combines edge-cut (for low-degree vertices) and vertex-cut (for high-degree vertices) with heuristics. To improve cache locality of inter-node graph accesses, PowerLyra further provides a locality-conscious data layout optimization. PowerLyra is implemented based on the latest GraphLab and can seamlessly support various graph algorithms running in both synchronous and asynchronous execution modes. A detailed evaluation on three clusters using various graph-analytics and MLDM (Machine Learning and Data Mining) applications shows that PowerLyra outperforms PowerGraph by up to 5.53X (from 1.24X) and 3.26X (from 1.49X) for real-world and synthetic graphs, respectively, and is much faster than other systems like GraphX and Giraph, yet with much less memory consumption. A porting of hybrid-cut to GraphX further confirms the efficiency and generality of PowerLyra.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Aravind:2019:GME, author = "Alex Aravind and Wim H. Hesselink", title = "Group Mutual Exclusion by Fetch-and-increment", journal = j-TOPC, volume = "5", number = "4", pages = "14:1--14:??", month = mar, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3309202", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Mar 11 18:54:51 MDT 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3309202", abstract = "The group mutual exclusion (GME) problem (also called the room synchronization problem) arises in various practical applications that require concurrent data sharing. Group mutual exclusion aims to achieve exclusive access to a shared resource (a shared room) while facilitating concurrency among non-conflicting requests. The problem is that threads with distinct interests are not allowed to access the shared resource concurrently, but multiple threads with same interest can. In Blelloch et al. (2003), the authors presented a simple solution to the room synchronization problem using fetch8add (F8A) and test-and-set (T8S) atomic operations. This algorithm has $ O(m) $ remote memory references (RMRs) in the cache coherent (CC) model, where $m$ is the number of forums. In Bhatt and Huang (2010), an open problem was posed: `` Is it possible to design a GME algorithm with constant RMR for the CC model using fetch8add instructions? '' This question is partially answered in this article by presenting a group mutual exclusion algorithm using fetch-and-increment instructions. The algorithm is simple and scalable.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Behzad:2019:OPH, author = "Babak Behzad and Surendra Byna and Prabhat and Marc Snir", title = "Optimizing {I/O} Performance of {HPC} Applications with Autotuning", journal = j-TOPC, volume = "5", number = "4", pages = "15:1--15:??", month = mar, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3309205", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Mar 11 18:54:51 MDT 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3309205", abstract = "Parallel Input output is an essential component of modern high-performance computing (HPC). Obtaining good I/O performance for a broad range of applications on diverse HPC platforms is a major challenge, in part, because of complex inter dependencies between I/O middleware and hardware. The parallel file system and I/O middleware layers all offer optimization parameters that can, in theory, result in better I/O performance. Unfortunately, the right combination of parameters is highly dependent on the application, HPC platform, problem size, and concurrency. Scientific application developers do not have the time or expertise to take on the substantial burden of identifying good parameters for each problem configuration. They resort to using system defaults, a choice that frequently results in poor I/O performance. We expect this problem to be compounded on exascale-class machines, which will likely have a deeper software stack with hierarchically arranged hardware resources. We present as a solution to this problem an autotuning system for optimizing I/O performance, I/O performance modeling, I/O tuning, and I/O patterns. We demonstrate the value of this framework across several HPC platforms and applications at scale.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Maier:2019:CHT, author = "Tobias Maier and Peter Sanders and Roman Dementiev", title = "Concurrent Hash Tables: Fast and General(?)!", journal = j-TOPC, volume = "5", number = "4", pages = "16:1--16:??", month = mar, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3309206", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Mar 11 18:54:51 MDT 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3309206", abstract = "Concurrent hash tables are one of the most important concurrent data structures, which are used in numerous applications. For some applications, it is common that hash table accesses dominate the execution time. To efficiently solve these problems in parallel, we need implementations that achieve speedups in highly concurrent scenarios. Unfortunately, currently available concurrent hashing libraries are far away from this requirement, in particular, when adaptively sized tables are necessary or contention on some elements occurs. Our starting point for better performing data structures is a fast and simple lock-free concurrent hash table based on linear probing that is, however, limited to word-sized key-value types and does not support dynamic size adaptation. We explain how to lift these limitations in a provably scalable way and demonstrate that dynamic growing has a performance overhead comparable to the same generalization in sequential hash tables. We perform extensive experiments comparing the performance of our implementations with six of the most widely used concurrent hash tables. Ours are considerably faster than the best algorithms with similar restrictions and an order of magnitude faster than the best more general tables. In some extreme cases, the difference even approaches four orders of magnitude. All our implementations discussed in this publication can be found on github [17].", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cruz:2019:ETM, author = "Eduardo H. M. Cruz and Matthias Diener and La{\'e}rcio L. Pilla and Philippe O. A. Navaux", title = "{EagerMap}: a Task Mapping Algorithm to Improve Communication and Load Balancing in Clusters of Multicore Systems", journal = j-TOPC, volume = "5", number = "4", pages = "17:1--17:??", month = mar, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3309711", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Mar 11 18:54:51 MDT 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3309711", abstract = "Communication between tasks and load imbalance have been identified as a major challenge for the performance and energy efficiency of parallel applications. A common way to improve communication is to increase its locality, that is, to reduce the distances of data transfers, prioritizing the usage of faster and more efficient local interconnections over remote ones. Regarding load imbalance, cores should execute a similar amount of work. An important problem to be solved in this context is how to determine an optimized mapping of tasks to cluster nodes and cores that increases the overall locality and load balancing. In this article, we propose the EagerMap algorithm to determine task mappings, which is based on a greedy heuristic to match application communication patterns to hardware hierarchies and which can also consider the task load. Compared to previous algorithms, EagerMap is faster, scales better, and supports more types of computer systems, while maintaining the same or better quality of the determined task mapping. EagerMap is therefore an interesting choice for task mapping on a variety of modern parallel architectures.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bader:2019:EEC, author = "David A. Bader", title = "Editorial from the {Editor-in-Chief}", journal = j-TOPC, volume = "6", number = "1", pages = "1:1--1:??", month = jun, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3325883", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:58 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3325883", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kronbichler:2019:MMF, author = "Martin Kronbichler and Karl Ljungkvist", title = "Multigrid for Matrix-Free High-Order Finite Element Computations on Graphics Processors", journal = j-TOPC, volume = "6", number = "1", pages = "2:1--2:??", month = jun, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3322813", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:58 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3322813", abstract = "This article presents matrix-free finite-element techniques for efficiently solving partial differential equations on modern many-core processors, such as graphics cards. We develop a GPU parallelization of a matrix-free geometric multigrid iterative solver targeting moderate and high polynomial degrees, with support for general curved and adaptively refined hexahedral meshes with hanging nodes. The central algorithmic component is the matrix-free operator evaluation with sum factorization. We compare the node-level performance of our implementation running on an Nvidia Pascal P100 GPU to a highly optimized multicore implementation running on comparable Intel Broadwell CPUs and an Intel Xeon Phi. Our experiments show that the GPU implementation is approximately 1.5 to 2 times faster across four different scenarios of the Poisson equation and a variety of element degrees in 2D and 3D. The lowest time to solution per degree of freedom is recorded for moderate polynomial degrees between 3 and 5. A detailed performance analysis highlights the capabilities of the GPU architecture and the chosen execution model with threading within the element, particularly with respect to the evaluation of the matrix-vector product. Atomic intrinsics are shown to provide a fast way for avoiding the possible race conditions in summing the elemental residuals into the global vector associated to shared vertices, edges, and surfaces. In addition, the solver infrastructure allows for using mixed-precision arithmetic that performs the multigrid V-cycle in single precision with an outer correction in double precision, increasing throughput by up to 83", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bonifaci:2019:GPT, author = "Vincenzo Bonifaci and Andreas Wiese and Sanjoy K. Baruah and Alberto Marchetti-Spaccamela and Sebastian Stiller and Leen Stougie", title = "A Generalized Parallel Task Model for Recurrent Real-Time Processes", journal = j-TOPC, volume = "6", number = "1", pages = "3:1--3:??", month = jun, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3322809", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:58 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3322809", abstract = "A model is considered for representing recurrent precedence-constrained tasks that are to execute on multiprocessor platforms. A recurrent task is specified as a directed acyclic graph (DAG), a period, and a relative deadline. Each vertex of the DAG represents a sequential job, while the edges of the DAG represent precedence constraints between these jobs. All the jobs of the DAG are released simultaneously and need to complete execution within the specified relative deadline of their release. Each task may release jobs in this manner an unbounded number of times, with successive releases occurring at least the specified period apart. Conditional control structures are also allowed. The scheduling problem is to determine whether a set of such recurrent tasks can be scheduled to always meet all deadlines upon a specified number of identical processors. This problem is shown to be computationally intractable, but amenable to efficient approximate solutions. Earliest Deadline First (EDF) and Deadline Monotonic (DM) are shown to be good approximate global scheduling algorithms. Polynomial and pseudo-polynomial time schedulability tests, of differing effectiveness, are presented for determining whether a given task set can be scheduled by EDF or DM to always meet deadlines on a specified number of processors.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ltaief:2019:MPP, author = "Hatem Ltaief and Dalal Sukkari and Aniello Esposito and Yuji Nakatsukasa and David Keyes", title = "Massively Parallel Polar Decomposition on Distributed-memory Systems", journal = j-TOPC, volume = "6", number = "1", pages = "4:1--4:??", month = jun, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3328723", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:58 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3328723", abstract = "We present a high-performance implementation of the Polar Decomposition (PD) on distributed-memory systems. Building upon on the QR-based Dynamically Weighted Halley (QDWH) algorithm, the key idea lies in finding the best rational approximation for the scalar sign function, which also corresponds to the polar factor for symmetric matrices, to further accelerate the QDWH convergence. Based on the Zolotarev rational functions-introduced by Zolotarev (ZOLO) in 1877-this new PD algorithm ZOLO-PD converges within two iterations even for ill-conditioned matrices, instead of the original six iterations needed for QDWH. ZOLO-PD uses the property of Zolotarev functions that optimality is maintained when two functions are composed in an appropriate manner. The resulting ZOLO-PD has a convergence rate up to 17, in contrast to the cubic convergence rate for QDWH. This comes at the price of higher arithmetic costs and memory footprint. These extra floating-point operations can, however, be processed in an embarrassingly parallel fashion. We demonstrate performance using up to 102,400 cores on two supercomputers. We demonstrate that, in the presence of a large number of processing units, ZOLO-PD is able to outperform QDWH by up to 2.3$ \times $ speedup, especially in situations where QDWH runs out of work, for instance, in the strong scaling mode of operation.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Saha:2019:OSA, author = "Dibakar Saha and Koushik Sinha", title = "Optimal Schedule for All-to-All Personalized Communication in Multiprocessor Systems", journal = j-TOPC, volume = "6", number = "1", pages = "5:1--5:??", month = jun, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3329867", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:58 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3329867", abstract = "In this article, we address the problem of finding an optimal schedule for all-to-all personalized message communication among the processors in a multiprocessor system where every processor has a unique message for every other processor. When there are n processors and \lfloor n /2 \rfloor parallel databus or channels for message communications, there exist algorithms that require O ( n$^2$ ) time for assigning the databus/channels to the processor-pairs to obtain a schedule with minimum number of time slots. However, in recent massively parallel processing systems with a huge number of processors, the number k of available databus/channels is usually much smaller than \lfloor n /2", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pumma:2019:SDL, author = "Sarunya Pumma and Min Si and Wu-Chun Feng and Pavan Balaji", title = "Scalable Deep Learning via {I/O} Analysis and Optimization", journal = j-TOPC, volume = "6", number = "2", pages = "6:1--6:??", month = sep, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3331526", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3331526", abstract = "Scalable deep neural network training has been gaining prominence because of the increasing importance of deep learning in a multitude of scientific and commercial domains. Consequently, a number of researchers have investigated techniques to optimize deep learning systems. Much of the prior work has focused on runtime and algorithmic enhancements to optimize the computation and communication. Despite these enhancements, however, deep learning systems still suffer from scalability limitations, particularly with respect to data I/O. This situation is especially true for training models where the computation can be effectively parallelized, leaving I/O as the major bottleneck. In fact, our analysis shows that I/O can take up to 90", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Aupy:2019:SSP, author = "Guilllaume Aupy and Ana Gainaru and Valentin {Le F{\`e}vre}", title = "{I/O} Scheduling Strategy for Periodic Applications", journal = j-TOPC, volume = "6", number = "2", pages = "7:1--7:??", month = sep, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3338510", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3338510", abstract = "With the ever-growing need of data in HPC applications, the congestion at the I/O level becomes critical in supercomputers. Architectural enhancement such as burst buffers and pre-fetching are added to machines but are not sufficient to prevent congestion. Recent online I/O scheduling strategies have been put in place, but they add an additional congestion point and overheads in the computation of applications. In this work, we show how to take advantage of the periodic nature of HPC applications to develop efficient periodic scheduling strategies for their I/O transfers. Our strategy computes once during the job scheduling phase a pattern that defines the I/O behavior for each application, after which the applications run independently, performing their I/O at the specified times. Our strategy limits the amount of congestion at the I/O node level and can be easily integrated into current job schedulers. We validate this model through extensive simulations and experiments on an HPC cluster by comparing it to state-of-the-art online solutions, showing that not only does our scheduler have the advantage of being de-centralized and thus overcoming the overhead of online schedulers, but also that it performs better than the other solutions, improving the application dilation up to 16", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kagaris:2019:SME, author = "Dimitri Kagaris and Sourav Dutta", title = "Scheduling Mutual Exclusion Accesses in Equal-Length Jobs", journal = j-TOPC, volume = "6", number = "2", pages = "8:1--8:??", month = sep, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3342562", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3342562", abstract = "A fundamental problem in parallel and distributed processing is the partial serialization that is imposed due to the need for mutually exclusive access to common resources. In this article, we investigate the problem of optimally scheduling (in terms of makespan) a set of jobs, where each job consists of the same number L of unit-duration tasks, and each task either accesses exclusively one resource from a given set of resources or accesses a fully shareable resource. We develop and establish the optimality of a fast polynomial-time algorithm to find a schedule with the shortest makespan for any number of jobs and for any number of resources for the case of L = 2. In the notation commonly used for job-shop scheduling problems, this result means that the problem J | d$_{ij}$ =1, n$_j$ =2| C$_{max}$ is polynomially solvable, adding to the polynomial solutions known for the problems J 2 | n$_j$ {$<$}= 2 | C$_{max}$ and J 2 | d$_{ij}$ = 1 | C$_{max}$ (whereas other closely related versions such as J 2 | n$_j$ \leq 3 | C$_{max}$, J 2 | d$_{ij}$ ) \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Mollah:2019:MUG, author = "Md Atiqul Mollah and Wenqi Wang and Peyman Faizian and MD Shafayat Rahman and Xin Yuan and Scott Pakin and Michael Lang", title = "Modeling Universal Globally Adaptive Load-Balanced Routing", journal = j-TOPC, volume = "6", number = "2", pages = "9:1--9:??", month = sep, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3349620", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3349620", abstract = "Universal globally adaptive load-balanced (UGAL) routing has been proposed for various interconnection networks and has been deployed in a number of current-generation supercomputers. Although UGAL-based schemes have been extensively studied, most existing results are based on either simulation or measurement. Without a theoretical understanding of UGAL, multiple questions remain: For which traffic patterns is UGAL most suited? In addition, what determines the performance of the UGAL-based scheme on a particular network configuration? In this work, we develop a set of throughput models for UGALbased on linear programming. We show that the throughput models are valid across the torus, Dragonfly, and Slim Fly network topologies. Finally, we identify a robust model that can accurately and efficiently predict UGAL throughput for a set of representative traffic patterns across different topologies. Our models not only provide a mechanism to predict UGAL performance on large-scale interconnection networks but also reveal the inner working of UGAL and further our understanding of this type of routing.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bateni:2019:ISI, author = "Mohammed Hossein Bateni and Mohammad T. Hajiaghayi and Silvio Lattanzi", title = "Introduction to the Special Issue for {SPAA'17}", journal = j-TOPC, volume = "6", number = "3", pages = "10:1--10:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3363417", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3363417", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Guha:2019:DPC, author = "Sudipto Guha and Yi Li and Qin Zhang", title = "Distributed Partial Clustering", journal = j-TOPC, volume = "6", number = "3", pages = "11:1--11:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3322808", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3322808", abstract = "Recent years have witnessed an increasing popularity of algorithm design for distributed data, largely due to the fact that massive datasets are often collected and stored in different locations. In the distributed setting, communication typically dominates the query processing time. Thus, it becomes crucial to design communication-efficient algorithms for queries on distributed data. Simultaneously, it has been widely recognized that partial optimizations, where we are allowed to disregard a small part of the data, provide us significantly better solutions. The motivation for disregarded points often arises from noise and other phenomena that are pervasive in large data scenarios. In this article, we focus on partial clustering problems, k -center, k -median, and k -means objectives in the distributed model, and provide algorithms with communication sublinear of the input size. As a consequence, we develop the first algorithms for the partial k -median and means objectives that run in subquadratic running time. We also initiate the study of distributed algorithms for clustering uncertain data, where each data point can possibly fall into multiple locations under certain probability distribution.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Fraigniaud:2019:DDC, author = "Pierre Fraigniaud and Dennis Olivetti", title = "Distributed Detection of Cycles", journal = j-TOPC, volume = "6", number = "3", pages = "12:1--12:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3322811", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3322811", abstract = "Distributed property testing in networks has been introduced by Brakerski and Patt-Shamir [6], with the objective of detecting the presence of large dense sub-networks in a distributed manner. Recently, Censor-Hillel et al. [7] have revisited this notion and formalized it in a broader context. In particular, they have shown how to detect 3-cycles in a constant number of rounds by a distributed algorithm. In a follow-up work, Fraigniaud et al. [21] have shown how to detect 4-cycles in a constant number of rounds as well. However, the techniques in these latter works were shown not to generalize to larger cycles C$_k$ with k {$>$}= 5. In this article, we completely settle the problem of cycle detection by establishing the following result: For every k {$>$}= 3, there exists a distributed property testing algorithm for C$_k$ -freeness, performing in a constant number of rounds. All these results hold in the classical congest model for distributed network computing. Our algorithm is 1-sided error. Its round-complexity is O (1 \epsilon ) where \epsilon \in (0,1) is the property-testing parameter measuring the gap between legal and illegal instances.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Albers:2019:ECD, author = "Susanne Albers", title = "On Energy Conservation in Data Centers", journal = j-TOPC, volume = "6", number = "3", pages = "13:1--13:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364210", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364210", abstract = "We formulate and study an optimization problem that arises in the energy management of data centers and, more generally, multiprocessor environments. Data centers host a large number of heterogeneous servers. Each server has an active state and several standby/sleep states with individual power consumption rates. The demand for computing capacity varies over time. Idle servers may be transitioned to low-power modes so as to rightsize the pool of active servers. The goal is to find a state transition schedule for the servers that minimizes the total energy consumed. On a small scale, the same problem arises in multicore architectures with heterogeneous processors on a chip. One has to determine active and idle periods for the cores so as to guarantee a certain service and minimize the consumed energy. For this power/capacity management problem, we develop two main results. We use the terminology of the data center setting. First, we investigate the scenario that each server has two states: an active state and a sleep state. We show that an optimal solution, minimizing energy consumption, can be computed in polynomial time by a combinatorial algorithm. The algorithm resorts to a single-commodity minimum-cost flow computation. Second, we study the general scenario that each server has an active state and multiple standby/sleep states. We devise a", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Feldkord:2019:MSP, author = "Bj{\"o}rn Feldkord and Friedhelm Meyer Auf Der Heide", title = "The Mobile Server Problem", journal = j-TOPC, volume = "6", number = "3", pages = "14:1--14:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364204", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364204", abstract = "We introduce the Mobile Server problem, inspired by current trends to move computational tasks from cloud structures to multiple devices close to the end user. An example of this is embedded systems in autonomous cars that communicate to coordinate their actions. Our model is a variant of the classical Page Migration problem. More formally, we consider a mobile server holding a data page. The server can move in the Euclidean space (of arbitrary dimension). In every round, requests for data items from the page pop up at arbitrary points in the space. The requests are served, each at a cost of the distance from the requesting point and the server, and the mobile server may move, at a cost D times the distance traveled for some constant D. We assume a maximum distance m that the server is allowed to move per round. We show that no online algorithm can achieve a competitive ratio independent of the length of the input sequence in this setting. Hence, we augment the maximum movement distance of the online algorithms to \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Azar:2019:TBC, author = "Yossi Azar and Danny Vainstein", title = "Tight Bounds for Clairvoyant Dynamic Bin Packing", journal = j-TOPC, volume = "6", number = "3", pages = "15:1--15:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364214", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364214", abstract = "In this article, we focus on the Clairvoyant Dynamic Bin Packing (DBP) problem, which extends the Classical Online Bin Packing problem in that items arrive and depart over time and the departure time of an item is known upon its arrival. The problem naturally arises when handling cloud-based networks. We focus specifically on the MinUsageTime objective function, which aims to minimize the overall usage time of all bins that are opened during the packing process. Earlier work has shown a O (log \mu / log log \mu) upper bound on the algorithm's competitiveness, where \mu is defined as the ratio between the maximal and minimal durations of all items. We improve the upper bound by giving a \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cooper:2019:NCT, author = "Colin Cooper and Tomasz Radzik and Nicolas Rivera", title = "New Cover Time Bounds for the Coalescing-Branching Random Walk on Graphs", journal = j-TOPC, volume = "6", number = "3", pages = "16:1--16:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364206", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364206", abstract = "We present new bounds on the cover time of the coalescing-branching random walk process COBRA. The COBRA process, introduced in Dutta et al. [9], can be viewed as spreading a single item of information throughout an undirected graph in synchronised rounds. In each round, each vertex that has received the information in the previous round (possibly simultaneously from more than one neighbour and possibly not for the first time), ``pushes'' the information to k randomly selected neighbours. The COBRA process is typically studied for integer branching rates k {$>$}= 2 (with the case k =1 corresponding to a random walk). The aim of the process is to propagate the information quickly, but with a limited number of transmissions per vertex per round. The COBRA cover time is the expected number of rounds until all vertices have received the information at least once. Our main results are bounds of O ( m + ( d$_{max}$ )$^2$ log n ) and O ( m log n ) on the COBRA cover time for arbitrary connected graphs with n vertices, m edges and maximum graph degree d$_{max}$, and bounds of \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sun:2019:DGC, author = "He Sun and Luca Zanetti", title = "Distributed Graph Clustering and Sparsification", journal = j-TOPC, volume = "6", number = "3", pages = "17:1--17:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364208", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364208", abstract = "Graph clustering is a fundamental computational problem with a number of applications in algorithm design, machine learning, data mining, and analysis of social networks. Over the past decades, researchers have proposed a number of algorithmic design methods for graph clustering. Most of these methods, however, are based on complicated spectral techniques or convex optimisation and cannot be directly applied for clustering many networks that occur in practice, whose information is often collected on different sites. Designing a simple and distributed clustering algorithm is of great interest and has comprehensive applications for processing big datasets. In this article, we present a simple and distributed algorithm for graph clustering: For a wide class of graphs that are characterised by a strong cluster-structure, our algorithm finishes in a poly-logarithmic number of rounds and recovers a partition of the graph close to optimal. One of the main procedures behind our algorithm is a sampling scheme that, given a dense graph as input, produces a sparse subgraph that provably preserves the cluster-structure of the input. Compared with previous sparsification algorithms that require Laplacian solvers or involve combinatorial constructions, this procedure is easy to implement in a distributed setting and runs fast in practice.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Khan:2019:NOP, author = "Shahbaz Khan", title = "Near Optimal Parallel Algorithms for Dynamic {DFS} in Undirected Graphs", journal = j-TOPC, volume = "6", number = "3", pages = "18:1--18:??", month = oct, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3364212", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3364212", abstract = "Depth first search (DFS) tree is a fundamental data structure for solving various graph problems. The classical algorithm [54] for building a DFS tree requires O ( m + n ) time for a given undirected graph G having n vertices and m edges. Recently, Baswana et al. [5] presented a simple algorithm for updating the DFS tree of an undirected graph after an edge/vertex update in {\tilde O}( n )$^1$ time. However, their algorithm is strictly sequential. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Rauchwerger:2019:ISI, author = "Lawrence Rauchwerger and Jaejin Lee and Armando Solar-Lezama and Guy Steele", title = "Introduction to the Special Issue on {PPoPP} 2017 (Part 1)", journal = j-TOPC, volume = "6", number = "4", pages = "19:1--19:??", month = dec, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3373151", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 27 16:13:12 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19e", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Schardl:2019:TER, author = "Tao B. Schardl and William S. Moses and Charles E. Leiserson", title = "{Tapir}: Embedding Recursive Fork-join Parallelism into {LLVM}'s Intermediate Representation", journal = j-TOPC, volume = "6", number = "4", pages = "19:1--19:??", month = dec, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365655", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 27 16:13:12 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3365655", abstract = "Tapir (pronounced TAY-per) is a compiler intermediate representation (IR) that embeds recursive fork-join parallelism, as supported by task-parallel programming platforms such as Cilk and OpenMP, into a mainstream compiler's IR. Mainstream compilers typically treat parallel linguistic constructs as syntactic sugar for function calls into a parallel runtime. These calls prevent the compiler from performing optimizations on and across parallel control constructs. Remedying this situation has generally been thought to require an extensive reworking of compiler analyses and code transformations to handle parallel semantics. Tapir leverages the ``serial-projection property,'' which is commonly satisfied by task-parallel programs, to handle the semantics of these programs without an extensive rework of the compiler. For recursive fork-join programs that satisfy the serial-projection property, Tapir enables effective compiler optimization of parallel programs with only minor changes to existing compiler analyses and code transformations. Tapir uses the serial-projection property to order logically parallel fine-grained tasks in the program's control-flow graph. This ordered representation of parallel tasks allows the compiler to optimize parallel codes effectively with only minor modifications. For example, to implement Tapir/LLVM, a prototype of Tapir in the LLVM compiler, we added or modified less than 3,000 lines of LLVM's half-million-line core middle-end functionality. These changes sufficed to enable LLVM's existing compiler optimizations for serial code-including loop-invariant-code motion, common-subexpression elimination, and tail-recursion elimination-to work with parallel control constructs such as parallel loops and Cilk's Cilk\_Spawn keyword. Tapir also supports parallel optimizations, such as loop scheduling, which restructure the parallel control flow of the program. By making use of existing LLVM optimizations and new parallel optimizations, Tapir/LLVM can optimize recursive fork-join programs more effectively than traditional compilation methods. On a suite of 35 Cilk application benchmarks, Tapir/LLVM produces more efficient executables for 30 benchmarks, with faster 18-core running times for 26 of them, compared to a nearly identical compiler that compiles parallel linguistic constructs the traditional way.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Utterback:2019:POR, author = "Robert Utterback and Kunal Agrawal and I-Ting Angelina Lee and Milind Kulkarni", title = "Processor-Oblivious Record and Replay", journal = j-TOPC, volume = "6", number = "4", pages = "20:1--20:??", month = dec, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365659", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 27 16:13:12 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/ft_gateway.cfm?id=3365659", abstract = "Record-and-replay systems are useful tools for debugging non-deterministic parallel programs by first recording an execution and then replaying that execution to produce the same access pattern. Existing record-and-replay systems generally target thread-based execution models, and record the behaviors and interleavings of individual threads. Dynamic multithreaded languages and libraries, such as the Cilk family, OpenMP, TBB, and the like, do not have a notion of threads. Instead, these languages provide a processor-oblivious model of programming, where programs expose task parallelism using high-level constructs such as spawn/sync without regard to the number of threads/cores available to run the program. Thread-based record-and-replay would violate the processor-oblivious nature of these programs, as they incorporate the number of threads into the recorded information, constraining the replayed execution to the same number of threads. In this article, we present a processor-oblivious record-and-replay scheme for dynamic multithreaded languages where record and replay can use different number of processors and both are scheduled using work stealing. We provide theoretical guarantees for our record and replay scheme-namely that record is optimal for programs with one lock and replay is near-optimal for all cases. In addition, we implemented this scheme in the Cilk Plus runtime system and our evaluation indicates that processor-obliviousness does not cause substantial overheads.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Yeh:2019:PGR, author = "Tsung Tai Yeh and Amit Sabne and Putt Sakdhnagool and Rudolf Eigenmann and Timothy G. Rogers", title = "{Pagoda}: a {GPU} Runtime System for Narrow Tasks", journal = j-TOPC, volume = "6", number = "4", pages = "21:1--21:??", month = nov, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365657", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Massively multithreaded GPUs achieve high throughput by running thousands of threads in parallel. To fully utilize the their hardware, contemporary workloads spawn work to the GPU in bulk by launching large tasks, where each task is a kernel that contains thousands of threads that occupy the entire GPU. GPUs face severe underutilization and their performance benefits vanish if the tasks are narrow, i.e., they contain less than 512 threads. Latency-sensitive applications in network, signal, and image processing that generate a large number of tasks with relatively small inputs are examples of such limited parallelism. This article presents Pagoda, a runtime system that virtualizes GPU resources, using an OS-like daemon kernel called MasterKernel. Tasks are spawned from the CPU onto Pagoda as they become available, and are scheduled by the MasterKernel at the warp granularity. This level of control enables the GPU to keep scheduling and executing tasks as long as free warps are found, dramatically reducing underutilization. Experimental results on real hardware demonstrate that Pagoda achieves a geometric mean speedup of 5.52X over PThreads running on a 20-core CPU, 1.76X over CUDA-HyperQ, and 1.44X over GeMTC, the state-of-the-art runtime GPU task scheduling system.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Steele:2019:UBP, author = "Guy L. {Steele Jr.} and Jean-Baptiste Tristan", title = "Using Butterfly-patterned Partial Sums to Draw from Discrete Distributions", journal = j-TOPC, volume = "6", number = "4", pages = "22:1--22:??", month = nov, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365662", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/prng.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "We describe a SIMD technique for drawing values from multiple discrete distributions, such as sampling from the random variables of a mixture model, that avoids computing a complete table of partial sums of the relative probabilities. A table of alternate (``butterfly-patterned'') form is faster to compute, making better use of coalesced memory accesses; from this table, complete partial sums are computed on the fly during a binary search. Measurements using Cuda 7.5 on an NVIDIA Titan Black GPU show that this technique makes an entire machine-learning application that uses a Latent Dirichlet Allocation topic model with 1,024 topics about 13\% faster (when using single-precision floating-point data) or about 35\% faster (when using double-precision floating-point data) than doing a straightforward matrix transposition after using coalesced accesses.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Vandierendonck:2019:HDI, author = "Hans Vandierendonck and Dimitrios S. Nikolopoulos", title = "Hyperqueues: Design and Implementation of Deterministic Concurrent Queues", journal = j-TOPC, volume = "6", number = "4", pages = "23:1--23:??", month = nov, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365660", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Nov 20 07:59:59 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The hyperqueue is a programming abstraction for queues that results in deterministic and scale-free parallel programs. Hyperqueues extend the concept of Cilk++ hyperobjects to provide thread-local views on a shared data structure. While hyperobjects are organized around private local views, hyperqueues provide a shared view on a queue data structure. Hereby, hyperqueues guarantee determinism for programs using concurrent queues. We define the programming API and semantics of two instances of the hyperqueue concept. These hyperqueues differ in their API and the degree of concurrency that is extracted. We describe the implementation of the hyperqueues in a work-stealing scheduler and demonstrate scalable performance on pipeline-parallel benchmarks from PARSEC and StreamIt.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "23", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ren:2019:ESP, author = "Bin Ren and Shruthi Balakrishna and Youngjoon Jo and Sriram Krishnamoorthy and Kunal Agrawal and Milind Kulkarni", title = "Extracting {SIMD} Parallelism from Recursive Task-Parallel Programs", journal = j-TOPC, volume = "6", number = "4", pages = "24:1--24:??", month = dec, year = "2019", CODEN = "????", DOI = "https://doi.org/10.1145/3365663", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 27 16:13:12 MST 2019", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "The pursuit of computational efficiency has led to the proliferation of throughput-oriented hardware, from GPUs to increasingly wide vector units on commodity processors and accelerators. This hardware is designed to execute data-parallel computations in a vectorized manner efficiently. However, many algorithms are more naturally expressed as divide-and-conquer, recursive, task-parallel computations. In the absence of data parallelism, it seems that such algorithms are not well suited to throughput-oriented architectures. This article presents a set of novel code transformations that expose the data parallelism latent in recursive, task-parallel programs. These transformations facilitate straightforward vectorization of task-parallel programs on commodity hardware. We also present scheduling policies that maintain high utilization of vector resources while limiting space usage. Across several task-parallel benchmarks, we demonstrate both efficient vector resource utilization and substantial speedup on chips using Intel's SSE4.2 vector units, as well as accelerators using Intel's AVX512 units. We then show through rigorous sampling that, in practice, our vectorization techniques are effective for a much larger class of programs.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "24", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Tumeo:2020:ITSa, author = "Antonino Tumeo and Fabrizio Petrini and John Feo and Mahantesh Halappanavar", title = "Introduction to the {TOPC} Special Issue on Innovations in Systems for Irregular Applications, {Part 1}", journal = j-TOPC, volume = "7", number = "1", pages = "1:1--1:2", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3383318", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3383318", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Anzt:2020:LBS, author = "Hartwig Anzt and Terry Cojean and Chen Yen-Chen and Jack Dongarra and Goran Flegar and Pratik Nayak and Stanimire Tomov and Yuhsiang M. Tsai and Weichung Wang", title = "Load-balancing Sparse Matrix Vector Product Kernels on {GPUs}", journal = j-TOPC, volume = "7", number = "1", pages = "2:1--2:26", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380930", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380930", abstract = "Efficient processing of Irregular Matrices on Single Instruction, Multiple Data (SIMD)-type architectures is a persistent challenge. Resolving it requires innovations in the development of data formats, computational techniques, and implementations that strike a balance between thread divergence, which is inherent for Irregular Matrices, and padding, which alleviates the performance-detrimental thread divergence but introduces artificial overheads. To this end, in this article, we address the challenge of designing high performance sparse matrix-vector product (SpMV) kernels designed for Nvidia Graphics Processing Units (GPUs). We present a compressed sparse row (CSR) format suitable for unbalanced matrices. We also provide a load-balancing kernel for the coordinate (COO) matrix format and extend it to a hybrid algorithm that stores part of the matrix in SIMD-friendly Ellpack format (ELL) format. The ratio between the ELL- and the COO-part is determined using a theoretical analysis of the nonzeros-per-row distribution. For the over 2,800 test matrices available in the Suite Sparse matrix collection, we compare the performance against SpMV kernels provided by NVIDIA's cuSPARSE library and a heavily-tuned sliced ELL (SELL-P) kernel that prevents unnecessary padding by considering the irregular matrices as a combination of matrix blocks stored in ELL format.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hadade:2020:SPU, author = "Ioan Hadade and Timothy M. Jones and Feng Wang and Luca di Mare", title = "Software Prefetching for Unstructured Mesh Applications", journal = j-TOPC, volume = "7", number = "1", pages = "3:1--3:23", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380932", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380932", abstract = "This article demonstrates the utility and implementation of software prefetching in an unstructured finite volume computational fluid dynamics code of representative size and complexity to an industrial application and across a number of modern \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Grutzmacher:2020:APC, author = "Thomas Gr{\"u}tzmacher and Terry Cojean and Goran Flegar and Hartwig Anzt and Enrique S. Quintana-Ort{\'\i}", title = "Acceleration of {PageRank} with Customized Precision Based on Mantissa Segmentation", journal = j-TOPC, volume = "7", number = "1", pages = "4:1--4:19", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380934", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/fparith.bib; https://www.math.utah.edu/pub/tex/bib/pagerank.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380934", abstract = "We describe the application of a communication-reduction technique for the PageRank algorithm that dynamically adapts the precision of the data access to the numerical requirements of the algorithm as the iteration converges. Our variable-precision strategy, using a customized precision format based on mantissa segmentation (CPMS), abandons the IEEE 754 single- and double-precision number representation formats employed in the standard implementation of PageRank, and instead handles the data in memory using a customized floating-point format. The customized format enables fast data access in different accuracy, prevents overflow/underflow by preserving the IEEE 754 double-precision exponent, and efficiently avoids data duplication, since all bits of the original IEEE 754 double-precision mantissa are preserved in memory, but re-organized for efficient reduced precision access. With this approach, the truncated values (omitting significand bits), as well as the original IEEE double-precision values, can be retrieved without duplicating the data in different formats.\par Our numerical experiments on an NVIDIA V100 GPU (Volta architecture) and a server equipped with two Intel Xeon Platinum 8168 CPUs (48 cores in total) expose that, compared with a standard IEEE double-precision implementation, the CPMS-based PageRank completes about 10\% faster if high-accuracy output is needed, and about 30\% faster if reduced output accuracy is acceptable.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Das:2020:SMP, author = "Apurba Das and Seyed-Vahid Sanei-Mehri and Srikanta Tirthapura", title = "Shared-memory Parallel Maximal Clique Enumeration from Static and Dynamic Graphs", journal = j-TOPC, volume = "7", number = "1", pages = "5:1--5:28", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380936", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380936", abstract = "Maximal Clique Enumeration (MCE) is a fundamental graph mining problem and is useful as a primitive in identifying dense structures in a graph. Due to the high computational cost of MCE, parallel methods are imperative for dealing with large graphs. We \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hamilton:2020:ASC, author = "Kathleen E. Hamilton and Catherine D. Schuman and Steven R. Young and Ryan S. Bennink and Neena Imam and Travis S. Humble", title = "Accelerating Scientific Computing in the Post-{Moore}'s Era", journal = j-TOPC, volume = "7", number = "1", pages = "6:1--6:31", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380940", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380940", abstract = "Novel uses of graphical processing units for accelerated computation revolutionized the field of high-performance scientific computing by providing specialized workflows tailored to algorithmic requirements. As the era of Moore's law draws to a close, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lakhotia:2020:GSC, author = "Kartik Lakhotia and Rajgopal Kannan and Sourav Pati and Viktor Prasanna", title = "{GPOP}: a Scalable Cache- and Memory-efficient Framework for Graph Processing over Parts", journal = j-TOPC, volume = "7", number = "1", pages = "7:1--7:24", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380942", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380942", abstract = "The past decade has seen the development of many shared-memory graph processing frameworks intended to reduce the effort of developing high-performance parallel applications. However, many of these frameworks, based on Vertex-centric or Edge-centric \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Anderson:2020:RRO, author = "Jeff Anderson and Engin Kayraklioglu and Shuai Sun and Joseph Crandall and Yousra Alkabani and Vikram Narayana and Volker Sorger and Tarek El-Ghazawi", title = "{ROC}: a Reconfigurable Optical Computer for Simulating Physical Processes", journal = j-TOPC, volume = "7", number = "1", pages = "8:1--8:29", month = apr, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3380944", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Apr 6 08:56:55 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3380944", abstract = "Due to the end of Moore's law and Dennard scaling, we are entering a new era of processors. Computing systems are increasingly facing power and performance challenges due to both device- and circuit-related challenges with resistive and capacitive \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Monemi:2020:EDW, author = "Alireza Monemi and Farshad Khunjush and Maurizio Palesi and Hamid Sarbazi-Azad", title = "An Enhanced Dynamic Weighted Incremental Technique for {QoS} Support in {NoC}", journal = j-TOPC, volume = "7", number = "2", pages = "9:1--9:31", month = may, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3391442", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Jun 1 09:19:25 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3391442", abstract = "Providing Quality-of-Service (QoS) in many-core network-on-chip (NoC) platforms is critical due to the high level of resource sharing in such systems. This article presents a hard-built Equality-of-Service (EoS) and Differential-Service (DS) as subsets \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Natarajan:2020:FLL, author = "Aravind Natarajan and Arunmoezhi Ramachandran and Neeraj Mittal", title = "{FEAST}: a Lightweight Lock-free Concurrent Binary Search Tree", journal = j-TOPC, volume = "7", number = "2", pages = "10:1--10:64", month = may, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3391438", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Jun 1 09:19:25 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3391438", abstract = "We present a lock-free algorithm for concurrent manipulation of a binary search tree (BST) in an asynchronous shared memory system that supports search, insert, and delete operations. In addition to read and write instructions, our algorithm uses \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Salah:2020:TSE, author = "Ahmad Salah and Kenli Li and Qing Liao and Mervat Hashem and Zhiyong Li and Anthony T. Chronopoulos and Albert Y. Zomaya", title = "A Time-space Efficient Algorithm for Parallel $k$-way In-place Merging based on Sequence Partitioning and Perfect Shuffle", journal = j-TOPC, volume = "7", number = "2", pages = "11:1--11:23", month = may, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3391443", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Jun 1 09:19:25 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3391443", abstract = "The huge data volumes, big data, and the emergence of new parallel architectures lead to revisiting classic computer science topics. The motivation of the proposed work for revisiting the parallel k -way in-place merging is primarily related to the \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Duan:2020:CSR, author = "Shaohua Duan and Pradeep Subedi and Philip Davis and Keita Teranishi and Hemanth Kolla and Marc Gamell and Manish Parashar", title = "{CoREC}: Scalable and Resilient In-memory Data Staging for In-situ Workflows", journal = j-TOPC, volume = "7", number = "2", pages = "12:1--12:29", month = may, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3391448", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Jun 1 09:19:25 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3391448", abstract = "The dramatic increase in the scale of current and planned high-end HPC systems is leading new challenges, such as the growing costs of data movement and IO, and the reduced mean time between failures (MTBF) of system components. In-situ workflows, i.e., \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alam:2020:GMS, author = "Maksudul Alam and Maleq Khan and Kalyan S. Perumalla and Madhav Marathe", title = "Generating Massive Scale-free Networks: Novel Parallel Algorithms using the Preferential Attachment Model", journal = j-TOPC, volume = "7", number = "2", pages = "13:1--13:35", month = may, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3391446", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Jun 1 09:19:25 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3391446", abstract = "Recently, there has been substantial interest in the study of various random networks as mathematical models of complex systems. As real-life complex systems grow larger, the ability to generate progressively large random networks becomes all the more \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lee:2020:ISI, author = "Jaejin Lee and Lawrence Rauchwerger and Armando Solar-Lezama and Guy Steele", title = "Introduction to the Special Issue on {PPoPP 2017} (Part 2)", journal = j-TOPC, volume = "7", number = "3", pages = "14:1--14:2", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3407185", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3407185", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jiang:2020:CSM, author = "Peng Jiang and Yang Xia and Gagan Agrawal", title = "Combining {SIMD} and Many\slash Multi-core Parallelism for Finite-state Machines with Enumerative Speculation", journal = j-TOPC, volume = "7", number = "3", pages = "15:1--15:26", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399714", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399714", abstract = "Finite-state Machine (FSM) is the key kernel behind many popular applications, including regular expression matching, text tokenization, and Huffman decoding. Parallelizing FSMs is extremely difficult because of the strong dependencies and unpredictable \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Basin:2020:KKV, author = "Dmitry Basin and Edward Bortnikov and Anastasia Braginsky and Guy Golan-Gueta and Eshcar Hillel and Idit Keidar and Moshe Sulamy", title = "{KiWi}: a Key--value Map for Scalable Real-time Analytics", journal = j-TOPC, volume = "7", number = "3", pages = "16:1--16:28", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399718", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/java2020.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399718", abstract = "We present KiWi, the first atomic KV-map to efficiently support simultaneous large scans and real-time access. The key to achieving this is treating scans as first class citizens and organizing the data structure around them. KiWi provides wait-free scans, whereas its put operations are lightweight and lock-free. It optimizes memory management jointly with data structure access. We implement KiWi and compare it to state-of-the-art solutions. Compared to other KV-maps providing atomic scans, KiWi performs either long scans or concurrent puts an order of magnitude faster. Its scans are twice as fast as non-atomic ones implemented via iterators in the Java skiplist.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chabbi:2020:EAL, author = "Milind Chabbi and Abdelhalim Amer and Xu Liu", title = "Efficient Abortable-locking Protocol for Multi-level {NUMA} Systems: Design and Correctness", journal = j-TOPC, volume = "7", number = "3", pages = "17:1--17:32", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399728", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399728", abstract = "The popularity of Non-Uniform Memory Access (NUMA) architectures has led to numerous locality-preserving hierarchical lock designs, such as HCLH, HMCS, and cohort locks. Locality-preserving locks trade fairness for higher throughput. Hence, some \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ben-Nun:2020:GAM, author = "Tal Ben-Nun and Michael Sutton and Sreepathi Pai and Keshav Pingali", title = "{Groute}: Asynchronous Multi-{GPU} Programming Model with Applications to Large-scale Graph Processing", journal = j-TOPC, volume = "7", number = "3", pages = "18:1--18:27", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399730", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399730", abstract = "Nodes with multiple GPUs are becoming the platform of choice for high-performance computing. However, most applications are written using bulk-synchronous programming models, which may not be optimal for irregular algorithms that benefit from low-. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alappat:2020:RAC, author = "Christie Alappat and Achim Basermann and Alan R. Bishop and Holger Fehske and Georg Hager and Olaf Schenk and Jonas Thies and Gerhard Wellein", title = "A Recursive Algebraic Coloring Technique for Hardware-efficient Symmetric Sparse Matrix--vector Multiplication", journal = j-TOPC, volume = "7", number = "3", pages = "19:1--19:37", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399732", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399732", abstract = "The symmetric sparse matrix-vector multiplication (SymmSpMV) is an important building block for many numerical linear algebra kernel operations or graph traversal applications. Parallelizing SymmSpMV on today's multicore platforms with up to 100 cores is difficult due to the need to manage conflicting updates on the result vector. Coloring approaches can be used to solve this problem without data duplication, but existing coloring algorithms do not take load balancing and deep memory hierarchies into account, hampering scalability and full-chip performance. In this work, we propose the recursive algebraic coloring engine (RACE), a novel coloring algorithm and open-source library implementation that eliminates the shortcomings of previous coloring methods in terms of hardware efficiency and parallelization overhead. We describe the level construction, distance-$k$ coloring, and load balancing steps in RACE, use it to parallelize SymmSpMV, and compare its performance on 31 sparse matrices with other state-of-the-art coloring techniques and Intel MKL on two modern multicore processors. RACE outperforms all other approaches substantially. By means of a parameterized roofline model, we analyze the SymmSpMV performance in detail and discuss outliers. While we focus on SymmSpMV in this article, our algorithm and software are applicable to any sparse matrix operation with data dependencies that can be resolved by distance-$k$ coloring.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Davydov:2020:ADS, author = "Denis Davydov and Martin Kronbichler", title = "Algorithms and Data Structures for Matrix-Free Finite Element Operators with {MPI}-Parallel Sparse Multi-Vectors", journal = j-TOPC, volume = "7", number = "3", pages = "20:1--20:30", month = aug, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3399736", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Aug 6 08:56:07 MDT 2020", bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/abs/10.1145/3399736", abstract = "Traditional solution approaches for problems in quantum mechanics scale as $ O(M^3) $, where $M$ is the number of electrons. Various methods have been proposed to address this issue and obtain a linear scaling $ O(M)$. One promising formulation is the direct minimization of energy. Such methods take advantage of physical localization of the solution, allowing users to seek it in terms of non-orthogonal orbitals with local support.\par This work proposes a numerically efficient implementation of sparse parallel vectors within the open-source finite element library deal.II. The main algorithmic ingredient is the matrix-free evaluation of the Hamiltonian operator by cell-wise quadrature. Based on an a-priori chosen support for each vector, we develop algorithms and data structures to perform (i) matrix-free sparse matrix multivector products (SpMM), (ii) the projection of an operator onto a sparse sub-space (inner products), and (iii) post-multiplication of a sparse multivector with a square matrix. The node-level performance is analyzed using a roofline model. Our matrix-free implementation of finite element operators with sparse multivectors achieves a performance of 157 GFlop/s on an Intel Cascade Lake processor with 20 cores. Strong and weak scaling results are reported for a representative benchmark problem using quadratic and quartic finite element bases.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sengupta:2020:HAP, author = "Tapan K. Sengupta and Prasannabalaji Sundaram and Vajjala K. Suman and Swagata Bhaumik", title = "A High Accuracy Preserving Parallel Algorithm for Compact Schemes for {DNS}", journal = j-TOPC, volume = "7", number = "4", pages = "21:1--21:32", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418073", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418073", abstract = "A new accuracy-preserving parallel algorithm employing compact schemes is presented for direct numerical simulation of the Navier--Stokes equations. Here the connotation of accuracy preservation is having the same level of accuracy obtained by the \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Aggarwal:2020:OLF, author = "Karan Aggarwal and Uday Bondhugula", title = "Optimizing the Linear Fascicle Evaluation Algorithm for Multi-core and Many-core Systems", journal = j-TOPC, volume = "7", number = "4", pages = "22:1--22:45", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418075", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418075", abstract = "Sparse matrix-vector multiplication ( SpMV ) operations are commonly used in various scientific and engineering applications. The performance of the SpMV operation often depends on exploiting regularity patterns in the matrix. Various representations and \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Tumeo:2020:ITSb, author = "Antonino Tumeo and Fabrizio Petrini and John Feo and Mahantesh Halappanavar", title = "Introduction to the {TOPC} Special Issue on Innovations in Systems for Irregular Applications, {Part 2}", journal = j-TOPC, volume = "7", number = "4", pages = "23:1--23:2", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3419771", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3419771", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "23", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Namashivayam:2020:MFI, author = "Naveen Namashivayam and Bill Long and Deepak Eachempati and Bob Cernohous and Mark Pagel", title = "A Modern {Fortran} Interface in {OpenSHMEM} Need for Interoperability with {Parallel Fortran} Using Coarrays", journal = j-TOPC, volume = "7", number = "4", pages = "24:1--24:25", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418084", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/fortran3.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418084", abstract = "Languages and libraries based on Partitioned Global Address Space (PGAS) programming models are convenient for exploiting scalable parallelism on large applications across different domains with irregular memory access patterns. OpenSHMEM is a PGAS-. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "24", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hein:2020:PSI, author = "Eric R. Hein and Srinivas Eswar and Abdurrahman Yasar and Jiajia Li and Jeffrey S. Young and Thomas M. Conte and {\"U}mit V. {\c{C}}ataly{\"u}rek and Richard Vuduc and Jason Riedy and Bora U{\c{c}}ar", title = "Programming Strategies for Irregular Algorithms on the {Emu Chick}", journal = j-TOPC, volume = "7", number = "4", pages = "25:1--25:25", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418077", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418077", abstract = "The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory cores before \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "25", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Leidel:2020:TME, author = "John D. Leidel and Xi Wang and Brody Williams and Yong Chen", title = "Toward a Microarchitecture for Efficient Execution of Irregular Applications", journal = j-TOPC, volume = "7", number = "4", pages = "26:1--26:24", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418082", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418082", abstract = "Given the increasing importance of efficient data-intensive computing, we find that modern processor designs are not well suited to the irregular memory access patterns often found in these algorithms. Applications and algorithms that do not exhibit \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "26", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Fezzardi:2020:ABD, author = "Pietro Fezzardi and Fabrizio Ferrandi", title = "Automated Bug Detection for High-level Synthesis of Multi-threaded Irregular Applications", journal = j-TOPC, volume = "7", number = "4", pages = "27:1--27:26", month = dec, year = "2020", CODEN = "????", DOI = "https://doi.org/10.1145/3418086", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sun Mar 28 08:05:40 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3418086", abstract = "Field Programmable Gate Arrays (FPGAs) are becoming an appealing technology in datacenters and High Performance Computing. High-Level Synthesis (HLS) of multi-threaded parallel programs is increasingly used to extract parallelism. Despite great leaps \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "27", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Savoie:2021:MIJ, author = "Lee Savoie and David K. Lowenthal and Bronis R. {De Supinski} and Kathryn Mohror and Nikhil Jain", title = "Mitigating Inter-Job Interference via Process-Level Quality-of-Service", journal = j-TOPC, volume = "8", number = "1", pages = "1:1--1:26", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3434397", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3434397", abstract = "Jobs on most high-performance computing (HPC) systems share the network with other concurrently executing jobs. Network sharing leads to contention that can severely degrade performance. This article investigates the use of Quality of Service (QoS) \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Reza:2021:SPM, author = "Tahsin Reza and Hassan Halawa and Matei Ripeanu and Geoffrey Sanders and Roger A. Pearce", title = "Scalable Pattern Matching in Metadata Graphs via Constraint Checking", journal = j-TOPC, volume = "8", number = "1", pages = "2:1--2:45", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3434391", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3434391", abstract = "Pattern matching is a fundamental tool for answering complex graph queries. Unfortunately, existing solutions have limited capabilities: They do not scale to process large graphs and/or support only a restricted set of search templates or usage \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Fineman:2021:ISIa, author = "Jeremy Fineman and Aydin Buluc and Seth Gilbert", title = "Introduction to the Special Issue for {SPAA 2018}: {Part 1}", journal = j-TOPC, volume = "8", number = "1", pages = "3e:1--3e:1", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3456774", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3456774", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3e", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alon:2021:PBP, author = "Noga Alon and Yossi Azar and Mark Berlin", title = "The Price of Bounded Preemption", journal = j-TOPC, volume = "8", number = "1", pages = "3:1--3:21", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3434377", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3434377", abstract = "In this article we provide a tight bound for the price of preemption for scheduling jobs on a single machine (or multiple machines). The input consists of a set of jobs to be scheduled and of an integer parameter k {$>$}= 1. Each job has a release time, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Dhulipala:2021:TEP, author = "Laxman Dhulipala and Guy E. Blelloch and Julian Shun", title = "Theoretically Efficient Parallel Graph Algorithms Can Be Fast and Scalable", journal = j-TOPC, volume = "8", number = "1", pages = "4:1--4:70", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3434393", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3434393", abstract = "There has been significant recent interest in parallel graph processing due to the need to quickly analyze the large graphs available today. Many graph codes have been designed for distributed memory or external memory. However, today even the largest \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kaplan:2021:DRS, author = "Haim Kaplan and Shay Solomon", title = "Dynamic Representations of Sparse Distributed Networks: a Locality-sensitive Approach", journal = j-TOPC, volume = "8", number = "1", pages = "5:1--5:26", month = apr, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3434395", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Apr 23 17:58:56 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3434395", abstract = "In 1999, Brodal and Fagerberg (BF) gave an algorithm for maintaining a low outdegree orientation of a dynamic uniformly sparse graph. Specifically, for a dynamic graph on $n$-vertices, with arboricity bounded by $ \alpha $ at all times, the BF algorithm supports \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Fineman:2021:ISIb, author = "Jeremy Fineman and Aydin Buluc and Seth Gilbert", title = "Introduction to the Special Issue for {SPAA 2018} --- {Part 2}", journal = j-TOPC, volume = "8", number = "2", pages = "6:1--6:1", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3463366", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3463366", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pandurangan:2021:DCL, author = "Gopal Pandurangan and Peter Robinson and Michele Scquizzato", title = "On the Distributed Complexity of Large-Scale Graph Computations", journal = j-TOPC, volume = "8", number = "2", pages = "7:1--7:28", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3460900", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3460900", abstract = "Motivated by the increasing need to understand the distributed algorithmic foundations of large-scale graph computations, we study some fundamental graph problems in a message-passing model for distributed computing where $ k \geq 2 $ machines jointly perform \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Geissmann:2021:PMC, author = "Barbara Geissmann and Lukas Gianinazzi", title = "Parallel Minimum Cuts in Near-linear Work and Low Depth", journal = j-TOPC, volume = "8", number = "2", pages = "8:1--8:20", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3460890", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3460890", abstract = "We present the first near-linear work and poly-logarithmic depth algorithm for computing a minimum cut in an undirected graph. Previous parallel algorithms with poly-logarithmic depth required at least quadratic work in the number of vertices. In a \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lucarelli:2021:ONP, author = "Giorgio Lucarelli and Benjamin Moseley and Nguyen Kim Thang and Abhinav Srivastav and Denis Trystram", title = "Online Non-preemptive Scheduling on Unrelated Machines with Rejections", journal = j-TOPC, volume = "8", number = "2", pages = "9:1--9:22", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3460880", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3460880", abstract = "When a computer system schedules jobs there is typically a significant cost associated with preempting a job during execution. This cost can be incurred from the expensive task of saving the memory's state or from loading data into and out of memory. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Winblad:2021:LFC, author = "Kjell Winblad and Konstantinos Sagonas and Bengt Jonsson", title = "Lock-free Contention Adapting Search Trees", journal = j-TOPC, volume = "8", number = "2", pages = "10:1--10:38", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3460874", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3460874", abstract = "Concurrent key-value stores with range query support are crucial for the scalability and performance of many applications. Existing lock-free data structures of this kind use a fixed synchronization granularity. Using a fixed synchronization granularity \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Green:2021:HSH, author = "Oded Green", title = "{HashGraph} --- Scalable Hash Tables Using a Sparse Graph Data Structure", journal = j-TOPC, volume = "8", number = "2", pages = "11:1--11:17", month = jun, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3460872", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Aug 24 07:42:49 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3460872", abstract = "In this article, we introduce HashGraph, a new scalable approach for building hash tables that uses concepts taken from sparse graph representations --- hence, the name HashGraph. HashGraph introduces a new way to deal with hash-collisions that does not use ``open-addressing'' or ``separate-chaining,'' yet it has the benefits of both these approaches. HashGraph currently works for static inputs. Recent progress with dynamic graph data structures suggests that HashGraph might be extendable to dynamic inputs as well. We show that HashGraph can deal with a large number of hash values per entry without loss of performance. Last, we show a new querying algorithm for value lookups. We experimentally compare HashGraph to several state-of-the-art implementations and find that it outperforms them on average $ 2 \times $ when the inputs are unique and by as much as $ 40 \times $ when the input contains duplicates. The implementation of HashGraph in this article is for NVIDIA GPUs. HashGraph can build a hash table at a rate of 2.5 billion keys per second on a NVIDIA GV100 GPU and can query at nearly the same rate.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Berenbrink:2021:ISI, author = "Petra Berenbrink", title = "Introduction to the Special Issue for {SPAA 2019}", journal = j-TOPC, volume = "8", number = "3", pages = "12:1--12:1", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3477610", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3477610", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Behnezhad:2021:MPC, author = "Soheil Behnezhad and Laxman Dhulipala and Hossein Esfandiari and Jakub Lacki and Vahab Mirrokni and Warren Schudy", title = "Massively Parallel Computation via Remote Memory Access", journal = j-TOPC, volume = "8", number = "3", pages = "13:1--13:25", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470631", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470631", abstract = "We introduce the Adaptive Massively Parallel Computation (AMPC) model, which is an extension of the Massively Parallel Computation (MPC) model. At a high level, the AMPC model strengthens the MPC model by storing all messages sent within a round in a \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ellen:2021:CLL, author = "Faith Ellen and Barun Gorain and Avery Miller and Andrzej Pelc", title = "Constant-Length Labeling Schemes for Deterministic Radio Broadcast", journal = j-TOPC, volume = "8", number = "3", pages = "14:1--14:17", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470633", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470633", abstract = "Broadcast is one of the fundamental network communication primitives. One node of a network, called the source, has a message that has to be learned by all other nodes. We consider broadcast in radio networks, modeled as simple undirected connected graphs \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bender:2021:EMD, author = "Michael A. Bender and Alex Conway and Mart{\'\i}n Farach-Colton and William Jannen and Yizheng Jiao and Rob Johnson and Eric Knorr and Sara Mcallister and Nirjhar Mukherjee and Prashant Pandey and Donald E. Porter and Jun Yuan and Yang Zhan", title = "External-memory Dictionaries in the Affine and {PDAM} Models", journal = j-TOPC, volume = "8", number = "3", pages = "15:1--15:20", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470635", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470635", abstract = "Storage devices have complex performance profiles, including costs to initiate IOs (e.g., seek times in hard drives), parallelism and bank conflicts (in SSDs), costs to transfer data, and firmware-internal operations. The Disk-access Machine (DAM) model \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Maier:2021:EPC, author = "Matthias Maier and Martin Kronbichler", title = "Efficient Parallel {$3$D} Computation of the Compressible {Euler} Equations with an Invariant-domain Preserving Second-order Finite-element Scheme", journal = j-TOPC, volume = "8", number = "3", pages = "16:1--16:30", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470637", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470637", abstract = "We discuss the efficient implementation of a high-performance second-order collocation-type finite-element scheme for solving the compressible Euler equations of gas dynamics on unstructured meshes. The solver is based on the convex-limiting technique \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Edwards:2021:SFG, author = "James Edwards and Uzi Vishkin", title = "Study of Fine-grained Nested Parallelism in {CDCL SAT} Solvers", journal = j-TOPC, volume = "8", number = "3", pages = "17:1--17:18", month = sep, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470639", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 21 07:18:25 MDT 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470639", abstract = "Boolean satisfiability (SAT) is an important performance-hungry problem with applications in many problem domains. However, most work on parallelizing SAT solvers has focused on coarse-grained, mostly embarrassing, parallelism. Here, we study fine-grained \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Feuilloley:2021:RLN, author = "Laurent Feuilloley and Pierre Fraigniaud", title = "Randomized Local Network Computing: Derandomization Beyond Locally Checkable Labelings", journal = j-TOPC, volume = "8", number = "4", pages = "18:1--18:25", month = dec, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470640", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 10 10:52:35 MST 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470640", abstract = "We carry on investigating the line of research questioning the power of randomization for the design of distributed algorithms. In their seminal paper, Naor and Stockmeyer [STOC 1993] established that, in the context of network computing in which all \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Monfared:2021:HTP, author = "Saleh Khalaj Monfared and Omid Hajihassani and Vahid Mohsseni and Dara Rahmati and Saeid Gorgin", title = "A High-throughput Parallel {Viterbi} Algorithm via Bitslicing", journal = j-TOPC, volume = "8", number = "4", pages = "19:1--19:25", month = dec, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470642", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 10 10:52:35 MST 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470642", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Wang:2021:PBD, author = "Shao-Chung Wang and Lin-Ya Yu and Li-An Her and Yuan-Shin Hwang and Jenq-Kuen Lee", title = "Pointer-Based Divergence Analysis for {OpenCL 2.0} Programs", journal = j-TOPC, volume = "8", number = "4", pages = "20:1--20:23", month = dec, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3470644", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 10 10:52:35 MST 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3470644", abstract = "A modern GPU is designed with many large thread groups to achieve a high throughput and performance. Within these groups, the threads are grouped into fixed-size SIMD batches in which the same instruction is applied to vectors of data in a lockstep. This \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kang:2021:AEC, author = "Xuejiao Kang and David F. Gleich and Ahmed Sameh and Ananth Grama", title = "Adaptive Erasure Coded Fault Tolerant Linear System Solver", journal = j-TOPC, volume = "8", number = "4", pages = "21:1--21:19", month = dec, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3490557", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 10 10:52:35 MST 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3490557", abstract = "As parallel and distributed systems scale, fault tolerance is an increasingly important problem-particularly on systems with limited I/O capacity and bandwidth. Erasure coded computations address this problem by augmenting a given problem instance with \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Jayanti:2021:DCA, author = "Prasad Jayanti and Siddhartha Jayanti", title = "Deterministic Constant-Amortized-{RMR} Abortable Mutex for {CC} and {DSM}", journal = j-TOPC, volume = "8", number = "4", pages = "22:1--22:26", month = dec, year = "2021", CODEN = "????", DOI = "https://doi.org/10.1145/3490559", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Dec 10 10:52:35 MST 2021", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3490559", abstract = "The abortable mutual exclusion problem, proposed by Scott and Scherer in response to the needs in real-time systems and databases, is a variant of mutual exclusion that allows processes to abort from their attempt to acquire the lock. Worst-case constant \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Leinhauser:2022:MDI, author = "Matthew Leinhauser and Ren{\'e} Widera and Sergei Bastrakov and Alexander Debus and Michael Bussmann and Sunita Chandrasekaran", title = "Metrics and Design of an Instruction Roofline Model for {AMD GPUs}", journal = j-TOPC, volume = "9", number = "1", pages = "1:1--1:14", month = mar, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3505285", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Mar 24 08:01:07 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3505285", abstract = "Due to the recent announcement of the Frontier supercomputer, many scientific application developers are working to make their applications compatible with AMD (CPU-GPU) architectures, which means moving away from the traditional CPU and NVIDIA-GPU \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Axtmann:2022:EPS, author = "Michael Axtmann and Sascha Witt and Daniel Ferizovic and Peter Sanders", title = "Engineering In-place (Shared-memory) Sorting Algorithms", journal = j-TOPC, volume = "9", number = "1", pages = "2:1--2:62", month = mar, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3505286", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Mar 24 08:01:07 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3505286", abstract = "We present new sequential and parallel sorting algorithms that now represent the fastest known techniques for a wide range of input sizes, input distributions, data types, and machines. Somewhat surprisingly, part of the speed advantage is due to the \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Mitchell:2022:BOR, author = "Rory Mitchell and Daniel Stokes and Eibe Frank and Geoffrey Holmes", title = "Bandwidth-Optimal Random Shuffling for {GPUs}", journal = j-TOPC, volume = "9", number = "1", pages = "3:1--3:20", month = mar, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3505287", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Mar 24 08:01:07 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3505287", abstract = "Linear-time algorithms that are traditionally used to shuffle data on CPUs, such as the method of Fisher-Yates, are not well suited to implementation on GPUs due to inherent sequential dependencies, and existing parallel shuffling algorithms are \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alomairy:2022:HPU, author = "Rabab Alomairy and Wael Bader and Hatem Ltaief and Youssef Mesri and David Keyes", title = "High-performance {$3$D} Unstructured Mesh Deformation Using Rank Structured Matrix Computations", journal = j-TOPC, volume = "9", number = "1", pages = "4:1--4:23", month = mar, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3512756", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Mar 24 08:01:07 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3512756", abstract = "The Radial Basis Function (RBF) technique is an interpolation method that produces high-quality unstructured adaptive meshes. However, the RBF-based boundary problem necessitates solving a large dense linear system with cubic arithmetic complexity that is \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Milman-Sela:2022:BLF, author = "Gal Milman-Sela and Alex Kogan and Yossi Lev and Victor Luchangco and Erez Petrank", title = "{BQ}: a Lock-Free Queue with Batching", journal = j-TOPC, volume = "9", number = "1", pages = "5:1--5:49", month = mar, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3512757", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Mar 24 08:01:07 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3512757", abstract = "Concurrent data structures provide fundamental building blocks for concurrent programming. Standard concurrent data structures may be extended by allowing a sequence of operations to be submitted as a batch for later execution. A sequence of such \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Rinberg:2022:FCD, author = "Arik Rinberg and Alexander Spiegelman and Edward Bortnikov and Eshcar Hillel and Idit Keidar and Lee Rhodes and Hadar Serviansky", title = "Fast Concurrent Data Sketches", journal = j-TOPC, volume = "9", number = "2", pages = "6:1--6:35", month = jun, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3512758", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 2 10:15:52 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3512758", abstract = "Data sketches are approximate succinct summaries of long data streams. They are widely used for processing massive amounts of data and answering statistical queries about it. Existing libraries producing sketches are very fast, but do not allow \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Blelloch:2022:JPB, author = "Guy Blelloch and Daniel Ferizovic and Yihan Sun", title = "Joinable Parallel Balanced Binary Trees", journal = j-TOPC, volume = "9", number = "2", pages = "7:1--7:41", month = jun, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3512769", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 2 10:15:52 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3512769", abstract = "In this article, we show how a single function, join, can be used to implement parallel balanced binary search trees (BSTs) simply and efficiently. Based on join, our approach applies to multiple balanced tree data structures, and a variety of functions \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chen:2022:FFG, author = "Yuedan Chen and Guoqing Xiao and Kenli Li and Francesco Piccialli and Albert Y. Zomaya", title = "{fgSpMSpV}: a Fine-grained Parallel {SpMSpV} Framework on {HPC} Platforms", journal = j-TOPC, volume = "9", number = "2", pages = "8:1--8:29", month = jun, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3512770", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 2 10:15:52 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3512770", abstract = "Sparse matrix--sparse vector (SpMSpV) multiplication is one of the fundamental and important operations in many high-performance scientific and engineering applications. The inherent irregularity and poor data locality lead to two main challenges to to scaling SpMSpV over high-performance computing (HPC) systems: (i) a large amount of redundant data limits the utilization of bandwidth and parallel resources; (ii) the irregular access pattern limits the exploitation of computing resources. This paper proposes a fine-grained parallel SpMSpV (fgSpMSpV) framework on Sunway TaihuLight supercomputer to alleviate the challenges for large-scale real-world applications. First, fgSpMSpV adopts an MPI+OpenMP+X parallelization model to exploit the multi-stage and hybrid parallelism of heterogeneous HPC architectures and accelerate both pre-/post-processing and main SpMSpV computation. Second, fgSpMSpV utilizes an adaptive parallel execution to reduce the pre-processing, adapt to the parallelism and memory hierarchy of the Sunway system, while still tame redundant and random memory accesses in SpMSpV, including a set of techniques like the fine-grained partitioner, re-collection method, and Compressed Sparse Column Vector (CSCV) matrix format. Third, fgSpMSpV uses several optimization techniques to further utilize the computing resources. fgSpMSpV on the Sunway TaihuLight gains a noticeable performance improvement from the key optimization techniques with various sparsity of the input. Additionally, fgSpMSpV is implemented on an NVIDIA Tesal P100 GPU and applied to the breath-first-search (BFS) application. fgSpMSpV on a P100 GPU obtains the speedup of up to 134.38 $ \times $ over the state-of-the-art SpMSpV algorithms, and the BFS application using fgSpMSpV achieves the speedup of up to 21.68 $ \times $ over the state-of-the-arts.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Liu:2022:SCC, author = "Sixue Cliff Liu and Robert Endre Tarjan", title = "Simple Concurrent Connected Components Algorithms", journal = j-TOPC, volume = "9", number = "2", pages = "9:1--9:26", month = jun, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3543546", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 2 10:15:52 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3543546", abstract = "We study a class of simple algorithms for concurrently computing the connected components of an n-vertex, m-edge graph. Our algorithms are easy to implement in either the COMBINING CRCW PRAM or the MPC computing model. For two related algorithms in this \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alabandi:2022:ISQ, author = "Ghadeer Alabandi and Martin Burtscher", title = "Improving the Speed and Quality of Parallel Graph Coloring", journal = j-TOPC, volume = "9", number = "3", pages = "10:1--10:35", month = sep, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3543545", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 20 09:34:53 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3543545", abstract = "Graph coloring assigns a color to each vertex of a graph such that no two adjacent vertices get the same color. It is a key building block in many applications. In practice, solutions that require fewer distinct colors and that can be computed faster are \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Nguyen:2022:DIC, author = "Hung K. Nguyen and Xuan-Tu Tran", title = "Design and Implementation of a Coarse-grained Dynamically Reconfigurable Multimedia Accelerator", journal = j-TOPC, volume = "9", number = "3", pages = "11:1--11:23", month = sep, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3543544", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 20 09:34:53 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3543544", abstract = "This article proposes and implements a Coarse-grained dynamically Reconfigurable Architecture, named Reconfigurable Multimedia Accelerator (REMAC). REMAC architecture is driven by the pipelined multi-instruction-multi-data execution model for exploiting \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Anju:2022:MID, author = "M. A. Anju and Rupesh Nasre", title = "Multi-Interval {DomLock}: Toward Improving Concurrency in Hierarchies", journal = j-TOPC, volume = "9", number = "3", pages = "12:1--12:27", month = sep, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3543543", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 20 09:34:53 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3543543", abstract = "Locking has been a predominant technique depended upon for achieving thread synchronization and ensuring correctness in multi-threaded applications. It has been established that the concurrent applications working with hierarchical data witness \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ji:2022:IPI, author = "Yuede Ji and Hang Liu and Yang Hu and H. Howie Huang", title = "{iSpan}: Parallel Identification of Strongly Connected Components with Spanning Trees", journal = j-TOPC, volume = "9", number = "3", pages = "13:1--13:27", month = sep, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3543542", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Tue Sep 20 09:34:53 MDT 2022", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3543542", abstract = "Detecting strongly connected components (SCCs) in a directed graph is crucial for understanding the structure of graphs. Most real-world graphs have one large SCC that contains the majority of the vertices as well as many small SCCs whose sizes are \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Benoit:2022:CWY, author = "Anne Benoit and Luca Perotin and Yves Robert and Hongyang Sun", title = "Checkpointing Workflows {\`a} la {Young\slash Daly} Is Not Good Enough", journal = j-TOPC, volume = "9", number = "4", pages = "14:1--14:??", month = dec, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3548607", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:10 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3548607", abstract = "This article revisits checkpointing strategies when workflows composed of multiple tasks execute on a parallel platform. The objective is to minimize the expectation of the total execution time. For a single task, the Young\slash Daly formula provides the \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Albers:2022:OAR, author = "Susanne Albers and Jens Quedenfeld", title = "Optimal Algorithms for Right-sizing Data Centers", journal = j-TOPC, volume = "9", number = "4", pages = "15:1--15:??", month = dec, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3565513", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:10 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3565513", abstract = "Electricity cost is a dominant and rapidly growing expense in data centers. Unfortunately, much of the consumed energy is wasted, because servers are idle for extended periods of time. We study a capacity management problem that dynamically right-sizes a \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kappes:2022:FRC, author = "Giorgos Kappes and Stergios V. Anastasiadis", title = "A Family of Relaxed Concurrent Queues for Low-Latency Operations and Item Transfers", journal = j-TOPC, volume = "9", number = "4", pages = "16:1--16:??", month = dec, year = "2022", CODEN = "????", DOI = "https://doi.org/10.1145/3565514", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:10 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3565514", abstract = "The producer-consumer communication over shared memory is a critical function of current scalable systems. Queues that provide low latency and high throughput on highly utilized systems can improve the overall performance perceived by the end users. In \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Sundaram:2023:NOH, author = "Prasannabalaji Sundaram and Aditi Sengupta and Vajjala K. Suman and Tapan K. Sengupta", title = "Non-overlapping High-accuracy Parallel Closure for Compact Schemes: Application in Multiphysics and Complex Geometry", journal = j-TOPC, volume = "10", number = "1", pages = "1:1--1:??", month = mar, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580005", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:11 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580005", abstract = "Compact schemes are often preferred in performing scientific computing for their superior spectral resolution. Error-free parallelization of a compact scheme is a challenging task due to the requirement of additional closures at the inter-processor \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lockhart:2023:PAO, author = "Shelby Lockhart and Amanda Bienz and William Gropp and Luke Olson", title = "Performance Analysis and Optimal Node-aware Communication for Enlarged Conjugate Gradient Methods", journal = j-TOPC, volume = "10", number = "1", pages = "2:1--2:??", month = mar, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580003", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:11 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580003", abstract = "Krylov methods are a key way of solving large sparse linear systems of equations but suffer from poor strong scalability on distributed memory machines. This is due to high synchronization costs from large numbers of collective communication calls \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Munch:2023:EDM, author = "Peter Munch and Timo Heister and Laura Prieto Saavedra and Martin Kronbichler", title = "Efficient Distributed Matrix-free Multigrid Methods on Locally Refined Meshes for {FEM} Computations", journal = j-TOPC, volume = "10", number = "1", pages = "3:1--3:??", month = mar, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580314", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:11 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580314", abstract = "This work studies three multigrid variants for matrix-free finite-element computations on locally refined meshes: geometric local smoothing, geometric global coarsening (both h -multigrid), and polynomial global coarsening (a variant of p -multigrid). We \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Klein:2023:TGL, author = "Christoph Klein and Robert Strzodka", title = "{Tridigpu}: a {GPU} Library for Block Tridiagonal and Banded Linear Equation Systems", journal = j-TOPC, volume = "10", number = "1", pages = "4:1--4:??", month = mar, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580373", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Apr 5 10:44:11 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib; https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580373", abstract = "In this article, we present a CUDA library with a C API for solving block cyclic tridiagonal and banded systems on one GPU. The library can process block tridiagonal systems with block sizes from $ 1 \times 1 $ (scalar) to $ 4 \times 4 $ and banded systems with up to four sub- and superdiagonals. For the compute-intensive block size cases and cases with many right-hand sides, we write out an explicit factorization to memory; however, for the scalar case, the fastest approach is to only output the coarse system and recompute the factorization. Prominent features of the library are (scaled) partial pivoting for improved numeric stability; highest-performance kernels, which completely utilize GPU memory bandwidth; and support for multiple sparse or dense right-hand side and solution vectors. The additional memory consumption is only 5\% of the original tridiagonal system, which enables the solution of systems up to GPU memory size. The performance of the state-of-the-art scalar tridiagonal solver of cuSPARSE is outperformed by factor 5 for large problem sizes of $ 2^{25} $ unknowns, on a GeForce RTX 2080 Ti.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lakhotia:2023:PPB, author = "Kartik Lakhotia and Rajgopal Kannan and Viktor Prasanna", title = "Parallel Peeling of Bipartite Networks for Hierarchical Dense Subgraph Discovery", journal = j-TOPC, volume = "10", number = "2", pages = "5:1--5:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3583084", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3583084", abstract = "Wing and Tip decomposition are motif-based analytics for bipartite graphs that construct a hierarchy of butterfly (2,2-biclique) dense edge and vertex induced subgraphs, respectively. They have applications in several domains, including e-commerce, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Zheng:2023:DGD, author = "Weijian Zheng and Dali Wang and Fengguang Song", title = "A Distributed-{GPU} Deep Reinforcement Learning System for Solving Large Graph Optimization Problems", journal = j-TOPC, volume = "10", number = "2", pages = "6:1--6:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3589188", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3589188", abstract = "Graph optimization problems (such as minimum vertex cover, maximum cut, traveling salesman problems) appear in many fields including social sciences, power systems, chemistry, and bioinformatics. Recently, deep reinforcement learning (DRL) has shown \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Brown:2023:PED, author = "Andrew D. Brown and Jonathan R. Beaumont and David B. Thomas and Julian C. Shillcock and Matthew F. Naylor and Graeme M. Bragg and Mark L. Vousden and Simon W. Moore and Shane T. Fleming", title = "{POETS}: an Event-driven Approach to Dissipative Particle Dynamics: Implementing a Massively Compute-intensive Problem on a Novel Hard\slash Software Architecture.", journal = j-TOPC, volume = "10", number = "2", pages = "7:1--7:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580372", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580372", abstract = "HPC clusters have become ever more expensive, both in terms of capital cost and energy consumption; some estimates suggest that competitive installations at the end of the next decade will require their own power station. One way around this looming \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Aleeva:2023:IIP, author = "Valentina Aleeva and Rifkhat Aleev", title = "Investigation and Implementation of Parallelism Resources of Numerical Algorithms", journal = j-TOPC, volume = "10", number = "2", pages = "8:1--8:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3583755", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3583755", abstract = "This article is devoted to an approach to solving a problem of the efficiency of parallel computing. The theoretical basis of this approach is the concept of a Q -determinant. Any numerical algorithm has a Q -determinant. The Q -determinant of the algorithm \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Wang:2023:HPC, author = "Haotian Wang and Wangdong Yang and Renqiu Ouyang and Rong Hu and Kenli Li and Keqin Li", title = "A Heterogeneous Parallel Computing Approach Optimizing {SpTTM} on {CPU-GPU} via {GCN}", journal = j-TOPC, volume = "10", number = "2", pages = "9:1--9:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3584373", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3584373", abstract = "Sparse Tensor-Times-Matrix (SpTTM) is the core calculation in tensor analysis. The sparse distributions of different tensors vary greatly, which poses a big challenge to designing efficient and general SpTTM. In this paper, we describe SpTTM on CPU-GPU \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Miao:2023:PIT, author = "Zheng Miao and Jon C. Calhoun and Rong Ge and Jiajia Li", title = "Performance Implication of Tensor Irregularity and Optimization for Distributed Tensor Decomposition", journal = j-TOPC, volume = "10", number = "2", pages = "10:1--10:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3580315", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3580315", abstract = "Tensors are used by a wide variety of applications to represent multi-dimensional data; tensor decompositions are a class of methods for latent data analytics, data compression, and so on. Many of these applications generate large tensors with irregular \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hesselink:2023:MLS, author = "Wim H. Hesselink and Peter A. Buhr", title = "{MCSH}, a Lock with the Standard Interface", journal = j-TOPC, volume = "10", number = "2", pages = "11:1--11:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3584696", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3584696", abstract = "The MCS lock of Mellor-Crummey and Scott (1991), 23 pages. is a very efficient first-come first-served mutual-exclusion algorithm that uses the atomic hardware primitives fetch-and-store and compare-and-swap. However, it has the disadvantage that the \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Zamani:2023:GEE, author = "Hadi Zamani and Laxmi Bhuyan and Jieyang Chen and Zizhong Chen", title = "{GreenMD}: Energy-efficient Matrix Decomposition on Heterogeneous Multi-{GPU} Systems", journal = j-TOPC, volume = "10", number = "2", pages = "12:1--12:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3583590", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3583590", abstract = "The current trend of performance growth in HPC systems is accompanied by a massive increase in energy consumption. In this article, we introduce GreenMD, an energy-efficient framework for heterogeneous systems for LU factorization utilizing multi-GPUs. LU \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Kamenev:2023:FSA, author = "Aleksandar Kamenev and Dariusz R. Kowalski and Miguel A. Mosteiro", title = "Faster Supervised Average Consensus in Adversarial and Stochastic Anonymous Dynamic Networks", journal = j-TOPC, volume = "10", number = "2", pages = "13:1--13:??", month = jun, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3593426", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:36 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3593426", abstract = "How do we reach consensus on an average value in a dynamic crowd without revealing identity? In this work, we study the problem of average network consensus in Anonymous Dynamic Networks (ADN). Network dynamicity is specified by the sequence of topology-. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Baruah:2023:CCF, author = "Sanjoy Baruah and Alberto Marchetti-Spaccamela", title = "The Computational Complexity of Feasibility Analysis for Conditional {DAG} Tasks", journal = j-TOPC, volume = "10", number = "3", pages = "14:1--14:??", month = sep, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3606342", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:37 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3606342", abstract = "The Conditional DAG (CDAG) task model is used for modeling multiprocessor real-time systems containing conditional expressions for which outcomes are not known prior to their evaluation. Feasibility analysis for CDAG tasks upon multiprocessor platforms is \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Blanusa:2023:FPA, author = "Jovan Blanusa and Kubilay Atasu and Paolo Ienne", title = "Fast Parallel Algorithms for Enumeration of Simple, Temporal, and Hop-constrained Cycles", journal = j-TOPC, volume = "10", number = "3", pages = "15:1--15:??", month = sep, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3611642", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:37 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3611642", abstract = "Cycles are one of the fundamental subgraph patterns and being able to enumerate them in graphs enables important applications in a wide variety of fields, including finance, biology, chemistry, and network science. However, to enable cycle enumeration in \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Alvermann:2023:OLP, author = "Andreas Alvermann and Georg Hager and Holger Fehske", title = "Orthogonal Layers of Parallelism in Large-Scale Eigenvalue Computations", journal = j-TOPC, volume = "10", number = "3", pages = "16:1--16:??", month = sep, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3614444", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 29 08:18:37 MDT 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3614444", abstract = "We address the communication overhead of distributed sparse matrix-(multiple)-vector multiplication in the context of large-scale eigensolvers, using filter diagonalization as an example. The basis of our study is a performance model, which includes a communication metric that is computed directly from the matrix sparsity pattern without running any code. The performance model quantifies to which extent scalability and parallel efficiency are lost due to communication overhead.\par To restore scalability, we identify two orthogonal layers of parallelism in the filter diagonalization technique. In the horizontal layer the rows of the sparse matrix are distributed across individual processes. In the vertical layer bundles of multiple vectors are distributed across separate process groups. An analysis in terms of the communication metric predicts that scalability can be restored if, and only if, one implements the two orthogonal layers of parallelism via different distributed vector layouts.\par Our theoretical analysis is corroborated by benchmarks for application matrices from quantum and solid state physics, road networks, and nonlinear programming. We finally demonstrate the benefits of using orthogonal layers of parallelism with two exemplary application cases --- an exciton and a strongly correlated electron system --- which incur either small or large communication overhead.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Azar:2023:ISI, author = "Yossi Azar and Julian Shun", title = "Introduction to the Special Issue for {SPAA'21}", journal = j-TOPC, volume = "10", number = "4", pages = "17:1--17:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3630608", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3630608", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Anderson:2023:PMC, author = "Daniel Anderson and Guy E. Blelloch", title = "Parallel Minimum Cuts in {$ O(m \log_2 n) $} Work and Low Depth", journal = j-TOPC, volume = "10", number = "4", pages = "18:1--18:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3565557", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3565557", abstract = "We present a randomized $ O(m \log^2 n) $ work, $ O(\polylog n) $ depth parallel algorithm for minimum cut. This algorithm matches the work bounds of a recent sequential algorithm by Gawrychowski, Mozes, and Weimann [ICALP'20], and improves on the previously best \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Im:2023:NCS, author = "Sungjin Im and Ravi Kumar and Mahshid Montazer Qaem and Manish Purohit", title = "Non-clairvoyant Scheduling with Predictions", journal = j-TOPC, volume = "10", number = "4", pages = "19:1--19:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3593969", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3593969", abstract = "In the single-machine non-clairvoyant scheduling problem, the goal is to minimize the total completion time of jobs whose processing times are unknown a priori. We revisit this well-studied problem and consider the question of how to effectively use (. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "19", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Albers:2023:ARS, author = "Susanne Albers and Jens Quedenfeld", title = "Algorithms for Right-sizing Heterogeneous Data Centers", journal = j-TOPC, volume = "10", number = "4", pages = "20:1--20:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3595286", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3595286", abstract = "Power consumption is a dominant and still growing cost factor in data centers. In time periods with low load, the energy consumption can be reduced by powering down unused servers. We resort to a model introduced by Lin, Wierman, Andrew, and Thereska [23, \ldots{}]", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "20", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Maus:2023:DGC, author = "Yannic Maus", title = "Distributed Graph Coloring Made Easy", journal = j-TOPC, volume = "10", number = "4", pages = "21:1--21:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3605896", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3605896", abstract = "In this article, we present a deterministic $ \mathsf {CONGEST} $ algorithm to compute an $ O(k \Delta)$-vertex coloring in $ O(\Delta / k) + \log^* n$ rounds, where $ \Delta $ is the maximum degree of the network graph and $ k \geq 1$ can be freely chosen. The algorithm is extremely simple: \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "21", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Ahmad:2023:FAA, author = "Zafar Ahmad and Rezaul Chowdhury and Rathish Das and Pramod Ganapathi and Aaron Gregory and Yimin Zhu", title = "A Fast Algorithm for Aperiodic Linear Stencil Computation using {Fast Fourier Transforms}", journal = j-TOPC, volume = "10", number = "4", pages = "22:1--22:??", month = dec, year = "2023", CODEN = "????", DOI = "https://doi.org/10.1145/3606338", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Dec 21 10:57:17 MST 2023", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3606338", abstract = "Stencil computations are widely used to simulate the change of state of physical systems across a multidimensional grid over multiple timesteps. The state-of-the-art techniques in this area fall into three groups: cache-aware tiled looping algorithms, cache-oblivious divide-and-conquer trapezoidal algorithms, and Krylov subspace methods. In this article, we present two efficient parallel algorithms for performing linear stencil computations. Current direct solvers in this domain are computationally inefficient, and Krylov methods require manual labor and mathematical training. We solve these problems for linear stencils by using discrete Fourier transforms preconditioning on a Krylov method to achieve a direct solver that is both fast and general. Indeed, while all currently available algorithms for solving general linear stencils perform (NT) work, where N is the size of the spatial grid and T is the number of timesteps, our algorithms perform o(NT) work. To the best of our knowledge, we give the first algorithms that use fast Fourier transforms to compute final grid data by evolving the initial data for many timesteps at once. Our algorithms handle both periodic and aperiodic boundary conditions and achieve polynomially better performance bounds (i.e., computational complexity and parallel runtime) than all other existing solutions. Initial experimental results show that implementations of our algorithms that evolve grids of roughly 107 cells for around 105 timesteps run orders of magnitude faster than state-of-the-art implementations for periodic stencil problems, and $ 1.3 \times $ to $ 8.5 \times $ faster for aperiodic stencil problems.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "22", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Benoit:2024:CST, author = "Anne Benoit and Lucas Perotin and Yves Robert and Fr{\'e}d{\'e}ric Vivien", title = "Checkpointing Strategies to Tolerate Non-Memoryless Failures on {HPC} Platforms", journal = j-TOPC, volume = "11", number = "1", pages = "1:1--1:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3624560", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3624560", abstract = "This article studies checkpointing strategies for parallel applications subject to failures. The optimal strategy to minimize total execution time, or makespan, is well known when failure IATs obey an Exponential distribution, but it is unknown for non-. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Perotin:2024:IOS, author = "Lucas Perotin and Hongyang Sun", title = "Improved Online Scheduling of Moldable Task Graphs under Common Speedup Models", journal = j-TOPC, volume = "11", number = "1", pages = "2:1--2:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3630052", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3630052", abstract = "We consider the online scheduling problem of moldable task graphs on multiprocessor systems for minimizing the overall completion time (or makespan). Moldable job scheduling has been widely studied in the literature, in particular when tasks have \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lin:2024:HCH, author = "Shengle Lin and Wangdong Yang and Yikun Hu and Qinyun Cai and Minlu Dai and Haotian Wang and Kenli Li", title = "{HPS Cholesky}: Hierarchical Parallelized Supernodal {Cholesky} with Adaptive Parameters", journal = j-TOPC, volume = "11", number = "1", pages = "3:1--3:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3630051", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3630051", abstract = "Sparse supernodal Cholesky on multi-NUMAs is challenging due to the supernode relaxation and load balancing. In this work, we propose a novel approach to improve the performance of sparse Cholesky by combining deep learning with a relaxation parameter and \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Marotta:2024:CRL, author = "Romolo Marotta and Mauro Ianni and Alessandro Pellegrini and Francesco Quaglia", title = "A Conflict-Resilient Lock-Free Linearizable Calendar Queue", journal = j-TOPC, volume = "11", number = "1", pages = "4:1--4:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3635163", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3635163", abstract = "In the last two decades, great attention has been devoted to the design of non-blocking and linearizable data structures, which enable exploiting the scaled-up degree of parallelism in off-the-shelf shared-memory multi-core machines. In this context, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Muller:2024:MAE, author = "Stefan K. Muller and Jan Hoffmann", title = "Modeling and Analyzing Evaluation Cost of {CUDA} Kernels", journal = j-TOPC, volume = "11", number = "1", pages = "5:1--5:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3639403", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3639403", abstract = "Motivated by the increasing importance of general-purpose Graphic Processing Units (GPGPU) programming, exemplified by NVIDIA's CUDA framework, as well as the difficulty, especially for novice programmers, of reasoning about performance in GPGPU kernels, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cai:2024:AAB, author = "Qinyun Cai and Guoqing Xiao and Shengle Lin and Wangdong Yang and Keqin Li and Kenli Li", title = "{ABSS}: an Adaptive Batch-Stream Scheduling Module for Dynamic Task Parallelism on Chiplet-based Multi-Chip Systems", journal = j-TOPC, volume = "11", number = "1", pages = "6:1--6:??", month = mar, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3643597", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Wed Mar 13 07:22:23 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3643597", abstract = "Thanks to the recognition and promotion of chiplet-based High-Performance Computing (HPC) system design technology by semiconductor industry/market leaders, chiplet-based multi-chip systems have gradually become the mainstream. Unfortunately, programming \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Fu:2024:TLT, author = "Qiang Fu and Yuede Ji and Thomas Rolinger and H. Howie Huang", title = "{TLPGNN}: a Lightweight Two-level Parallelism Paradigm for Graph Neural Network Computation on Single and Multiple {GPUs}", journal = j-TOPC, volume = "11", number = "2", pages = "7:1--7:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3644712", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3644712", abstract = "Graph Neural Networks (GNNs) are an emerging class of deep learning models specifically designed for graph-structured data. They have been effectively employed in a variety of real-world applications, including recommendation systems, drug development, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "7", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Li:2024:CSO, author = "Zixuan Li and Yunchuan Qin and Qi Xiao and Wangdong Yang and Kenli Li", title = "{cuFasterTucker}: a Stochastic Optimization Strategy for Parallel Sparse {FastTucker} Decomposition on {GPU} Platform", journal = j-TOPC, volume = "11", number = "2", pages = "8:1--8:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3648094", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3648094", abstract = "The amount of scientific data is currently growing at an unprecedented pace, with tensors being a common form of data that display high-order, high-dimensional, and sparse features. While tensor-based analysis methods are effective, the vast increase in \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "8", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Darche:2024:LOT, author = "S{\'e}bastien Darche and Michel R. Dagenais", title = "Low-Overhead Trace Collection and Profiling on {GPU} Compute Kernels", journal = j-TOPC, volume = "11", number = "2", pages = "9:1--9:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3649510", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3649510", abstract = "While GPUs can bring substantial speedup to compute-intensive tasks, their programming is notoriously hard. From their programming model, to microarchitectural particularities, the programmer may encounter many pitfalls which may hinder performance in \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "9", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Li:2024:DSD, author = "Ziyang Li and Dongsheng Li and Yingwen Chen and Kai Chen and Yiming Zhang", title = "Decentralized Scheduling for Data-Parallel Tasks in the Cloud", journal = j-TOPC, volume = "11", number = "2", pages = "10:1--10:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3651858", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3651858", abstract = "For latency-sensitive data processing applications in the cloud, concurrent data-parallel tasks need to be scheduled and processed quickly. A data-parallel task usually consists of a set of sub-tasks, generating a set of flows that are collectively \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "10", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Xiao:2024:MLB, author = "Guoqing Xiao and Tao Zhou and Yuedan Chen and Yikun Hu and Kenli Li", title = "Machine Learning-Based Kernel Selector for {SpMV} Optimization in Graph Analysis", journal = j-TOPC, volume = "11", number = "2", pages = "11:1--11:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3652579", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3652579", abstract = "Sparse Matrix and Vector multiplication (SpMV) is one of the core algorithms in various large-scale scientific computing and real-world applications. With the rapid development of AI and big data, the input vector in SpMV becomes sparse in many \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "11", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Li:2024:CNS, author = "Zixuan Li and Yikun Hu and Mengquan Li and Wangdong Yang and Kenli Li", title = "{cuFastTucker}: a Novel Sparse {FastTucker} Decomposition For {HHLST} on Multi-{GPUs}", journal = j-TOPC, volume = "11", number = "2", pages = "12:1--12:??", month = jun, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3661450", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Thu Jun 13 07:45:59 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3661450", abstract = "High-order, high-dimension, and large-scale sparse tensors (HHLST) have found their origin in various real industrial applications, such as social networks, recommender systems, bioinformatics, and traffic information. To handle these complex tensors, \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "12", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Liu:2024:IPG, author = "Yiqian Liu and Noushin Azami and Avery Vanausdal and Martin Burtscher", title = "{Indigo3}: a Parallel Graph Analytics Benchmark Suite for Exploring Implementation Styles and Common Bugs", journal = j-TOPC, volume = "11", number = "3", pages = "13:1--13:??", month = sep, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3665251", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 13 13:52:04 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3665251", abstract = "Graph analytics codes are widely used and tend to exhibit input-dependent behavior, making them particularly interesting for software verification and validation. This article presents Indigo3, a labeled benchmark suite based on 7 graph algorithms that \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "13", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Bontes:2024:RSC, author = "Johan Bontes and James Gain", title = "Redzone stream compaction: removing $k$ items from a list in parallel {$ O(k) $} time", journal = j-TOPC, volume = "11", number = "3", pages = "14:1--14:??", month = sep, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3675782", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Fri Sep 13 13:52:04 MDT 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3675782", abstract = "Stream compaction, the parallel removal of selected items from a list, is a fundamental building block in parallel algorithms. It is extensively used, both in computer graphics, for shading, collision detection, and ray tracing, as well as in general \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "14", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Cui:2024:ATP, author = "Cu Cui", title = "Acceleration of Tensor-Product Operations with Tensor Cores", journal = j-TOPC, volume = "11", number = "4", pages = "15:1--15:??", month = dec, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3695466", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Nov 18 14:38:19 MST 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3695466", abstract = "In this article, we explore the acceleration of tensor product operations in finite element methods, leveraging the computational power of the NVIDIA A100 GPU Tensor Cores. We provide an accessible overview of the necessary mathematical background and discuss our implementation strategies. Our study focuses on two common programming approaches for NVIDIA Tensor Cores: the C++ Warp Matrix Functions in nvcuda::wmma and the inline Parallel Thread Execution (PTX) instructions mma.sync.aligned. A significant focus is placed on the adoption of the versatile inline PTX instructions combined with a conflict-free shared memory access pattern, a key to unlocking superior performance. When benchmarked against traditional CUDA Cores, our approach yields a remarkable 2.3-fold increase in double-precision performance, achieving 8 TFLOPS/s --- 45% of the theoretical maximum. Furthermore, in half-precision computations, numerical experiments demonstrate a fourfold enhancement in solving the Poisson equation using the flexible GMRES (FGMRES) method, preconditioned by a multigrid method in 3D. This is achieved while maintaining the same discretization error as observed in double-precision computations. These results highlight the considerable benefits of using Tensor Cores for finite element operators with tensor products, achieving an optimal balance between computational speed and precision.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "15", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Hesselink:2024:FCF, author = "Wim A. Hesselink and Peter A. Buhr and Colby A. Parsons", title = "First-Come-First-Served as a Separate Principle", journal = j-TOPC, volume = "11", number = "4", pages = "16:1--16:??", month = dec, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3669989", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Nov 18 14:38:19 MST 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3669989", abstract = "A lock is a mechanism to guarantee mutual exclusion with eventual progress, i.e., some degree of fairness. First-come-first-served (FCFS) progress is perfectly fair. FCFS progress can be offered by a locking algorithm or added by wrapping a non-FCFS lock \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "16", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pahlke:2024:PDM, author = "Johannes Pahlke and Ivo F. Sbalzarini", title = "Proven Distributed Memory Parallelization of Particle Methods", journal = j-TOPC, volume = "11", number = "4", pages = "17:1--17:??", month = dec, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3696189", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Nov 18 14:38:19 MST 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3696189", abstract = "We provide a mathematically proven parallelization scheme for particle methods on distributed-memory computer systems. Particle methods are a versatile and widely used class of algorithms for computer simulations and numerical predictions in various \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "17", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Tepiele:2024:DPB, author = "Hermann Bogning Tepiele and Vianney Kengne Tchendji and Mathias Akong Onabid and Jean Fr{\'e}d{\'e}ric Myoupo and Armel Nkonjoh Ngomade", title = "Dominant Point-Based Sequential and Parallel Algorithms for the Multiple Sequential Substring Constrained-{LCS} Problem", journal = j-TOPC, volume = "11", number = "4", pages = "18:1--18:??", month = dec, year = "2024", CODEN = "????", DOI = "https://doi.org/10.1145/3696657", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Mon Nov 18 14:38:19 MST 2024", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", URL = "https://dl.acm.org/doi/10.1145/3696657", abstract = "The Longest Common Subsequence (LCS) problem is a well-known and studied problem in computer science and bioinformatics. It consists in finding the longest subsequence that is common to two or more given sequences. In this article, we address the problem \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "18", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Pham:2025:DBM, author = "Minh Pham and Yongke Yuan and Hao Li and Chengcheng Mou and Yicheng Tu and Zichen Xu and Jinghan Meng", title = "Dynamic Buffer Management in Massively Parallel Systems: The Power of Randomness", journal = j-TOPC, volume = "12", number = "1", pages = "1:1--1:??", month = mar, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3701623", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Massively parallel systems, such as Graphics Processing Units (GPUs), play an increasingly crucial role in today's data-intensive computing. The unique challenges associated with developing system software for massively parallel hardware to support \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "1", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Wu:2025:EEP, author = "Chun-Yu Wu and Chih-Chieh Tu and Kai-Jung Cheng and Che-Rung Lee", title = "{EITHOT}: Efficient In-place Transposition of High Order Tensors on {GPUs}", journal = j-TOPC, volume = "12", number = "1", pages = "2:1--2:??", month = mar, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3711871", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Tensor transposition is a fundamental operation in tensor calculations with various applications. However, a naive implementation that copies each element from the source tensor to the transposed position in the target tensor requires double space, making \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "2", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Chen:2025:KDD, author = "Youguang Chen and William Ruys and George Biros", title = "{KNN-DBSCAN}: a {DBSCAN} in high dimensions", journal = j-TOPC, volume = "12", number = "1", pages = "3:1--3:??", month = mar, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3701624", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "Clustering is a fundamental task in machine learning. One of the most successful and broadly used algorithms is DBSCAN, a density-based clustering algorithm. DBSCAN requires $\epsilon$-nearest neighbor graphs of the input dataset, which are computed with range-. \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "3", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Lindermayr:2025:PPN, author = "Alexander Lindermayr and Nicole Megow", title = "Permutation Predictions for Non-Clairvoyant Scheduling", journal = j-TOPC, volume = "12", number = "2", pages = "4:1--4:??", month = jun, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3711872", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In non-clairvoyant scheduling, the task is to schedule jobs with a priori unknown processing requirements. We revisit this well-studied problem with the objective of minimizing the total (weighted) completion time in a recently popular learning-augmented \ldots{}", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "4", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{Tolmachev:2025:HPS, author = "Dmitrii Tolmachev and Philippe Marti and Giacomo Castiglioni and Andrew Jackson", title = "High Performance Solution of Tridiagonal Systems on the {GPU}", journal = j-TOPC, volume = "12", number = "2", pages = "5:1--5:25", month = jun, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3716171", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this article, we present PfSolve --- a new, performant, cross-platform, and open-source implementation of tridiagonal and bidiagonal matrix solvers for the GPU architecture. Released as a stand-alone library, PfSolve can solve systems of arbitrary size that fit into the memory of a single GPU with a potential extension to multi-GPU support in the future. The code works in single, double, and double-double emulation of quad precision using only 0.1\% of the original system size as additional memory. PfSolve is based on the in-house implementation of the Parallel Thomas algorithm optimized for GPU execution by using warp-level instructions and occupancy optimizations, which are discussed in detail in the article. This work also presents an accuracy analysis of the Parallel Thomas algorithm for tridiagonal matrices with various dominance factors (approximately, the ratio of the off-diagonal to diagonal terms) and demonstrates that PfSolve achieves a considerable speedup over vendor solutions on modern HPC GPUs like Nvidia H100 and AMD MI210. The source code for PfSolve is available on GitHub.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "5", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", } @Article{AlDaas:2025:CLB, author = "Hussam {Al Daas} and Grey Ballard and Laura Grigori and Suraj Kumar and Kathryn Rouse and Mathieu Verite", title = "Communication Lower Bounds and Optimal Algorithms for Symmetric Matrix Computations", journal = j-TOPC, volume = "12", number = "2", pages = "6:1--6:??", month = jun, year = "2025", CODEN = "????", DOI = "https://doi.org/10.1145/3727344", ISSN = "2329-4949 (print), 2329-4957 (electronic)", ISSN-L = "2329-4949", bibdate = "Sat Jun 14 09:03:17 MDT 2025", bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib", abstract = "In this article, we focus on the communication costs of three symmetric matrix computations: (i) multiplying a matrix with its transpose, known as a symmetric rank-k update (SYRK); (ii) adding the result of the multiplication of a matrix with the transpose of another matrix and the transpose of that result, known as a symmetric rank-2k update (SYR2K); and (iii) performing matrix multiplication with a symmetric input matrix (SYMM). All three computations appear in the Level 3 Basic Linear Algebra Subroutines (BLAS) and have wide use in applications involving symmetric matrices. We establish communication lower bounds for these kernels using sequential and distributed-memory parallel computational models, and we show that our bounds are tight by presenting communication-optimal algorithms for each setting. Our lower bound proofs rely on applying a geometric inequality for symmetric computations and analytically solving constrained nonlinear optimization problems. The symmetric matrix and its corresponding computations are accessed and performed according to a triangular block partitioning scheme in the optimal algorithms.", acknowledgement = ack-nhfb, ajournal = "ACM Trans. Parallel Comput.", articleno = "6", fjournal = "ACM Transactions on Parallel Computing", journal-URL = "https://dl.acm.org/loi/topc", }