{"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":1771955946029,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102465, U1811461"],"award-info":[{"award-number":["62102465, U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2016ZT06D211"],"award-info":[{"award-number":["2016ZT06D211"]}]},{"name":"the Guangdong Natural Science Foundation","award":["2018B030312002"],"award-info":[{"award-number":["2018B030312002"]}]},{"name":"the Major Program of Guangdong Basic and Applied Research","award":["2019B030302002"],"award-info":[{"award-number":["2019B030302002"]}]},{"name":"CCF-Baidu Open Fund","award":["CCF-BAIDU OF2021032"],"award-info":[{"award-number":["CCF-BAIDU OF2021032"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,17]]},"DOI":"10.1145\/3528416.3530231","type":"proceedings-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T02:16:59Z","timestamp":1651717019000},"page":"94-102","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["moTuner"],"prefix":"10.1145","author":[{"given":"Zewei","family":"Mo","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejia","family":"Lin","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[[2022,5,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. 2021. AMD Instinct\u2122 MI100 Accelerator. Retrieved 2022-01 from https:\/\/www.amd.com\/en\/products\/server-accelerators\/instinct-mi100."},{"key":"e_1_3_2_1_2_1","unstructured":"AMD. 2021. AMD rocBLAS Library. Retrieved 2022-01 from https:\/\/github.com\/ROCmSoftwarePlatform\/rocBLAS."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412380"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444943"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2254064.2254118"},{"key":"e_1_3_2_1_6_1","unstructured":"Cambricon. 2021. Cambricon MLU Accelerator. Retrieved 2022-01 from https:\/\/www.cambricon.com\/."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009837.3009846"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2535838.2535874"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3014426"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Synthesis of fixed-point programs. In Proceedings of the International Conference on Embedded Software","volume":"22","author":"Darulova Eva","year":"2013","unstructured":"Eva Darulova, Viktor Kuncak, et al. 2013. Synthesis of fixed-point programs. In Proceedings of the International Conference on Embedded Software. IEEE, 22:1--22:10.","journal-title":"IEEE"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/120864672"},{"key":"e_1_3_2_1_12_1","unstructured":"Amir Gholami Sehoon Kim et al. 2021. A Survey of Quantization Methods for Efficient Neural Network Inference. CoRR abs\/2103.13630."},{"key":"e_1_3_2_1_13_1","volume-title":"GPU-FPtuner: Mixed-precision Autotuning for Floating-point Applications on GPU. In 27th IEEE International Conference on High Performance Computing. IEEE, 294--304","author":"Gu Ruidong","year":"2020","unstructured":"Ruidong Gu and Michela Becchi. 2020. GPU-FPtuner: Mixed-precision Autotuning for Floating-point Applications on GPU. In 27th IEEE International Conference on High Performance Computing. IEEE, 294--304."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213862"},{"key":"e_1_3_2_1_15_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 770--778","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, et al. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 770--778."},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis","volume":"49","author":"Ichimura Tsuyoshi","year":"2018","unstructured":"Tsuyoshi Ichimura, Kohei Fujita, et al. 2018. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. IEEE \/ ACM, 49:1--49:11.","journal-title":"IEEE \/ ACM"},{"key":"e_1_3_2_1_17_1","unstructured":"ICL. 2021. The High Performance LINPACK for Accelerator Introspection (HPL-AI) benchmark. Retrieved 2022-01 from https:\/\/bitbucket.org\/icl\/hpl-ai\/src\/main\/."},{"key":"e_1_3_2_1_18_1","unstructured":"Intel. 2019. Introduction to Intel deep learning boost on second generation Intel Xeon scalable processors. Retrieved 2022-01 from https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/articles\/introduction-to-intel-deep-learning-boost-on-second-generation-intel-xeon-scalable.html."},{"key":"e_1_3_2_1_19_1","unstructured":"Intel. 2021. Intel MKL. Retrieved 2022-01 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/onemkl.html."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/PAAP.2012.38"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433707"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330360"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Ignacio Laguna Paul C. Wood et al. 2019. GPUMixer: Performance-Driven Floating-Point Tuning for GPU Scientific Applications. In High Performance Computing - 34th International Conference Proceedings Vol. 11501. Springer 227--246.","DOI":"10.1007\/978-3-030-20656-7_12"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.08.002"},{"key":"e_1_3_2_1_27_1","volume-title":"LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation. In 2nd IEEE \/ ACM International Symposium on Code Generation and Optimization. IEEE Computer Society, 75--88","author":"Lattner Chris","year":"2004","unstructured":"Chris Lattner and Vikram Adve. 2004. LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation. In 2nd IEEE \/ ACM International Symposium on Code Generation and Optimization. IEEE Computer Society, 75--88."},{"key":"e_1_3_2_1_28_1","volume-title":"Unleashing the Low-Precision Computation Potential of Tensor Cores on GPUs. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization. IEEE, 90--102","author":"Li Guangli","year":"2021","unstructured":"Guangli Li, Jingling Xue, et al. 2021. Unleashing the Low-Precision Computation Potential of Tensor Cores on GPUs. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization. IEEE, 90--102."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00051"},{"key":"e_1_3_2_1_31_1","unstructured":"netlib. 2021. HPL benchmark. Retrieved 2022-01 from https:\/\/www.netlib.org\/benchmark\/hpl\/."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tifs.2006.05.004"},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2008. cuBLAS Library. Retrieved 2022-01 from https:\/\/docs.nvidia.com\/cuda\/cublas\/."},{"key":"e_1_3_2_1_34_1","unstructured":"NVIDIA. 2021. NVIDIA A100 Tensor Core GPU. Retrieved 2022-01 from https:\/\/www.nvidia.com\/en-us\/data-center\/a100.html."},{"key":"e_1_3_2_1_35_1","unstructured":"Riken. 2021. Comprehensive software for ab initio quantum chemistry calculations of large and complicated molecular systems. Retrieved 2022-01 from https:\/\/www.r-ccs.riken.jp\/software_center\/software\/ntchem\/overview\/."},{"key":"e_1_3_2_1_36_1","first-page":"1","article-title":"Precimonious: Tuning Assistant for Floating-Point Precision. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","volume":"27","author":"Rubio-Gonz\u00e1lez Cindy","year":"2013","unstructured":"Cindy Rubio-Gonz\u00e1lez, Cuong Nguyen, et al. 2013. Precimonious: Tuning Assistant for Floating-Point Precision. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, 27:1--27:12.","journal-title":"Association for Computing Machinery"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884850"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1137\/0907058"},{"key":"e_1_3_2_1_39_1","volume-title":"DRQ: Dynamic Region-based Quantization for Deep Neural Network Acceleration. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture. IEEE, 1010--1021","author":"Song Zhuoran","year":"2020","unstructured":"Zhuoran Song, Bangqi Fu, et al. 2020. DRQ: Dynamic Region-based Quantization for Deep Neural Network Acceleration. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture. IEEE, 1010--1021."},{"key":"e_1_3_2_1_40_1","volume-title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization. CoRR abs\/2102.10462.","author":"Yang Huanrui","year":"2021","unstructured":"Huanrui Yang, Lin Duan, et al. 2021. BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization. CoRR abs\/2102.10462."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Zhang Zhaoyang","year":"2021","unstructured":"Zhaoyang Zhang, Wenqi Shao, et al. 2021. Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139. PMLR, 12546--12556."}],"event":{"name":"CF '22: 19th ACM International Conference on Computing Frontiers","location":"Turin Italy","acronym":"CF '22","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 19th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530231","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528416.3530231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:42Z","timestamp":1750186962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530231"}},"subtitle":["a compiler-based auto-tuning approach for mixed-precision operators"],"short-title":[],"issued":{"date-parts":[[2022,5,17]]},"references-count":41,"alternative-id":["10.1145\/3528416.3530231","10.1145\/3528416"],"URL":"https:\/\/doi.org\/10.1145\/3528416.3530231","relation":{},"subject":[],"published":{"date-parts":[[2022,5,17]]},"assertion":[{"value":"2022-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}