{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:20:26Z","timestamp":1773886826176,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/hpec.2017.8091072","type":"proceedings-article","created":{"date-parts":[[2017,11,3]],"date-time":"2017-11-03T03:45:54Z","timestamp":1509680754000},"page":"1-7","source":"Crossref","is-referenced-by-count":53,"title":["Exploiting half precision arithmetic in Nvidia GPUs"],"prefix":"10.1109","author":[{"given":"Nhut-Minh","family":"Ho","sequence":"first","affiliation":[]},{"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1133255.1133997"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007559022013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.18"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1145\/1454115.1454119","article-title":"Outer-Loop Vectorization-Revisited for Short SIMD Architectures","author":"dorit nuzman","year":"2008","journal-title":"In International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-10113-8_6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926255"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref4","year":"0","journal-title":"A Guide to Vectorization with Intel C++ Compilers"},{"key":"ref3","year":"0","journal-title":"Auto-vectorization in Gcc"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1450095.1450121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2007.4429976"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145824"},{"key":"ref2","year":"0","journal-title":"NVIDIA Tesla P100 whitepaper"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/996893.996853"},{"key":"ref1","article-title":"754–2008 IEEE standard for floating-point arithmetic","volume":"2008","year":"2008","journal-title":"IEEE Computer Society Std"},{"key":"ref20","year":"0","journal-title":"Clang libtooling"},{"key":"ref22","year":"0","journal-title":"Gist github link"},{"key":"ref21","year":"0","journal-title":"IEEE 754-based half-precision floating point library"},{"key":"ref24","year":"0","journal-title":"FP16 throughput on GP104"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2005.7"},{"key":"ref26","year":"0","journal-title":"Github link"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"}],"event":{"name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Waltham, MA, USA","start":{"date-parts":[[2017,9,12]]},"end":{"date-parts":[[2017,9,14]]}},"container-title":["2017 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8079092\/8091018\/08091072.pdf?arnumber=8091072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T22:28:40Z","timestamp":1693175320000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8091072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/hpec.2017.8091072","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}