{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:03:15Z","timestamp":1771923795473,"version":"3.50.1"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/cgo68049.2026.11395227","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:46:32Z","timestamp":1771879592000},"page":"670-682","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Low-Precision Approximation of Tensor Operators on GPUs: Enabling Greater Trade-Offs between Performance and Accuracy"],"prefix":"10.1109","author":[{"given":"Fan","family":"Luo","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Lab of Processors, Institute of Computing Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangli","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Lab of Processors, Institute of Computing Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Hao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Lab of Processors, Institute of Computing Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueying","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Feng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Lab of Processors, Institute of Computing Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Cui","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Lab of Processors, Institute of Computing Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingling","family":"Xue","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Computer Science and Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mixed precision training","volume-title":"International Conference on Learning Representations","author":"Micikevicius"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370335"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref6","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3652032.3657567"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3528416.3530231"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref11","article-title":"Smoothquant: accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. ICML\u201923","author":"Xiao"},{"key":"ref12","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref14","first-page":"30 318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Cutlass: Cuda template library for dense linear algebra at all levels and scales","year":"2018"},{"issue":"4","key":"ref16","first-page":"5","article-title":"8-bit inference with tensorrt","volume":"2","author":"Migacz","year":"2017","journal-title":"GPU technology conference"},{"key":"ref17","article-title":"Learning to optimize tensor programs","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Zheng"},{"key":"ref19","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3441830"},{"key":"ref22","article-title":"Llm.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, ser. NIPS \u201922","author":"Dettmers"},{"key":"ref23","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref24","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019"},{"key":"ref25","article-title":"Ganq: Gpu-adaptive non-uniform quantization for large language models","author":"Zhao","year":"2025"},{"key":"ref26","article-title":"Quip#: even better llm quantization with hadamard incoherence and lattice codebooks","volume-title":"Proceedings of the 41st International Conference on Machine Learning, ser. ICML\u201924","author":"Tseng"},{"issue":"24","key":"ref27","first-page":"8835","article-title":"Development of a stokes flow solver robust to large viscosity jumps using a schur complement approach with mixed precision arithmetic","volume-title":"Journal of Computational Physics","volume":"230","author":"Furuichi","year":"2011"},{"issue":"9","key":"ref28","first-page":"1517","article-title":"Solving lattice qcd systems of equations using mixed precision solvers on gpus","volume-title":"Computer Physics Communications","volume":"181","author":"Clark","year":"2010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2013.6645508"},{"issue":"2","key":"ref30","first-page":"374","article-title":"Spfp: Speed without compromise\u2014a mixed precision model for gpu accelerated molecular dynamics simulations","volume-title":"Computer Physics Communications","volume":"184","author":"Le Grand","year":"2013"},{"issue":"12","key":"ref31","first-page":"2526","article-title":"Accelerating scientific computations with mixed precision algorithms","volume-title":"Computer Physics Communications","volume":"180","author":"Baboulin","year":"2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1377596.1377597"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1731022.1731027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2006.57"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560545"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431554"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC55832.2022.9969373"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3084839"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2774288"},{"key":"ref40","first-page":"30 318","article-title":"Gpt3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Dettmers","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3008996"},{"issue":"1","key":"ref43","article-title":"Adaptive quantization for deep neural network","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Zhou"},{"key":"ref44","article-title":"Heterogeneous bitwidth binarization in convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Fromm","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref46","article-title":"Mixed precision quantization of convnets via differentiable neural architecture search","author":"Wu","year":"2018"},{"key":"ref47","article-title":"Towards learning of filter-level heterogeneous compression of convolutional neural networks","author":"Zur","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1993316.1993518"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.3233\/978-1-61499-843-3-297","article-title":"Implications of reduced-precision computations in HPC: Performance, energy and error","volume-title":"International Conference on Parallel Computing (ParCo)","author":"Cherubin"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.1998.655893"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.23919\/FMCAD.2017.8102236"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638484"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccps.2018.00028"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884850"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213862"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2014.6881424"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC50609.2020.00043"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20656-7_12"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330360"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00051"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3009837.3009846"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3316482.3326341"}],"event":{"name":"2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11395173\/11394837\/11395227.pdf?arnumber=11395227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:03:00Z","timestamp":1771920180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/cgo68049.2026.11395227","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}