{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:38Z","timestamp":1750220858090,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T00:00:00Z","timestamp":1582329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Samsung Research Funding & Incubation Center","award":["SRFC-IT1901-03"],"award-info":[{"award-number":["SRFC-IT1901-03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,22]]},"DOI":"10.1145\/3368826.3377917","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T21:49:28Z","timestamp":1582321768000},"page":"280-292","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["PreScaler: an efficient system-aware precision scaling framework on heterogeneous systems"],"prefix":"10.1145","author":[{"given":"Seokwon","family":"Kang","sequence":"first","affiliation":[{"name":"Hanyang University, South Korea"}]},{"given":"Kyunghwan","family":"Choi","sequence":"additional","affiliation":[{"name":"Hanyang University, South Korea"}]},{"given":"Yongjun","family":"Park","sequence":"additional","affiliation":[{"name":"Hanyang University, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2020,2,22]]},"reference":[{"volume-title":"a C language family frontend for LLVM","year":"2007","key":"e_1_3_2_1_1_1","unstructured":"Clang. a C language family frontend for LLVM, 2007. http:\/\/clang.llvm.org ."},{"key":"e_1_3_2_1_2_1","volume-title":"Using code perforation to improve performance, reduce energy consumption, and respond to failures","author":"Anant A.","year":"2009","unstructured":"A. Anant, M. C. Rinard, S. Sidiroglou, S. Misailovic, and H. Ho\ufb00mann. Using code perforation to improve performance, reduce energy consumption, and respond to failures. 2009."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806620"},{"key":"e_1_3_2_1_4_1","volume-title":"Computer systems: a programmer\u2019s perspective","author":"Bryant R. E.","year":"2003","unstructured":"R. E. Bryant, O. David Richard, and O. David Richard. Computer systems: a programmer\u2019s perspective, volume 281. Prentice Hall Upper Saddle River, 2003."},{"key":"e_1_3_2_1_5_1","first-page":"376","volume-title":"2011 38th Annual international symposium on computer architecture (ISCA)","author":"Esmaeilzadeh H.","unstructured":"H. Esmaeilzadeh, E. Blem, R. S. Amant, K. Sankaralingam, and D. Burger. Dark silicon and the end of multicore scaling. In 2011 38th Annual international symposium on computer architecture (ISCA), pages 365\u2013376. IEEE, 2011."},{"key":"e_1_3_2_1_6_1","first-page":"460","volume-title":"Proceedings of the 2012 45th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Esmaeilzadeh H.","unstructured":"H. Esmaeilzadeh, A. Sampson, L. Ceze, and D. Burger. Neural acceleration for general-purpose approximate programs. In Proceedings of the 2012 45th Annual IEEE\/ACM International Symposium on Microarchitecture, pages 449\u2013460. IEEE Computer Society, 2012."},{"key":"e_1_3_2_1_7_1","volume-title":"Journal of Computational Science","author":"Graillat S.","year":"2019","unstructured":"S. Graillat, F. J\u00e9z\u00e9quel, R. Picot, F. F\u00e9votte, and B. Lathuili\u00e8re. Autotuning for \ufb02oating-point precision with discrete stochastic arithmetic. Journal of Computational Science, 2019."},{"key":"e_1_3_2_1_8_1","volume-title":"IEEE","author":"Hong S.","year":"2018","unstructured":"S. Hong, I. Lee, and Y. Park. Nn compactor: Minimizing memory and logic resources for small neural networks. In 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 581\u2013584. IEEE, 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"Intel xeon e5-2600 model speci\ufb01cation","author":"INTEL.","year":"2016","unstructured":"INTEL. Intel xeon e5-2600 model speci\ufb01cation, 2016. https:\/\/www.intel.com\/content\/www\/us\/en\/processors\/xeon xeon-e5-brief.html ."},{"key":"e_1_3_2_1_10_1","volume-title":"Intel gold 5115 model speci\ufb01cation","author":"INTEL.","year":"2017","unstructured":"INTEL. Intel gold 5115 model speci\ufb01cation, 2017. https:\/\/ark.intel.com\/content\/www\/kr\/ko\/ark\/products\/120484 intel-xeon-gold-5115-processor-13-75m-cache-2-40-ghz.html ."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317833"},{"key":"e_1_3_2_1_12_1","volume-title":"OpenCL - the open standard for parallel programming of heterogeneous systems","author":"KHRONOS Group","year":"2010","unstructured":"KHRONOS Group. OpenCL - the open standard for parallel programming of heterogeneous systems, 2010. http:\/\/www.khronos.org."},{"key":"e_1_3_2_1_13_1","first-page":"246","volume-title":"International Conference on High Performance Computing","author":"Laguna I.","unstructured":"I. Laguna, P. C. Wood, R. Singh, and S. Bagchi. Gpumixer: Performance-driven \ufb02oating-point tuning for gpu scienti\ufb01c applications. In International Conference on High Performance Computing, pages 227\u2013246. Springer, 2019."},{"key":"e_1_3_2_1_14_1","first-page":"378","volume-title":"Proceedings of the 27th international ACM conference on International conference on supercomputing","author":"Lam M. O.","unstructured":"M. O. Lam, J. K. Hollingsworth, B. R. de Supinski, and M. P. LeGendre. Automatically adapting programs for mixed-precision \ufb02oating-point computation. In Proceedings of the 27th international ACM conference on International conference on supercomputing, pages 369\u2013378. ACM, 2013."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908087"},{"key":"e_1_3_2_1_17_1","first-page":"365","volume-title":"2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA)","author":"Lustig D.","unstructured":"D. Lustig and M. Martonosi. Reducing gpu o\ufb04oad latency via \ufb01ne-grained cpu-gpu synchronization. In 2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA), pages 354\u2013365. IEEE, 2013."},{"issue":"4","key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2893356","article-title":"A survey of techniques for approximate computing","volume":"48","author":"Mittal S.","year":"2016","unstructured":"S. Mittal. A survey of techniques for approximate computing. ACM Comput. Surv., 48(4):62:1\u201362:33, Mar. 2016.","journal-title":"ACM Comput. Surv."},{"key":"e_1_3_2_1_19_1","first-page":"614","volume-title":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)","author":"Moreau T.","unstructured":"T. Moreau, M. Wyse, J. Nelson, A. Sampson, H. Esmaeilzadeh, L. Ceze, and M. Oskin. Snnap: Approximate computing on programmable socs via neural acceleration. In 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), pages 603\u2013614. IEEE, 2015."},{"key":"e_1_3_2_1_20_1","volume-title":"Pro\ufb01le-driven automated mixed precision. arXiv preprint arXiv:1606.00251","author":"Nathan R.","year":"2016","unstructured":"R. Nathan, H. Naeimi, D. J. Sorin, and X. Sun. Pro\ufb01le-driven automated mixed precision. arXiv preprint arXiv:1606.00251, 2016."},{"key":"e_1_3_2_1_21_1","volume-title":"Microprocessor Forum","author":"Nickolls J.","year":"2007","unstructured":"J. Nickolls et al. NVIDIA CUDA software and GPU parallel computing architecture. In Microprocessor Forum, May 2007."},{"key":"e_1_3_2_1_22_1","volume-title":"NVIDIA Tesla P100","author":"NVIDIA.","year":"2016","unstructured":"NVIDIA. NVIDIA Tesla P100, 2016. https:\/\/https:\/\/images.nvidia.com\/content\/pdf\/tesla\/ whitepaper\/pascal-architecture-whitepaper.pdf ."},{"key":"e_1_3_2_1_23_1","volume-title":"NVIDIA DGX Station","author":"NVIDIA.","year":"2017","unstructured":"NVIDIA. NVIDIA DGX Station, 2017. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/ dgx-station\/nvidia-dgx-station-datasheet.pdf ."},{"key":"e_1_3_2_1_24_1","volume-title":"NVIDIA Tesla V100","author":"NVIDIA.","year":"2017","unstructured":"NVIDIA. NVIDIA Tesla V100, 2017. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/ volta-architecture-whitepaper.pdf ."},{"key":"e_1_3_2_1_25_1","volume-title":"NVIDIA Titan Xp Graphics Cards","author":"NVIDIA.","year":"2017","unstructured":"NVIDIA. NVIDIA Titan Xp Graphics Cards, 2017. https:\/\/www.nvidia.com\/en-us\/titan\/titan-xp\/ ."},{"key":"e_1_3_2_1_26_1","volume-title":"Nvidia Graphic Driver","author":"NVIDIA.","year":"2018","unstructured":"NVIDIA. Nvidia Graphic Driver, 2018. Available at https:\/\/www.nvidia.com\/Download\/index.aspx ."},{"key":"e_1_3_2_1_27_1","volume-title":"NVIDIA RTX 2080 Ti Graphics Cards, 2018","author":"NVIDIA.","year":"2080","unstructured":"NVIDIA. NVIDIA RTX 2080 Ti Graphics Cards, 2018. https:\/\/www.nvidia.com\/en-us\/geforce\/graphics-cards\/rtx-2080-ti\/ ."},{"key":"e_1_3_2_1_28_1","volume-title":"Nvidia Container Toolkit. build and run docker containers leveraging nvidia gpus","author":"NVIDIA.","year":"2019","unstructured":"NVIDIA. Nvidia Container Toolkit. build and run docker containers leveraging nvidia gpus, 2019. Available at https:\/\/github.com\/NVIDIA\/nvidia-docker ."},{"key":"e_1_3_2_1_29_1","volume-title":"Throughput of native arithmetic instructions","author":"NVIDIA.","year":"2019","unstructured":"NVIDIA. Throughput of native arithmetic instructions, 2019. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/ ."},{"key":"e_1_3_2_1_30_1","first-page":"757","volume-title":"Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering","author":"Park J.","unstructured":"J. Park, H. Esmaeilzadeh, X. Zhang, M. Naik, and W. Harris. Flexjava: Language support for safe and modular approximate programming. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, pages 745\u2013757. ACM, 2015."},{"volume-title":"the polyhedral benchmark suite","year":"2011","key":"e_1_3_2_1_31_1","unstructured":"Polybench. the polyhedral benchmark suite, 2011. http:\/\/www.cse.ohio-state.edu\/ pouchet\/software\/polybench."},{"key":"e_1_3_2_1_32_1","unstructured":"C. Rau. Ieee 754-based half-precision \ufb02oating-point library 2017. http:\/\/half.sourceforge.net ."},{"key":"e_1_3_2_1_33_1","first-page":"12","volume-title":"SC\u201913: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Rubio-Gonz\u00e1lez C.","unstructured":"C. Rubio-Gonz\u00e1lez, C. Nguyen, H. D. Nguyen, J. Demmel, W. Kahan, K. Sen, D. H. Bailey, C. Iancu, and D. Hough. Precimonious: Tuning assistant for \ufb02oating-point precision. In SC\u201913: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pages 1\u201312. IEEE, 2013."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541948"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540711"},{"key":"e_1_3_2_1_38_1","first-page":"174","volume-title":"ACM SIGPLAN Notices","author":"Sampson A.","unstructured":"A. Sampson, W. Dietl, E. Fortuna, D. Gnanapragasam, L. Ceze, and D. Grossman. Enerj: Approximate data types for safe and general low-power computation. In ACM SIGPLAN Notices, volume 46, pages 164\u2013174. ACM, 2011."},{"key":"e_1_3_2_1_39_1","first-page":"342","volume-title":"Proceedings of the 25th edition on Great Lakes Symposium on VLSI","author":"Tian Y.","unstructured":"Y. Tian, Q. Zhang, T. Wang, F. Yuan, and Q. Xu. Approxma: Approximate memory access for dynamic precision scaling. In Proceedings of the 25th edition on Great Lakes Symposium on VLSI, pages 337\u2013342. ACM, 2015."},{"key":"e_1_3_2_1_40_1","first-page":"32","volume-title":"Proceedings of the 2014 international symposium on Low power electronics and design","author":"Venkataramani S.","unstructured":"S. Venkataramani, A. Ranjan, K. Roy, and A. Raghunathan. Axnn: energy-e\ufb03cient neuromorphic systems using approximate computing. In Proceedings of the 2014 international symposium on Low power electronics and design, pages 27\u201332. ACM, 2014."},{"key":"e_1_3_2_1_41_1","first-page":"706","volume-title":"Proceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition","author":"Zhang Q.","unstructured":"Q. Zhang, T. Wang, Y. Tian, F. Yuan, and Q. Xu. Approxann: An approximate computing framework for arti\ufb01cial neural network. In Proceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition, pages 701\u2013706. EDA Consortium, 2015."}],"event":{"name":"CGO '20: 18th ACM\/IEEE International Symposium on Code Generation and Optimization","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"],"location":"San Diego CA USA","acronym":"CGO '20"},"container-title":["Proceedings of the 18th ACM\/IEEE International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368826.3377917","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3368826.3377917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:28Z","timestamp":1750202608000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3368826.3377917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,22]]},"references-count":40,"alternative-id":["10.1145\/3368826.3377917","10.1145\/3368826"],"URL":"https:\/\/doi.org\/10.1145\/3368826.3377917","relation":{},"subject":[],"published":{"date-parts":[[2020,2,22]]},"assertion":[{"value":"2020-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}