{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:23:31Z","timestamp":1784643811370,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER-1652294, XPS-1628991, SHF-1763918"],"award-info":[{"award-number":["CAREER-1652294, XPS-1628991, SHF-1763918"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322257","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"397-410","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":95,"title":["Duality cache for data parallel acceleration"],"prefix":"10.1145","author":[{"given":"Daichi","family":"Fujiki","sequence":"first","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Mahlke","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reetuparna","family":"Das","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522344"},{"key":"e_1_3_2_1_2_1","volume-title":"Compute Caches. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA). 481--492","author":"Aga S.","unstructured":"S. Aga, S. Jeloka, A. Subramaniyan, S. Narayanasamy, D. Blaauw, and R. Das. 2017. Compute Caches. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA). 481--492."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/275107.275139"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1054943.1054946"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_8_1","unstructured":"ROSE compiler infrastructure. 2018. Rose Compiler. http:\/\/rosecompiler.org\/."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854318"},{"key":"e_1_3_2_1_10_1","volume-title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 383--396","author":"Eckert C.","unstructured":"C. Eckert, X. Wang, J. Wang, A. Subramaniyan, R. Iyer, D. Sylvester, D. Blaaauw, and R. Das. 2018. Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 383--396."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/5910"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00039"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/966049.781505"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173171"},{"key":"e_1_3_2_1_16_1","volume-title":"An Energy Efficient 32-nm 20-MB Shared On-Die L3 Cache for Intel\u00ae Xeon\u00ae Processor E5 Family. J. Solid-State Circuits","author":"Huang Min","year":"2013","unstructured":"Min Huang, Moty Mehalel, Ramesh Arvapalli, and Songnian He. 2013. An Energy Efficient 32-nm 20-MB Shared On-Die L3 Cache for Intel\u00ae Xeon\u00ae Processor E5 Family. J. Solid-State Circuits (2013)."},{"key":"e_1_3_2_1_17_1","unstructured":"Intel. 2008. x87 and SSE Floating Point Assists in IA-32: Flush-To-Zero (FTZ) and Denormals-Are-Zero (DAZ). https:\/\/software.intel.com\/en-us\/articles\/x87-and-sse-floating-point-assists-in-ia-32-flush-to-zero-ftz-and-denormals-are-zero-daz\/."},{"key":"e_1_3_2_1_18_1","unstructured":"Intel. 2018. Intel Processor Graphics. https:\/\/software.intel.com\/en-us\/articles\/intel-graphics-developers-guides."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2515510"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1816021"},{"key":"e_1_3_2_1_24_1","unstructured":"MathWorks. 2018. Compute Square Root Using CORDIC. https:\/\/www.mathworks.com\/help\/fixedpoint\/examples\/compute-square-root-using-cordic.html."},{"key":"e_1_3_2_1_25_1","volume-title":"A tool to model large caches. HP laboratories","author":"Muralimanohar Naveen","year":"2009","unstructured":"Naveen Muralimanohar, Rajeev Balasubramonian, and Norman P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP laboratories (2009), 22--31."},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA. 2018. CUDA Toolkit. https:\/\/developer.nvidia.com\/cuda-toolkit."},{"key":"e_1_3_2_1_27_1","unstructured":"NVIDIA. 2018. Parallel Thread Execution ISA. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html."},{"key":"e_1_3_2_1_28_1","unstructured":"NVIDIA. 2018. PGI Compilers & Tools. https:\/\/www.pgroup.com\/."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/279361.279387"},{"key":"e_1_3_2_1_30_1","unstructured":"PathScale. 2013. Performance test suite for openacc compiler intel mic patus and single-core cpu. https:\/\/github.com\/pathscale\/OpenACC-benchmarks."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"D. Patterson T. Anderson N. Cardwell R. Fromm K. Keeton C. Kozyrakis R. Thomas and K. Yelick. 1997. A case for intelligent RAM. Micro IEEE (1997). 10.1109\/40.592312","DOI":"10.1109\/40.592312"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_36_1","volume-title":"Euro-Par 2013: Parallel Processing Workshops, Dieter an Mey","author":"Tabuchi Akihiro","unstructured":"Akihiro Tabuchi, Masahiro Nakao, and Mitsuhisa Sato. 2014. A Source-to-Source OpenACC Compiler for CUDA. In Euro-Par 2013: Parallel Processing Workshops, Dieter an Mey, Michael Alexander, Paolo Bientinesi, Mario Cannataro, Carsten Clauss, Alexandru Costan, Gabor Kecskemeti, Christine Morin, Laura Ricci, Julio Sahuquillo, Martin Schulz, Vittorio Scarano, Stephen L Scott, and Josef Weidendorfer (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 178--187."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1959.5222693"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1478786.1478840"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691165"},{"key":"e_1_3_2_1_40_1","volume-title":"2014 IEEE International Symposium on Workload Characterization (IISWC). 140--149","author":"Xu Q.","unstructured":"Q. Xu, H. Jeon, and M. Annavaram. 2014. Graph processing on GPUs: Where are the bottlenecks?. In 2014 IEEE International Symposium on Workload Characterization (IISWC). 140--149."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_2_1_42_1","unstructured":"Qiuling Zhu B. Akin H.E. Sumbul F. Sadi J.C. Hoe L. Pileggi and F. Franchetti. 2013. A 3D-stacked logic-in-memory accelerator for application-specific data intensive computing. In 3D Systems Integration Conference (3DIC) 2013 IEEE International."}],"event":{"name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona","acronym":"ISCA '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322257","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322257","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:06Z","timestamp":1750204446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":42,"alternative-id":["10.1145\/3307650.3322257","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322257","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}