Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

GARDENIA

GARDENIA This article presents the Graph Algorithm Repository for Designing Next-generation Accelerators (GARDENIA), a benchmark suite for studying irregular graph algorithms on massively parallel accelerators. Applications with limited control and data irregularity are the main focus of existing generic benchmarks for accelerators, while available graph processing benchmarks do not apply state-of-the-art algorithms and/or optimization techniques. GARDENIA includes emerging graph processing workloads from graph analytics, sparse linear algebra, and machine-learning domains, which mimic massively multithreaded commercial programs running on modern large-scale datacenters. Our characterization shows that GARDENIA exhibits irregular microarchitectural behavior, which is quite different from structured workloads and straightforward-implemented graph benchmarks. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Journal on Emerging Technologies in Computing Systems (JETC) Association for Computing Machinery

GARDENIA

Download PDF
13 pages

Loading next page...
 
/lp/association-for-computing-machinery/gardenia-skWEj0NrJ2

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2019 ACM
ISSN
1550-4832
eISSN
1550-4840
DOI
10.1145/3283450
Publisher site
See Article on Publisher Site

Abstract

This article presents the Graph Algorithm Repository for Designing Next-generation Accelerators (GARDENIA), a benchmark suite for studying irregular graph algorithms on massively parallel accelerators. Applications with limited control and data irregularity are the main focus of existing generic benchmarks for accelerators, while available graph processing benchmarks do not apply state-of-the-art algorithms and/or optimization techniques. GARDENIA includes emerging graph processing workloads from graph analytics, sparse linear algebra, and machine-learning domains, which mimic massively multithreaded commercial programs running on modern large-scale datacenters. Our characterization shows that GARDENIA exhibits irregular microarchitectural behavior, which is quite different from structured workloads and straightforward-implemented graph benchmarks.

Journal

ACM Journal on Emerging Technologies in Computing Systems (JETC) – Association for Computing Machinery

Published: Jan 9, 2019

Keywords: Benchmark suite

References

  • A scalable processing-in-memory accelerator for parallel graph processing
    Ahn, Junwhan; Hong, Sungpack; Yoo, Sungjoo; Mutlu, Onur; Choi, Kiyoung
  • Direction-optimizing breadth-first search
    Beamer, Scott; Asanović, Krste; Patterson, David
  • Locality exists in graph processing: Workload characterization on an ivy bridge server
    Beamer, Scott; Asanovic, Krste; Patterson, David
  • The GAP benchmark suite
    Beamer, Scott; Asanovic, Krste; Patterson, David A.
  • The PARSEC benchmark suite: Characterization and architectural implications
    Bienia, Christian; Kumar, Sanjeev; Singh, Jaswinder Pal; Li, Kai
  • A quantitative study of irregular programs on GPUs
    Burtscher, M.; Nasre, R.; Pingali, K.
  • Pannotia: Understanding irregular GPGPU graph applications
    Che, Shuai; Beckmann, Bradford M.; Reinhardt, Steven K.; Skadron, Kevin
  • Rodinia: A benchmark suite for heterogeneous computing
    Che, Shuai; Boyer, Michael; Meng, Jiayuan; Tarjan, David; Sheaffer, Jeremy W.; Lee, Sang-Ha; Skadron, Kevin
  • Efficient and high-quality sparse graph coloring on the GPU
    Chen, Xuhao; Li, Pingfan; Fang, Jianbin; Tang, Tao; Wang, Zhiying; Yang, Canqun
  • Cusp: Generic Parallel Algorithms for Sparse Matrix and Graph Computations
    Dalton, Steven; Bell, Nathan; Olson, Luke; Garland, Michael
  • Work-efficient parallel GPU methods for single-source shortest paths
    Davidson, A.; Baxter, S.; Garland, M.; Owens, J. D.
  • The University of Florida sparse matrix collection
    Davis, Timothy A.; Hu, Yifan
  • Graphicionado: A high-performance and energy-efficient accelerator for graph analytics
    Ham, T. J.; Wu, L.; Sundaram, N.; Satish, N.; Martonosi, M.
  • Accelerating CUDA graph algorithms at maximum warp
    Hong, Sungpack; Kim, Sang Kyun; Oguntebi, Tayo; Olukotun, Kunle
  • CuSha: Vertex-centric graph processing on GPUs
    Khorasani, Farzad; Vora, Keval; Gupta, Rajiv; Bhuyan, Laxmi N.
  • Konect: The Koblenz network collection
    Kunegis, Jérôme
  • SNAP: Stanford Network Analysis Platform
    Leskovec, J.
  • Distributed GraphLab: A framework for machine learning and data mining in the cloud
    Low, Yucheng; Bickson, Danny; Gonzalez, Joseph; Guestrin, Carlos; Kyrola, Aapo; Hellerstein, Joseph M.
  • Graphlab: A new parallel framework for machine learning
    Low, Yucheng; Gonzalez, Joseph; Kyrola, Aapo; Bickson, Danny; Guestrin, Carlos; Hellerstein, Joseph M.
  • Pregel: A system for large-scale graph processing
    Malewicz, Grzegorz; Austern, Matthew H.; Bik, Aart J. C.; Dehnert, James C.; Horn, Ilan; Leiser, Naty; Czajkowski, Grzegorz
  • Scalable GPU graph traversal
    Merrill, Duane; Garland, Michael; Grimshaw, Andrew
  • Δ-stepping: A parallelizable shortest path algorithm
    Meyer, Ulrich; Sanders, Peter
  • GraphBIG: Understanding graph computing in the context of industrial solutions
    Nai, Lifeng; Xia, Yinglong; Tanase, Ilie G.; Kim, Hyesoon; Lin, Ching-Yung
  • Data-driven versus topology-driven irregular computations on GPUs
    Nasre, R.; Burtscher, M.; Pingali, K.
  • cuDNN Library
    NVIDIA.,
  • CUSPARSE Library
    NVIDIA.,
  • nvGRAPH Library
    NVIDIA.,
  • Computing SDK
    Nvidia, GPU
  • Energy efficient architecture for graph analytics accelerators
    Ozdal, Muhammet Mustafa; Yesil, Serif; Kim, Taemin; Ayupov, Andrey; Greth, John; Burns, Steven; Ozturk, Ozcan
  • The PageRank Citation Ranking: Bringing Order to the Web
    Page, Lawrence; Brin, Sergey; Motwani, Rajeev; Winograd, Terry
  • GraphReduce: Processing large-scale graphs on accelerator-based systems
    Sengupta, Dipanjan; Song, Shuaiwen Leon; Agarwal, Kapil; Schwan, Karsten
  • Ligra: A lightweight graph processing framework for shared memory
    Shun, Julian; Blelloch, Guy E.
  • Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing
    Stratton, John A.; Rodrigrues, Christopher; Sung, I.-Jui; Obeid, Nady; Chang, Liwen; Liu, Geng; Hwu, Wen-Mei W.
  • GraphMat: High-performance graph analytics made productive
    Sundaram, Narayanan; Satish, Nadathur; Patwary, Md Mostofa Ali; Dulloor, Subramanya R.; Anderson, Michael J.; Vadlamudi, Satya Gautam; Das, Dipankar; Dubey, Pradeep
  • Gunrock: A high-performance graph processing library on the GPU
    Wang, Yangzihao; Davidson, Andrew; Pan, Yuechao; Wu, Yuduo; Riffel, Andy; Owens, John D.
  • IMP: Indirect memory prefetcher
    Yu, Xiangyao; Hughes, Christopher J.; Satish, Nadathur; Devadas, Srinivas
  • Medusa: Simplified graph processing on GPUs
    Zhong, J.; He, B.