{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:37:42Z","timestamp":1783035462256,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. National Science Foundation","award":["2216903,2217154,2009007,2339521,2517201,2513656"],"award-info":[{"award-number":["2216903,2217154,2009007,2339521,2517201,2513656"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759841","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"617-630","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FaSTCC: Fast Sparse Tensor Contractions on CPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3294-1481","authenticated-orcid":false,"given":"Saurabh","family":"Raje","sequence":"first","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4233-9796","authenticated-orcid":false,"given":"Hunter","family":"McCoy","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4556-4937","authenticated-orcid":false,"given":"Atanas","family":"Rountev","sequence":"additional","affiliation":[{"name":"Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-0320","authenticated-orcid":false,"given":"Prashant","family":"Pandey","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4737-2034","authenticated-orcid":false,"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Edoardo Apr\u00e0\u00a0et al.2020. NWChem: Past present and future. The Journal of Chemical Physics 152 18 (May 2020). 10.1063\/5.0004997","DOI":"10.1063\/5.0004997"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Aart J.\u00a0C. Bik Peter J.\u00a0H. Brinkhaus Peter M.\u00a0W. Knijnenburg and Harry A.\u00a0G. Wijshoff. 1998. The automatic generation of sparse primitives. ACM Trans. Math. Softw. 24 2 (June 1998) 190\u2013225. 10.1145\/290200.287636","DOI":"10.1145\/290200.287636"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Jiri Brabec Jakub Lang Masaaki Saitow Ji\u0159\u00ed Pittner Frank Neese and Ond\u0159ej Demel. 2018. Domain-Based Local Pair Natural Orbital Version of Mukherjee\u2019s State-Specific Coupled Cluster Method. Journal of Chemical Theory and Computation 14 3 (2018) 1370\u20131382. 10.1021\/acs.jctc.7b01184 arXiv:https:\/\/doi.org\/10.1021\/acs.jctc.7b01184 PMID: 29345924.","DOI":"10.1021\/acs.jctc.7b01184"},{"key":"e_1_3_3_3_5_2","unstructured":"Aydin Bulu\u00e7. 2010. Linear algebraic primitives for parallel computing on large graphs. Ph.\u00a0D. Dissertation. USA. Advisor(s) Gilbert John R. AAI3398781."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps.2011.73"},{"key":"e_1_3_3_3_7_2","unstructured":"Justus\u00a0A. Calvin and Edward\u00a0F. Valeev. 2015. Task-Based Algorithm for Matrix Multiplication: A Step Towards Block-Sparse Tensor Computing. arxiv:https:\/\/arXiv.org\/abs\/1504.05046\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/1504.05046"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532386"},{"key":"e_1_3_3_3_9_2","unstructured":"Andrew Ensinger Gabriel Kulp Victor Agostinelli Dennis Lyakhov and Lizhong Chen. 2024. Swift: High-Performance Sparse Tensor Contraction for Scientific Applications. arxiv:https:\/\/arXiv.org\/abs\/2410.10094\u00a0[cs.DS] https:\/\/arxiv.org\/abs\/2410.10094"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638500"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Matthew Fishman Steven\u00a0R. White and E.\u00a0Miles Stoudenmire. 2022. The ITensor Software Library for Tensor Network Calculations. SciPost Phys. Codebases (2022) 4. 10.21468\/SciPostPhysCodeb.4","DOI":"10.21468\/SciPostPhysCodeb.4"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"E.\u00a0Schuyler Fried Nicolas P.\u00a0D. Sawaya Yudong Cao Ian\u00a0D. Kivlichan Jhonathan Romero and Al\u00e1n Aspuru-Guzik. 2018. qTorch: The quantum tensor contraction handler. PLOS ONE 13 12 (Dec. 2018) e0208510. 10.1371\/journal.pone.0208510","DOI":"10.1371\/journal.pone.0208510"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Fred\u00a0G Gustavson. 1978. Two fast algorithms for sparse matrices: Multiplication and permuted transposition. ACM Transactions on Mathematical Software (TOMS) 4 3 (1978) 250\u2013269.","DOI":"10.1145\/355791.355796"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"So Hirata. 2003. Tensor Contraction Engine: Abstraction and Automated Parallel Implementation of Configuration-Interaction Coupled-Cluster and Many-Body Perturbation Theories. The Journal of Physical Chemistry A 107 46 (2003) 9887\u20139897. 10.1021\/jp034596z arXiv:https:\/\/doi.org\/10.1021\/jp034596z","DOI":"10.1021\/jp034596z"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Rong Hu Haotian Wang Wangdong Yang Renqiu Ouyang Keqin Li and Kenli Li. 2024. BCB-SpTC: An Efficient Sparse High-Dimensional Tensor Contraction Employing Tensor Core Acceleration. IEEE Transactions on Parallel and Distributed Systems PP (12 2024) 1\u201315. 10.1109\/TPDS.2024.3477746","DOI":"10.1109\/TPDS.2024.3477746"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Tsung-Wei Huang Dian-Lun Lin Chun-Xun Lin and Yibo Lin. 2022. Taskflow: A Lightweight Parallel and Heterogeneous Task Graph Computing System. IEEE Trans. Parallel Distrib. Syst. 33 6 (June 2022) 1303\u20131320. 10.1109\/TPDS.2021.3104255","DOI":"10.1109\/TPDS.2021.3104255"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Khaled Ibrahim Samuel Williams and Evgeny Epifanovsky. 2015. Analysis and tuning of libtensor framework on multicore architectures. 2014 21st International Conference on High Performance Computing HiPC 2014 (06 2015). 10.1109\/HiPC.2014.7116881","DOI":"10.1109\/HiPC.2014.7116881"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659985"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661182"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Fredrik Kjolstad Shoaib Kamil Stephen Chou David Lugato and Saman Amarasinghe. 2017. The tensor algebra compiler. Proc. ACM on Programming Languages 1 OOPSLA Article 77 (Oct. 2017) 29\u00a0pages. 10.1145\/3133901","DOI":"10.1145\/3133901"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Christoph K\u00f6ppl and Hans-Joachim Werner. 2016. Parallel and Low-Order Scaling Implementation of Hartree\u2013Fock Exchange Using Local Density Fitting. Journal of Chemical Theory and Computation 12 7 (2016) 3122\u20133134. 10.1021\/acs.jctc.6b00251 arXiv:https:\/\/doi.org\/10.1021\/acs.jctc.6b00251 PMID: 27267488.","DOI":"10.1021\/acs.jctc.6b00251"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460355"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441581"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404413"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Devin\u00a0A Matthews. 2018. High-performance tensor contraction without transposition. SIAM Journal on Scientific Computing 40 1 (2018) C1\u2013C24.","DOI":"10.1137\/16M108968X"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Erdal Mutlu Ajay Panyala Nitin Gawande Abhishek Bagusetty Jeffrey Glabe Jinsung Kim Karol Kowalski Nicholas\u00a0P. Bauman Bo Peng Himadri Pathak Jiri Brabec and Sriram Krishnamoorthy. 2023. TAMM: Tensor algebra for many-body methods. The Journal of Chemical Physics 159 2 (07 2023) 024801. 10.1063\/5.0142433","DOI":"10.1063\/5.0142433"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95953-1_7"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps49936.2021.00016"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"e_1_3_3_3_30_2","unstructured":"Nvidia. 2020. cuTENSOR: A high-performance CUDA library for tensor primitives. https:\/\/docs.nvidia.com\/cuda\/cutensor\/index.html."},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Peter Pinski Christoph Riplinger Edward\u00a0F Valeev and Frank Neese. 2015. Sparse maps\u2014A systematic infrastructure for reduced-scaling electronic structure methods. I. An efficient and simple linear scaling local MP2 method that uses an intermediate basis of pair natural orbitals. The Journal of chemical physics 143 3 (2015).","DOI":"10.1063\/1.4926879"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.16930011"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Saurabh Raje Yufan Xu Atanas Rountev Edward\u00a0F. Valeev and P. Sadayappan. 2024. CoNST: Code Generator for Sparse Tensor Networks. ACM Trans. Archit. Code Optim. 21 4 Article 82 (Nov. 2024) 24\u00a0pages. 10.1145\/3689342","DOI":"10.1145\/3689342"},{"key":"e_1_3_3_3_34_2","volume-title":"Efficient parallel sparse tensor contraction","author":"Singh Somesh","year":"2024","unstructured":"Somesh Singh and Bora U\u00e7ar. 2024. Efficient parallel sparse tensor contraction. Technical Report RR-9551. Inria Lyon. https:\/\/hal.science\/hal-04659658"},{"key":"e_1_3_3_3_35_2","volume-title":"FROSTT: The Formidable Repository of Open Sparse Tensors and Tools","author":"Smith Shaden","year":"2017","unstructured":"Shaden Smith, Jee\u00a0W. Choi, Jiajia Li, Richard Vuduc, Jongsoo Park, Xing Liu, and George Karypis. 2017. FROSTT: The Formidable Repository of Open Sparse Tensors and Tools. http:\/\/frostt.io\/"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.27"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","unstructured":"Edgar Solomonik Devin Matthews Jeff\u00a0R. Hammond John\u00a0F. Stanton and James Demmel. 2014. A massively parallel tensor contraction framework for coupled-cluster computations. J. Parallel and Distrib. Comput. 74 12 (2014) 3176\u20133190. 10.1016\/j.jpdc.2014.06.002Domain-Specific Languages and High-Level Frameworks for High-Performance Computing.","DOI":"10.1016\/j.jpdc.2014.06.002"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Paul Springer and Paolo Bientinesi. 2018. Design of a high-performance GEMM-like tensor\u2013tensor multiplication. ACM Transactions on Mathematical Software (TOMS) 44 3 (2018) 1\u201329.","DOI":"10.1145\/3157733"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/micro50266.2020.00068"},{"key":"e_1_3_3_3_40_2","unstructured":"TACO [n. d.]. TACO: The Tensor Algebra Compiler. http:\/\/tensor-compiler.org\/"},{"key":"e_1_3_3_3_41_2","volume-title":"Sparse Matrices","author":"Tewarson R.P.","year":"1973","unstructured":"R.P. Tewarson. 1973. Sparse Matrices. Academic Press. https:\/\/books.google.com\/books?id=I-FQAAAAMAAJ"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/LLVMHPC54804.2021.00009"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Xinliang Wang Weifeng Liu Wei Xue and Li Wu. 2018. swSpTRSV: a fast sparse triangular solve with sparse level tile layout on sunway architectures. ACM SIGPLAN Notices 53 1 (Feb. 2018) 338\u2013353. 10.1145\/3200691.3178513","DOI":"10.1145\/3200691.3178513"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446702"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","unstructured":"Tuowen Zhao Tobi Popoola Mary Hall Catherine Olschanowsky and Michelle Strout. 2022. Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration. ACM Trans. Archit. Code Optim. 20 1 Article 16 (Dec. 2022) 26\u00a0pages. 10.1145\/3566054","DOI":"10.1145\/3566054"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3712285.3759841","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759841","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:34:15Z","timestamp":1773254055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":44,"alternative-id":["10.1145\/3712285.3759841","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759841","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}