{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T11:04:37Z","timestamp":1784718277424,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T00:00:00Z","timestamp":1785024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2402542"],"award-info":[{"award-number":["OAC-2402542"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2139536"],"award-info":[{"award-number":["OAC-2139536"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,26]]},"DOI":"10.1145\/3785462.3815862","type":"proceedings-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:41:43Z","timestamp":1784716903000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3486-7863","authenticated-orcid":false,"given":"Hang","family":"Liu","sequence":"first","affiliation":[{"name":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1051-5927","authenticated-orcid":false,"given":"Junjie","family":"Li","sequence":"additional","affiliation":[{"name":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8505-0223","authenticated-orcid":false,"given":"Yinzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7281-3268","authenticated-orcid":false,"given":"Niraj","family":"Nepal","sequence":"additional","affiliation":[{"name":"Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9837-5796","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,26]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Ahmad Abdelfattah Hartwig Anzt Erik\u00a0G Boman Erin Carson Terry Cojean Jack Dongarra Alyson Fox Mark Gates Nicholas\u00a0J Higham Xiaoye\u00a0S Li Jennifer Loe Piotr Luszczek Srikara Pranesh Siva Rajamanickam Tobias Ribizel Barry\u00a0F Smith Kasia Swirydowicz Stephen Thomas Stanimire Tomov Yaohung\u00a0M Tsai and Ulrike\u00a0Meier Yang. 2021. A survey of numerical linear algebra methods utilizing mixed-precision arithmetic. The International Journal of High Performance Computing Applications 35 4 (July 2021) 344\u2013369. 10.1177\/10943420211003313Publisher: SAGE Publications Ltd STM.","DOI":"10.1177\/10943420211003313"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654125"},{"key":"e_1_3_3_1_4_2","volume-title":"HPE Cray Programming Environment documentation","author":"Enterprise Hewlett Packard","year":"2024","unstructured":"Hewlett Packard Enterprise. 2024. HPE Cray Programming Environment documentation. HPE Cray. https:\/\/h41374.www4.hpe.com\/docs\/csml\/cray_libsci_acc.html"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2001.930115"},{"key":"e_1_3_3_1_6_2","unstructured":"Hiroyuki Ootomo and Piotr Luszczek. 2024. ozIMMU. Retrieved March 16 2025 from https:\/\/github.com\/enp1s0\/ozIMMU"},{"key":"e_1_3_3_1_7_2","volume-title":"IBM Engineering and Scientific Subroutine Library for Linux on POWER","year":"2018","unstructured":"IBM. 2018. IBM Engineering and Scientific Subroutine Library for Linux on POWER. IBM. https:\/\/www.ibm.com\/docs\/en\/SSFHY8_6.1\/reference\/essl_reference_pdf.pdf"},{"key":"e_1_3_3_1_8_2","unstructured":"Junjie Li. 2025. Performant Automatic BLAS Offloading on Unified Memory Architecture with OpenMP First-Touch Style Data Movement. arxiv:https:\/\/arXiv.org\/abs\/2501.00279\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2501.00279"},{"key":"e_1_3_3_1_9_2","volume-title":"SCILIB-accel: automatic BLAS offload tool","author":"Li Junjie","year":"2024","unstructured":"Junjie Li and Yinzhi Wang. 2024. SCILIB-accel: automatic BLAS offload tool. GitHub. https:\/\/github.com\/nicejunjie\/scilib-accel"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626203.3670561"},{"key":"e_1_3_3_1_11_2","unstructured":"Hang Liu Junjie Li and Yinzhi Wang. 2025. A Pilot Study on Tunable Precision Emulation via Automatic BLAS Offloading. arxiv:https:\/\/arXiv.org\/abs\/2503.22875\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2503.22875"},{"key":"e_1_3_3_1_12_2","unstructured":"MuST Developers. 2026. Multiple Scattering Theory code for first principles calculations. Retrieved March 16 2026 from https:\/\/github.com\/mstsuite\/MuST"},{"key":"e_1_3_3_1_13_2","volume-title":"NVBLAS documentation","year":"2024","unstructured":"NVIDIA. 2024. NVBLAS documentation. NVIDIA. https:\/\/docs.nvidia.com\/cuda\/nvblas"},{"key":"e_1_3_3_1_14_2","unstructured":"NVIDIA. 2025. NVIDIA cuBLAS. https:\/\/docs.nvidia.com\/cuda\/cublas\/#floating-point-emulation. Accessed: 2026-03-27."},{"key":"e_1_3_3_1_15_2","unstructured":"NVIDIA Corporation. 2026. NVIDIA HGX Platform. https:\/\/www.nvidia.com\/en-us\/data-center\/hgx\/ Accessed: 2026-03-29."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Hiroyuki Ootomo Katsuhisa Ozaki and Rio Yokota. 2024. DGEMM on integer matrix multiplication unit. The International Journal of High Performance Computing Applications 38 4 (July 2024) 297\u2013313. 10.1177\/10943420241239588Publisher: SAGE Publications Ltd STM.","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_3_1_17_2","unstructured":"Heidi Poxon. 2013. Introduction to the Cray Accelerated Scientific Libraries. (2013). https:\/\/www.olcf.ornl.gov\/wp-content\/uploads\/2013\/01\/Scientific_Libs.pdf"},{"key":"e_1_3_3_1_18_2","unstructured":"Yuki Uchino Qianxiang Ma Toshiyuki Imamura Katsuhisa Ozaki and Patrick\u00a0Lars Gutsche. 2025. Emulation of Complex Matrix Multiplication based on the Chinese Remainder Theorem. arxiv:https:\/\/arXiv.org\/abs\/2512.08321\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2512.08321"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Yuki Uchino Katsuhisa Ozaki and Toshiyuki Imamura. 2025. Performance enhancement of the Ozaki Scheme on integer matrix multiplication unit. The International Journal of High Performance Computing Applications 39 3 (2025) 462\u2013476. 10.1177\/10943420241313064","DOI":"10.1177\/10943420241313064"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.5555\/509058.509129"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624143"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Yang Wang G.\u00a0M. Stocks W.\u00a0A. Shelton D.\u00a0M.\u00a0C. Nicholson Z. Szotek and W.\u00a0M. Temmerman. 1995. Order-N Multiple Scattering Approach to Electronic Structure Calculations. Phys. Rev. Lett. 75 (Oct 1995) 2867\u20132870. Issue 15. 10.1103\/PhysRevLett.75.2867","DOI":"10.1103\/PhysRevLett.75.2867"},{"key":"e_1_3_3_1_23_2","unstructured":"Yuki Uchino. 2024. ozIMMU-H. Retrieved March 16 2025 from https:\/\/github.com\/RIKEN-RCCS\/accelerator_for_ozIMMU"},{"key":"e_1_3_3_1_24_2","unstructured":"Yuki Uchino Emil Briggs. 2026. GEMMul8. Retrieved March 16 2026 from https:\/\/github.com\/RIKEN-RCCS\/GEMMul8"}],"event":{"name":"PEARC '26: Practice and Experience in Advanced Research Computing","location":"Minneapolis MN USA","acronym":"PEARC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3785462.3815862","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:41:50Z","timestamp":1784716910000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785462.3815862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,26]]},"references-count":23,"alternative-id":["10.1145\/3785462.3815862","10.1145\/3785462"],"URL":"https:\/\/doi.org\/10.1145\/3785462.3815862","relation":{},"subject":[],"published":{"date-parts":[[2026,7,26]]},"assertion":[{"value":"2026-07-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}