{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:44:56Z","timestamp":1772725496241,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":100,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T00:00:00Z","timestamp":1570838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,12]]},"DOI":"10.1145\/3352460.3358286","type":"proceedings-article","created":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T11:16:45Z","timestamp":1570792605000},"page":"600-614","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":65,"title":["SMASH"],"prefix":"10.1145","author":[{"given":"Konstantinos","family":"Kanellopoulos","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nandita","family":"Vijaykumar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University and ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christina","family":"Giannoula","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich and National Technical University of Athens"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roknoddin","family":"Azizi","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Skanda","family":"Koppula","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nika Mansouri","family":"Ghiasi","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taha","family":"Shahroodi","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan Gomez","family":"Luna","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich and Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Intel Math Kernel Library. http:\/\/software.intel.com\/en-us\/articles\/intel-mkl\/"},{"key":"e_1_3_2_1_2_1","unstructured":"Intel Xeon Gold 5118. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/120473\/intel-xeon-gold-5118-processor-16-5m-cache-2-30-ghz.html."},{"key":"e_1_3_2_1_3_1","unstructured":"SMASH code. https:\/\/github.com\/CMU-SAFARI\/SMASH"},{"key":"e_1_3_2_1_4_1","volume-title":"A Scalable Processing-in-Memory Accelerator for Parallel Graph Processing,\" in ISCA","author":"Ahn J.","year":"2015","unstructured":"J. Ahn, S. Hong, S. Yoo, O. Mutlu, and K. Choi, \"A Scalable Processing-in-Memory Accelerator for Parallel Graph Processing,\" in ISCA, 2015."},{"key":"e_1_3_2_1_5_1","volume-title":"Locality-Aware Processing-in-Memory Architecture,\"","author":"Ahn J.","year":"2015","unstructured":"J. Ahn, S. Yoo, O. Mutlu, and K. Y. Choi, \"PIM-Enabled Instructions: A Low-Overhead, Locality-Aware Processing-in-Memory Architecture,\" 2015."},{"key":"e_1_3_2_1_6_1","volume-title":"Exploiting Locality in Sparse Matrix-Matrix Multiplication on Many-Core Architectures,\" TPDS","author":"Akbudak K.","year":"2017","unstructured":"K. Akbudak and C. Aykanat, \"Exploiting Locality in Sparse Matrix-Matrix Multiplication on Many-Core Architectures,\" TPDS, 2017."},{"key":"e_1_3_2_1_7_1","volume-title":"Pattern-Based Sparse Matrix Representation for Memory-Efficient SMVM Kernels,\" in ISC","author":"Belgin M.","year":"2009","unstructured":"M. Belgin, G. Back, and C. J. Ribbens, \"Pattern-Based Sparse Matrix Representation for Memory-Efficient SMVM Kernels,\" in ISC, 2009."},{"key":"e_1_3_2_1_8_1","volume-title":"SlimSell: A Vectorizable Graph Representation for Breadth-First Search,\" in IPDPS","author":"Besta M.","year":"2017","unstructured":"M. Besta, F. Marending, E. Solomonik, and T. Hoefler, \"SlimSell: A Vectorizable Graph Representation for Breadth-First Search,\" in IPDPS, 2017."},{"key":"e_1_3_2_1_9_1","volume-title":"To Push or To Pull: On Reducing Communication and Synchronization in Graph Computations,\" in HPDC","author":"Besta M.","year":"2017","unstructured":"M. Besta, M. Podstawski, L. Groner, E. Solomonik, and T. Hoefler, \"To Push or To Pull: On Reducing Communication and Synchronization in Graph Computations,\" in HPDC, 2017."},{"key":"e_1_3_2_1_10_1","volume-title":"Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid,\" SIGGRAPH","author":"Bolz J.","year":"2003","unstructured":"J. Bolz, I. Farmer, E. Grinspun, and P. Schr\u00f6der, \"Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid,\" SIGGRAPH, 2003."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173177"},{"key":"e_1_3_2_1_12_1","volume-title":"The Anatomy of a Large-scale Hypertextual Web Search Engine,\" in WWW","author":"Brin S.","year":"1998","unstructured":"S. Brin and L. Page, \"The Anatomy of a Large-scale Hypertextual Web Search Engine,\" in WWW, 1998."},{"key":"e_1_3_2_1_13_1","volume-title":"Challenges and Advances in Parallel Sparse Matrix-Matrix Multiplication,\" in ICPP","author":"Buluc A.","year":"2008","unstructured":"A. Buluc and J. R. Gilbert, \"Challenges and Advances in Parallel Sparse Matrix-Matrix Multiplication,\" in ICPP, 2008."},{"key":"e_1_3_2_1_14_1","volume-title":"Parallel Sparse Matrix-Matrix Multiplication and Indexing: Implementation and Experiments,\" SISC","author":"Bulu\u00e7 A.","year":"2012","unstructured":"A. Bulu\u00e7 and J. R. Gilbert, \"Parallel Sparse Matrix-Matrix Multiplication and Indexing: Implementation and Experiments,\" SISC, 2012."},{"key":"e_1_3_2_1_15_1","volume-title":"Reduced-Bandwidth Multithreaded Algorithms for Sparse Matrix-Vector Multiplication,\" in IPDPS","author":"Buluc A.","year":"2011","unstructured":"A. Buluc, S. Williams, L. Oliker, and J. Demmel, \"Reduced-Bandwidth Multithreaded Algorithms for Sparse Matrix-Vector Multiplication,\" in IPDPS, 2011."},{"key":"e_1_3_2_1_16_1","volume-title":"Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication Using Compressed Sparse Blocks,\" in SPAA","author":"Bulu\u00e7 A.","year":"2009","unstructured":"A. Bulu\u00e7, J. T. Fineman, M. Frigo, J. R. Gilbert, and C. E. Leiserson, \"Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication Using Compressed Sparse Blocks,\" in SPAA, 2009."},{"key":"e_1_3_2_1_17_1","volume-title":"Towards Memristor based Accelerator for Sparse Matrix Vector Multiplication,\" in ISCAS","author":"Cui J.","year":"2016","unstructured":"J. Cui and Q. Qiu, \"Towards Memristor based Accelerator for Sparse Matrix Vector Multiplication,\" in ISCAS, 2016."},{"key":"e_1_3_2_1_18_1","volume-title":"Optimizing Sparse Matrix-Matrix Multiplication for the GPU,\" TMS","author":"Dalton S.","year":"2015","unstructured":"S. Dalton, L. Olson, and N. Bell, \"Optimizing Sparse Matrix-Matrix Multiplication for the GPU,\" TMS, 2015."},{"key":"e_1_3_2_1_19_1","volume-title":"The University of Florida Sparse Matrix Collection,\" TOMS","author":"Davis T. A.","year":"2011","unstructured":"T. A. Davis and Y. Hu, \"The University of Florida Sparse Matrix Collection,\" TOMS, 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/898763"},{"key":"e_1_3_2_1_21_1","volume-title":"A GPU Solver for Sparse Generalized Eigenvalue Problems with Symmetric Complex-Valued Matrices Obtained Using Higher-Order FEM,\" IEEE Access","author":"Dziekonski A.","year":"2018","unstructured":"A. Dziekonski and M. Mrozowski, \"A GPU Solver for Sparse Generalized Eigenvalue Problems with Symmetric Complex-Valued Matrices Obtained Using Higher-Order FEM,\" IEEE Access, 2018."},{"key":"e_1_3_2_1_22_1","volume-title":"Performance Analysis and Optimization of Sparse Matrix-Vector Multiplication on Modern Multi-and Many-Core Processors,\" in ICPP","author":"Elafrou A.","year":"2017","unstructured":"A. Elafrou, G. Goumas, and N. Koziris, \"Performance Analysis and Optimization of Sparse Matrix-Vector Multiplication on Modern Multi-and Many-Core Processors,\" in ICPP, 2017."},{"key":"e_1_3_2_1_23_1","volume-title":"SparseX: A Library for High-Performance Sparse Matrix-Vector Multiplication on Multicore Platforms,\" TOMS","author":"Elafrou A.","year":"2018","unstructured":"A. Elafrou, V. Karakasis, T. Gkountouvas, K. Kourtis, G. Goumas, and N. Koziris, \"SparseX: A Library for High-Performance Sparse Matrix-Vector Multiplication on Multicore Platforms,\" TOMS, 2018."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"R. D. Falgout \"An Introduction to Algebraic Multigrid \" Computing in Science Engineering 2006.","DOI":"10.1109\/MCSE.2006.105"},{"key":"e_1_3_2_1_25_1","volume-title":"hypre: A Library of High Performance Preconditioners,\" in ICCS","author":"Falgout R. D.","year":"2002","unstructured":"R. D. Falgout and U. M. Yang, \"hypre: A Library of High Performance Preconditioners,\" in ICCS, 2002."},{"key":"e_1_3_2_1_26_1","volume-title":"A High Memory Bandwidth FPGA Accelerator for Sparse Matrix-Vector Multiplication,\" in FCCM","author":"Fowers J.","year":"2014","unstructured":"J. Fowers, K. Ovtcharov, K. Strauss, E. S. Chung, and G. Stitt, \"A High Memory Bandwidth FPGA Accelerator for Sparse Matrix-Vector Multiplication,\" in FCCM, 2014."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"L. Freeman \"A Set of Measures of Centrality Based on Betweenness \" Sociometry 1977.","DOI":"10.2307\/3033543"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_2_1_29_1","unstructured":"B. Graham \"Spatially-Sparse Convolutional Neural Networks \" arXiv 2014."},{"key":"e_1_3_2_1_30_1","volume-title":"Efficient Sparse Matrix-vector Multiplication on GPUs Using the CSR Storage Format,\" in SC","author":"Greathouse J. L.","year":"2014","unstructured":"J. L. Greathouse and M. Daga, \"Efficient Sparse Matrix-vector Multiplication on GPUs Using the CSR Storage Format,\" in SC, 2014."},{"key":"e_1_3_2_1_31_1","volume-title":"GPU-Accelerated Sparse Matrix-Matrix Multiplication by Iterative Row Merging,\" SIAM","author":"Gremse F.","year":"2015","unstructured":"F. Gremse, A. H\u00f6fter, L. O. Schwen, F. Kiessling, and U. Naumann, \"GPU-Accelerated Sparse Matrix-Matrix Multiplication by Iterative Row Merging,\" SIAM, 2015."},{"key":"e_1_3_2_1_32_1","volume-title":"Accelerating SpMV on FPGAs by Compressing Nonzero Values,\" in FCCM","author":"Grigoras P.","year":"2015","unstructured":"P. Grigoras, P. Burovskiy, E. Hung, and W. Luk, \"Accelerating SpMV on FPGAs by Compressing Nonzero Values,\" in FCCM, 2015."},{"key":"e_1_3_2_1_33_1","volume-title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation,\" CoRR","author":"Gupta U.","year":"2019","unstructured":"U. Gupta, X. Wang, M. Naumov, C. Wu, B. Reagen, D. Brooks, B. Cottel, K. M. Hazelwood, B. Jia, H. S. Lee, A. Malevich, D. Mudigere, M. Smelyanskiy, L. Xiong, and X. Zhang, \"The Architectural Implications of Facebook's DNN-based Personalized Recommendation,\" CoRR, 2019."},{"key":"e_1_3_2_1_34_1","volume-title":"PASTIX: A High-Performance Parallel Direct Solver for Sparse Symmetric Positive Definite Systems,\" PMAA","author":"H\u00e9non P.","year":"2002","unstructured":"P. H\u00e9non, P. Ramet, and J. Roman, \"PASTIX: A High-Performance Parallel Direct Solver for Sparse Symmetric Positive Definite Systems,\" PMAA, 2002."},{"key":"e_1_3_2_1_35_1","volume-title":"Efficient Sparse-Matrix Multi-Vector Product on GPUs,\" in HPDC","author":"Hong C.","year":"2018","unstructured":"C. Hong, A. Sukumaran-Rajam, B. Bandyopadhyay, J. Kim, S. E. Kurt, I. Nisa, S. Sabhlok, \u00dc. V. \u00c7ataly\u00fcrek, S. Parthasarathy, and P. Sadayappan, \"Efficient Sparse-Matrix Multi-Vector Product on GPUs,\" in HPDC, 2018."},{"key":"e_1_3_2_1_36_1","volume-title":"Mechanisms, Evaluation,\"","author":"Hsieh K.","year":"2016","unstructured":"K. Hsieh, S. M. Khan, N. Vijaykumar, K. K. Chang, A. Boroumand, S. Ghose, and O. Mutlu, \"Accelerating Pointer Chasing in 3D-Stacked memory: Challenges, Mechanisms, Evaluation,\" 2016."},{"key":"e_1_3_2_1_37_1","volume-title":"Sparsity: Optimization Framework for Sparse Matrix Kernels,\" IJHPCA","author":"Im E.-J.","year":"2004","unstructured":"E.-J. Im, K. Yelick, and R. Vuduc, \"Sparsity: Optimization Framework for Sparse Matrix Kernels,\" IJHPCA, 2004."},{"key":"e_1_3_2_1_38_1","volume-title":"Optimizing Sparse Matrix Vector Multiplication on SMP.\" in PPSC","author":"Im E.-J.","year":"1999","unstructured":"E.-J. Im and K. A. Yelick, \"Optimizing Sparse Matrix Vector Multiplication on SMP.\" in PPSC, 1999."},{"key":"e_1_3_2_1_39_1","volume-title":"PFEAST: A High Performance Sparse Eigenvalue Solver Using Distributed-memory Linear Solvers,\" in SC","author":"Kestyn J.","year":"2016","unstructured":"J. Kestyn, V. Kalantzis, E. Polizzi, and Y. Saad, \"PFEAST: A High Performance Sparse Eigenvalue Solver Using Distributed-memory Linear Solvers,\" in SC, 2016."},{"key":"e_1_3_2_1_40_1","volume-title":"taco: A Tool to Generate Tensor Algebra Kernels,\" in ASE","author":"Kjolstad F.","year":"2017","unstructured":"F. Kjolstad, S. Chou, D. Lugato, S. Kamil, and S. Amarasinghe, \"taco: A Tool to Generate Tensor Algebra Kernels,\" in ASE, 2017."},{"key":"e_1_3_2_1_41_1","volume-title":"Optimizing Sparse Matrix-Vector Multiplication using Index and Value Compression,\" in CF","author":"Kourtis K.","year":"2008","unstructured":"K. Kourtis, G. Goumas, and N. Koziris, \"Optimizing Sparse Matrix-Vector Multiplication using Index and Value Compression,\" in CF, 2008."},{"key":"e_1_3_2_1_42_1","volume-title":"CSX: An Extended Compression Format for SpMV on Shared Memory Systems,\" in PPoPP","author":"Kourtis K.","year":"2011","unstructured":"K. Kourtis, V. Karakasis, G. Goumas, and N. Koziris, \"CSX: An Extended Compression Format for SpMV on Shared Memory Systems,\" in PPoPP, 2011."},{"key":"e_1_3_2_1_43_1","volume-title":"Westmere: A Family of 32nm IA Processors,\" in ISSCC","author":"Kurd N.","year":"2010","unstructured":"N. Kurd, S. Bhamidipati, C. Mozak, J. L. Miller, T. M. Wilson, M. Nemani, and M. Chowdhury, \"Westmere: A Family of 32nm IA Processors,\" in ISSCC, 2010."},{"key":"e_1_3_2_1_44_1","volume-title":"Evaluation Criteria for Sparse Matrix Storage Formats,\" in TPDS","author":"Langr D.","year":"2016","unstructured":"D. Langr and P. Tvrdik, \"Evaluation Criteria for Sparse Matrix Storage Formats,\" in TPDS, 2016."},{"key":"e_1_3_2_1_45_1","volume-title":"Snap: A General-Purpose Network Analysis and Graph-Mining Library,\" TIST","author":"Leskovec J.","year":"2016","unstructured":"J. Leskovec and R. Sosi\u010d, \"Snap: A General-Purpose Network Analysis and Graph-Mining Library,\" TIST, 2016."},{"key":"e_1_3_2_1_46_1","volume-title":"SMAT: An Input Adaptive Auto-tuner for Sparse Matrix-vector Multiplication,\" in PLDI","author":"Li J.","year":"2013","unstructured":"J. Li, G. Tan, M. Chen, and N. Sun, \"SMAT: An Input Adaptive Auto-tuner for Sparse Matrix-vector Multiplication,\" in PLDI, 2013."},{"key":"e_1_3_2_1_47_1","volume-title":"CACTI-P: Architecture-Level Modeling for SRAM-Based Structures with Advanced Leakage Reduction Techniques,\" in CAD","author":"Li S.","year":"2011","unstructured":"S. Li, K. Chen, J. H. Ahn, J. B. Brockman, and N. P. Jouppi, \"CACTI-P: Architecture-Level Modeling for SRAM-Based Structures with Advanced Leakage Reduction Techniques,\" in CAD, 2011."},{"key":"e_1_3_2_1_48_1","unstructured":"C. Y. Lin N. Wong and H. K.-H. So \"Design Space Exploration for Sparse Matrix-Matrix Multiplication on FPGAs \" FPT 2013."},{"key":"e_1_3_2_1_49_1","volume-title":"Amazon.com Recommendations: Item-to-Item Collaborative Filtering,\" IC","author":"Linden G.","year":"2003","unstructured":"G. Linden, B. Smith, and J. York, \"Amazon.com Recommendations: Item-to-Item Collaborative Filtering,\" IC, 2003."},{"key":"e_1_3_2_1_50_1","volume-title":"Sparse Convolutional Neural Networks,\" in CVPR","author":"Liu B.","year":"2015","unstructured":"B. Liu, M. Wang, H. Foroosh, M. Tappen, and M. Pensky, \"Sparse Convolutional Neural Networks,\" in CVPR, 2015."},{"key":"e_1_3_2_1_51_1","volume-title":"An Efficient GPU General Sparse Matrix-Matrix Multiplication for Irregular Data,\" in IPDPS","author":"Liu W.","year":"2014","unstructured":"W. Liu and B. Vinter, \"An Efficient GPU General Sparse Matrix-Matrix Multiplication for Irregular Data,\" in IPDPS, 2014."},{"key":"e_1_3_2_1_52_1","volume-title":"A Framework for General Sparse Matrix-matrix Multiplication on GPUs and Heterogeneous Processors,\" JPDC","author":"Liu W.","year":"2015","unstructured":"W. Liu and B. Vinter, \"A Framework for General Sparse Matrix-matrix Multiplication on GPUs and Heterogeneous Processors,\" JPDC, 2015."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_2_1_54_1","volume-title":"Efficient Sparse Matrix-Vector Multiplication on x86-Based Many-Core Processors,\" in SC","author":"Liu X.","year":"2013","unstructured":"X. Liu, M. Smelyanskiy, E. Chow, and P. Dubey, \"Efficient Sparse Matrix-Vector Multiplication on x86-Based Many-Core Processors,\" in SC, 2013."},{"key":"e_1_3_2_1_55_1","volume-title":"Sparse Matrix-Matrix Multiplication on Modern Architectures,\" in HiPC","author":"Matam K. K.","year":"2012","unstructured":"K. K. Matam, S. R. K. B. Indarapu, and K. Kothapalli, \"Sparse Matrix-Matrix Multiplication on Modern Architectures,\" in HiPC, 2012."},{"key":"e_1_3_2_1_56_1","volume-title":"Optimizing Sparse Matrix-Vector Product Computations using Unroll and Jam,\" IJHPCA","author":"Mellor-Crummey J.","year":"2004","unstructured":"J. Mellor-Crummey and J. Garvin, \"Optimizing Sparse Matrix-Vector Product Computations using Unroll and Jam,\" IJHPCA, 2004."},{"key":"e_1_3_2_1_57_1","volume-title":"Merge-Based Parallel Sparse Matrix-Vector Multiplication,\" in SC","author":"Merrill D.","year":"2016","unstructured":"D. Merrill and M. Garland, \"Merge-Based Parallel Sparse Matrix-Vector Multiplication,\" in SC, 2016."},{"key":"e_1_3_2_1_58_1","volume-title":"Merge-Based Sparse Matrix-Vector Multiplication (SpMV) using the CSR Storage Format,\" in PPoPP","author":"Merrill D.","year":"2016","unstructured":"D. Merrill and M. Garland, \"Merge-Based Sparse Matrix-Vector Multiplication (SpMV) using the CSR Storage Format,\" in PPoPP, 2016."},{"key":"e_1_3_2_1_59_1","volume-title":"Fine-Grained Accelerators for Sparse Machine Learning Workloads,\" in ASP-DAC","author":"Mishra A. K.","year":"2017","unstructured":"A. K. Mishra, E. Nurvitadhi, G. Venkatesh, J. Pearce, and D. Marr, \"Fine-Grained Accelerators for Sparse Machine Learning Workloads,\" in ASP-DAC, 2017."},{"key":"e_1_3_2_1_60_1","volume-title":"Exploiting Locality in Graph Analytics Through Hardware-Accelerated Traversal Scheduling,\" in MICRO","author":"Mukkara A.","year":"2018","unstructured":"A. Mukkara, N. Beckmann, M. Abeydeera, X. Ma, and D. Sanchez, \"Exploiting Locality in Graph Analytics Through Hardware-Accelerated Traversal Scheduling,\" in MICRO, 2018."},{"key":"e_1_3_2_1_61_1","volume-title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems,\" CoRR","author":"Naumov M.","year":"2019","unstructured":"M. Naumov, D. Mudigere, H. M. Shi, J. Huang, N. Sundaraman, J. Park, X. Wang, U. Gupta, C. Wu, A. G. Azzolini, D. Dzhulgakov, A. Mallevich, I. Cherniavskii, Y. Lu, R. Krishnamoorthi, A. Yu, V. Kondratenko, S. Pereira, X. Chen, W. Chen, V. Rao, B. Jia, L. Xiong, and M. Smelyanskiy, \"Deep Learning Recommendation Model for Personalization and Recommendation Systems,\" CoRR, 2019."},{"key":"e_1_3_2_1_62_1","volume-title":"When Cache Blocking of Sparse Matrix Vector Multiply Works and Why,\" AAECC","author":"Nishtala R.","year":"2007","unstructured":"R. Nishtala, R. W. Vuduc, J. W. Demmel, and K. A. Yelick, \"When Cache Blocking of Sparse Matrix Vector Multiply Works and Why,\" AAECC, 2007."},{"key":"e_1_3_2_1_63_1","volume-title":"A Sparse Matrix Vector Multiply Accelerator for Support Vector Machine,\" in CASES","author":"Nurvitadhi E.","year":"2015","unstructured":"E. Nurvitadhi, A. Mishra, and D. Marr, \"A Sparse Matrix Vector Multiply Accelerator for Support Vector Machine,\" in CASES, 2015."},{"key":"e_1_3_2_1_64_1","volume-title":"Hardware Accelerator for Analytics of Sparse Data,\" in DAC","author":"Nurvitadhi E.","year":"2016","unstructured":"E. Nurvitadhi, A. Mishra, Y. Wang, G. Venkatesh, and D. Marr, \"Hardware Accelerator for Analytics of Sparse Data,\" in DAC, 2016."},{"key":"e_1_3_2_1_65_1","unstructured":"L. Page S. Brin R. Motwani and T. Winograd \"The PageRank Citation Ranking: Bringing Order to the Web.\" Stanford InfoLab Tech. Rep. 1999."},{"key":"e_1_3_2_1_66_1","volume-title":"OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator,\" in HPCA","author":"Pal S.","year":"2018","unstructured":"S. Pal, J. Beaumont, D.-H. Park, A. Amarnath, S. Feng, C. Chakrabarti, H.-S. Kim, D. Blaauw, T. Mudge, and R. Dreslinski, \"OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator,\" in HPCA, 2018."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"crossref","unstructured":"G. Penn \"Efficient Transitive Closure of Sparse Matrices over Closed Semirings \" AMiLP 2006.","DOI":"10.1016\/j.tcs.2005.11.008"},{"key":"e_1_3_2_1_68_1","volume-title":"Improving Performance of Sparse Matrix-Vector Multiplication,\" in SC","author":"Pinar A.","year":"1999","unstructured":"A. Pinar and M. T. Heath, \"Improving Performance of Sparse Matrix-Vector Multiplication,\" in SC, 1999."},{"key":"e_1_3_2_1_69_1","volume-title":"Sparse LU Factorization for Parallel Circuit Simulation on GPU,\" in DAC","author":"Ren L.","year":"2012","unstructured":"L. Ren, X. Chen, Y. Wang, C. Zhang, and H. Yang, \"Sparse LU Factorization for Parallel Circuit Simulation on GPU,\" in DAC, 2012."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_2_1_72_1","volume-title":"Scan Primitives for GPU Computing,\" in GH","author":"Sengupta S.","year":"2007","unstructured":"S. Sengupta, M. Harris, Y. Zhang, and J. D. Owens, \"Scan Primitives for GPU Computing,\" in GH, 2007."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750379"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_1_75_1","unstructured":"A. Smith. 6 New Facts About Facebook. http:\/\/mediashift.org"},{"key":"e_1_3_2_1_76_1","volume-title":"GraphR: Accelerating Graph Processing using ReRAM,\" in HPCA","author":"Song L.","year":"2018","unstructured":"L. Song, Y. Zhuo, X. Qian, H. Li, and Y. Chen, \"GraphR: Accelerating Graph Processing using ReRAM,\" in HPCA, 2018."},{"key":"e_1_3_2_1_77_1","volume-title":"clSpMV: A Cross-Platform OpenCL SpMV Framework on GPUs,\" in ICS","author":"Su B.-Y.","year":"2012","unstructured":"B.-Y. Su and K. Keutzer, \"clSpMV: A Cross-Platform OpenCL SpMV Framework on GPUs,\" in ICS, 2012."},{"key":"e_1_3_2_1_78_1","volume-title":"Caching-Efficient Multithreaded Fast Multiplication of Sparse Matrices,\" in IPPS","author":"Sulatycke P. D.","year":"1998","unstructured":"P. D. Sulatycke and K. Ghose, \"Caching-Efficient Multithreaded Fast Multiplication of Sparse Matrices,\" in IPPS, 1998."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"crossref","unstructured":"S. Toledo \"Improving the Memory-System Performance of Sparse-Matrix Vector Multiplication \" IBM Journal of research and development 1997.","DOI":"10.1147\/rd.416.0711"},{"key":"e_1_3_2_1_80_1","volume-title":"Rethinking the Memory Hierarchy for Modern Languages,\" in MICRO","author":"Tsai P.-A.","year":"2018","unstructured":"P.-A. Tsai, Y. L. Gan, and D. Sanchez, \"Rethinking the Memory Hierarchy for Modern Languages,\" in MICRO, 2018."},{"key":"e_1_3_2_1_81_1","volume-title":"Not Cache Lines: An Object-Based Compressed Memory Hierarchy,\" in ASPLOS","author":"Tsai P.-A.","year":"2019","unstructured":"P.-A. Tsai and D. Sanchez, \"Compress Objects, Not Cache Lines: An Object-Based Compressed Memory Hierarchy,\" in ASPLOS, 2019."},{"key":"e_1_3_2_1_82_1","volume-title":"An Energy Efficient Column-major Backend for FPGA SpMV Accelerators,\" in ICCD","author":"Umuroglu Y.","year":"2014","unstructured":"Y. Umuroglu and M. Jahre, \"An Energy Efficient Column-major Backend for FPGA SpMV Accelerators,\" in ICCD, 2014."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"crossref","unstructured":"S. Van Dongen \"Graph Clustering via a Discrete Uncoupling Process \" SIMAX 2008.","DOI":"10.1137\/040608635"},{"key":"e_1_3_2_1_84_1","volume-title":"The Locality Descriptor: A Holistic Cross-Layer Abstraction to Express Data Locality In GPUs,\" in ISCA","author":"Vijaykumar N.","year":"2018","unstructured":"N. Vijaykumar, E. Ebrahimi, K. Hsieh, P. B. Gibbons, and O. Mutlu, \"The Locality Descriptor: A Holistic Cross-Layer Abstraction to Express Data Locality In GPUs,\" in ISCA, 2018."},{"key":"e_1_3_2_1_85_1","volume-title":"A Case for Richer Cross-layer Abstractions: Bridging the Semantic Gap with Expressive Memory,\" in ISCA","author":"Vijaykumar N.","year":"2018","unstructured":"N. Vijaykumar, A. Jain, D. Majumdar, K. Hsieh, G. Pekhimenko, E. Ebrahimi, N. Hajinazar, P. B. Gibbons, and O. Mutlu, \"A Case for Richer Cross-layer Abstractions: Bridging the Semantic Gap with Expressive Memory,\" in ISCA, 2018."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"crossref","unstructured":"R. W. Vuduc and H.-J. Moon \"Fast Sparse Matrix-vector Multiplication by Exploiting Variable Block Structure \" in HPCC 2005.","DOI":"10.2172\/891708"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"e_1_3_2_1_88_1","volume-title":"On Improving the Performance of Sparse Matrix-Vector Multiplication,\" in HiPC","author":"White J. B.","year":"1997","unstructured":"J. B. White and P. Sadayappan, \"On Improving the Performance of Sparse Matrix-Vector Multiplication,\" in HiPC, 1997."},{"key":"e_1_3_2_1_89_1","volume-title":"Accelerating Sparse Matrix Computations via Data Compression,\" in ICS","author":"Willcock J.","year":"2006","unstructured":"J. Willcock and A. Lumsdaine, \"Accelerating Sparse Matrix Computations via Data Compression,\" in ICS, 2006."},{"key":"e_1_3_2_1_90_1","volume-title":"Optimization of Sparse Matrix-Vector Multiplication on Emerging Multicore Platforms,\" in SC","author":"Williams S.","year":"2007","unstructured":"S. Williams, L. Oliker, R. Vuduc, J. Shalf, K. Yelick, and J. Demmel, \"Optimization of Sparse Matrix-Vector Multiplication on Emerging Multicore Platforms,\" in SC, 2007."},{"key":"e_1_3_2_1_91_1","volume-title":"Efficient PageRank and SpMV Computation on AMD GPUs,\" in ICPP","author":"Wu T.","year":"2010","unstructured":"T. Wu, B. Wang, Y. Shan, F. Yan, Y. Wang, and N. Xu, \"Efficient PageRank and SpMV Computation on AMD GPUs,\" in ICPP, 2010."},{"key":"e_1_3_2_1_92_1","volume-title":"Model-driven Level 3 BLAS Performance Optimization on Loongson 3A processor,\" in ICPADS","author":"Xianyi Z.","year":"2012","unstructured":"Z. Xianyi, W. Qian, and Z. Yunquan, \"Model-driven Level 3 BLAS Performance Optimization on Loongson 3A processor,\" in ICPADS, 2012."},{"key":"e_1_3_2_1_93_1","volume-title":"yaSpMV: Yet Another SpMV Framework on GPUs,\" in PPoPP","author":"Yan S.","year":"2014","unstructured":"S. Yan, C. Li, Y. Zhang, and H. Zhou, \"yaSpMV: Yet Another SpMV Framework on GPUs,\" in PPoPP, 2014."},{"key":"e_1_3_2_1_94_1","volume-title":"Sparse Matrix Multiplication on CAM Based Accelerator,\" CoRR","author":"Yavits L.","year":"2017","unstructured":"L. Yavits and R. Ginosar, \"Sparse Matrix Multiplication on CAM Based Accelerator,\" CoRR, 2017."},{"key":"e_1_3_2_1_95_1","volume-title":"GraphP: Reducing Communication for PIM-based Graph Processing with Efficient Data Partition,\" in HPCA","author":"Zhang M.","year":"2018","unstructured":"M. Zhang, Y. Zhuo, C. Wang, M. Gao, Y. Wu, K. Chen, C. Kozyrakis, and X. Qian, \"GraphP: Reducing Communication for PIM-based Graph Processing with Efficient Data Partition,\" in HPCA, 2018."},{"key":"e_1_3_2_1_96_1","volume-title":"Cambricon-X: An Accelerator for Sparse Neural Networks,\" in MICRO","author":"Zhang S.","year":"2016","unstructured":"S. Zhang, Z. Du, L. Zhang, H. Lan, S. Liu, L. Li, Q. Guo, T. Chen, and Y. Chen, \"Cambricon-X: An Accelerator for Sparse Neural Networks,\" in MICRO, 2016."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"crossref","DOI":"10.2172\/1426119","volume-title":"Bridging the Gap between Deep Learning and Sparse Matrix Format Selection,\" in PPoPP","author":"Zhao Y.","year":"2018","unstructured":"Y. Zhao, J. Li, C. Liao, and X. Shen, \"Bridging the Gap between Deep Learning and Sparse Matrix Format Selection,\" in PPoPP, 2018."},{"key":"e_1_3_2_1_98_1","volume-title":"Cambricon-S: Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software\/Hardware Approach,\" in MICRO","author":"Zhou X.","year":"2018","unstructured":"X. Zhou, Z. Du, Q. Guo, S. Liu, C. Liu, C. Wang, X. Zhou, L. Li, T. Chen, and Y. Chen, \"Cambricon-S: Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software\/Hardware Approach,\" in MICRO, 2018."},{"key":"e_1_3_2_1_99_1","volume-title":"Accelerating Sparse Matrix-Matrix Multiplication with 3D-Stacked Logic-in-Memory Hardware,\" in HPEC","author":"Zhu Q.","year":"2013","unstructured":"Q. Zhu, T. Graf, H. E. Sumbul, L. Pileggi, and F. Franchetti, \"Accelerating Sparse Matrix-Matrix Multiplication with 3D-Stacked Logic-in-Memory Hardware,\" in HPEC, 2013."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"}],"event":{"name":"MICRO '52: The 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Columbus OH USA","acronym":"MICRO '52","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE CS"]},"container-title":["Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358286","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352460.3358286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T22:26:03Z","timestamp":1753827963000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358286"}},"subtitle":["Co-designing Software Compression and Hardware-Accelerated Indexing for Efficient Sparse Matrix Operations"],"short-title":[],"issued":{"date-parts":[[2019,10,12]]},"references-count":100,"alternative-id":["10.1145\/3352460.3358286","10.1145\/3352460"],"URL":"https:\/\/doi.org\/10.1145\/3352460.3358286","relation":{},"subject":[],"published":{"date-parts":[[2019,10,12]]},"assertion":[{"value":"2019-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}