{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:59:06Z","timestamp":1771955946925,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"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":[[2024,6,20]]},"DOI":"10.1145\/3652032.3657567","type":"proceedings-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:00:08Z","timestamp":1718902808000},"page":"34-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["MixPert: Optimizing Mixed-Precision Floating-Point Emulation on GPU Integer Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7205-4062","authenticated-orcid":false,"given":"Zejia","family":"Lin","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4686-4493","authenticated-orcid":false,"given":"Aoyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3507-4299","authenticated-orcid":false,"given":"Xianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-3375","authenticated-orcid":false,"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEESTD.2019.8766229"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420211003313"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009837.3009846"},{"key":"e_1_3_2_1_4_1","unstructured":"GNU Compiler Collections. 2022. Soft float library routines. https:\/\/gcc.gnu.org\/onlinedocs\/gccint\/Soft-float-library-routines.html"},{"key":"e_1_3_2_1_5_1","unstructured":"AMD Corporation. 2023. Amd cnda 3 architecture. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf"},{"key":"e_1_3_2_1_6_1","unstructured":"Nvidia Corporation. 2014. Cuda basic linear algebra subroutine library (cublas). https:\/\/docs.nvidia.com\/cuda\/cublas\/index.html"},{"key":"e_1_3_2_1_7_1","unstructured":"Nvidia Corporation. 2018. Cuda templates for linear algebra subroutines (cutlass). https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"e_1_3_2_1_8_1","unstructured":"Nvidia Corporation. 2021. Nvidia A100 tensor core GPU architecture. https:\/\/resources.nvidia.com\/en-us-genomics-ep\/ampere-architecture-white-paper"},{"key":"e_1_3_2_1_9_1","unstructured":"Nvidia Corporation. 2021. Nvidia ampere ga102 gpu architecture. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.1.pdf"},{"key":"e_1_3_2_1_10_1","unstructured":"Nvidia Corporation. 2022. Nvidia H100 tensor core GPU architecture. https:\/\/resources.nvidia.com\/en-us-tensor-core\/gtc22-whitepaper-hopper"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377912"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.211631"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995923"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_15_1","unstructured":"Liwen Fan Ruixin Wang Kuan Fang and Xian Sun. 2019. Cubert. https:\/\/github.com\/zhihu\/cuBERT"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585515"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441599"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1236463.1236468"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5654017"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HIPC50609.2020.00043"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213862"},{"key":"e_1_3_2_1_22_1","unstructured":"Manish Gupta. 2022. FP32 emulation via tensor core instruction. https:\/\/github.com\/NVIDIA\/cutlass\/tree\/main\/examples\/27_ampere_3xtf32_fast_accurate_tensorop_gemm"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"e_1_3_2_1_24_1","unstructured":"John Hauser. 2016 (Retrieved 2024.1). Berkeley softfloat. http:\/\/www.jhauser.us\/arithmetic\/SoftFloat.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441830"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/PAAP.2012.38"},{"key":"e_1_3_2_1_27_1","unstructured":"Wayne Joubert. 2019. Sparkler. https:\/\/github.com\/wdj\/sparkler"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.PARCO.2019.02.003"},{"key":"e_1_3_2_1_29_1","unstructured":"Konstantinos Kallas. 2017. Gpus-kmeans. https:\/\/github.com\/angelhof\/gpus-kmeans"},{"key":"e_1_3_2_1_30_1","unstructured":"Innovative Computing Laboratory. 2019. The High Performance LINPACK for Accelerator Introspection (HPL-AI) benchmark. https:\/\/bitbucket.org\/icl\/hpl-ai\/src\/main"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20656-7_12"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370335"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00083"},{"key":"e_1_3_2_1_35_1","unstructured":"Zixuan Ma. 2022. A GPU FP32 computation method with Tensor Cores. https:\/\/github.com\/JohndeVostok\/APE"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532377"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291656.3291720"},{"key":"e_1_3_2_1_39_1","volume-title":"6th International Conference on Learning Representations","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory F. Diamos, Erich Elsen, David Garc\u00eda, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed precision training. In 6th International Conference on Learning Representations, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05814-y"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(91)90023-5"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Hiryuki Ootomo Hidetaka Manabe Kenji Harada and Rio Yokota. 2023. Quantum circuit simulation by\u00a0sdgemm emulation on\u00a0tensor cores and\u00a0automatic precision selection. In High Performance Computing Abhinav Bhatele Jeff Hammond Marc Baboulin and Carola Kruse (Eds.). Springer Nature Switzerland 259\u2013276. isbn:978-3-031-32041-5","DOI":"10.1007\/978-3-031-32041-5_14"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Hiroyuki Ootomo Katsuhisa Ozaki and Rio Yokota. 2024. DGEMM on Integer Matrix Multiplication Unit. arxiv:2306.11975.","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/14063.14074"},{"key":"e_1_3_2_1_46_1","unstructured":"Huawei Technologies. 2023. HUAWEI Ascend AI Chipsets. https:\/\/www.hisilicon.com\/en\/products\/Ascend"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Pedro Valero-Lara Ian Jorquera Frank Lui and Jeffrey Vetter. 2023. Mixed-Precision S\/DGEMM Using the TF32 and TF64 Frameworks on Low-Precision AI Tensor Cores. ACM 179\u2013186. https:\/\/doi.org\/10.1145\/3624062.3624084 10.1145\/3624062.3624084","DOI":"10.1145\/3624062.3624084"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508408"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623338"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638484"}],"event":{"name":"LCTES '24: 25th ACM SIGPLAN\/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","location":"Copenhagen Denmark","acronym":"LCTES '24","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 25th ACM SIGPLAN\/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652032.3657567","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652032.3657567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:12Z","timestamp":1750291392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652032.3657567"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":50,"alternative-id":["10.1145\/3652032.3657567","10.1145\/3652032"],"URL":"https:\/\/doi.org\/10.1145\/3652032.3657567","relation":{},"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"2024-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}