{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:01Z","timestamp":1763468221790,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,6,15]],"date-time":"2014-06-15T00:00:00Z","timestamp":1402790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,6,15]]},"DOI":"10.1145\/2613908.2613909","type":"proceedings-article","created":{"date-parts":[[2014,6,24]],"date-time":"2014-06-24T12:16:26Z","timestamp":1403612186000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Adaptive Cache Bypass and Insertion for Many-core Accelerators"],"prefix":"10.1145","author":[{"given":"Xuhao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology and Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengzhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Wen","family":"Chang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Sheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Pearson","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Mei W.","family":"Hwu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2014,6,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"\"NVIDIA CUDA SDK code samples.\"  \"NVIDIA CUDA SDK code samples.\""},{"key":"e_1_3_2_1_2_1","volume-title":"AMD Corporation","author":"Graphics Cores Next","year":"2012","unstructured":"AMD Graphics Cores Next (GCN) Architecture white paper , AMD Corporation , 2012 . AMD Graphics Cores Next (GCN) Architecture white paper, AMD Corporation, 2012."},{"key":"e_1_3_2_1_3_1","volume-title":"Yuan et al., \"Analyzing cuda workloads using a detailed gpu simulator,\" In ISPASS '09","author":"Bakhoda G.","year":"2009","unstructured":"A. Bakhoda , G. Yuan et al., \"Analyzing cuda workloads using a detailed gpu simulator,\" In ISPASS '09 , Boston, MA , 2009 . A. Bakhoda, G. Yuan et al., \"Analyzing cuda workloads using a detailed gpu simulator,\" In ISPASS '09, Boston, MA, 2009."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2159430.2159443"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.43"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000075"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540742"},{"key":"e_1_3_2_1_9_1","volume-title":"May","author":"Grauer-Gray L.","year":"2012","unstructured":"S. Grauer-Gray , L. Xu et al., \"Auto-tuning a high-level language targeted to gpu codes,\" In InPar '12 , May 2012 . S. Grauer-Gray, L. Xu et al., \"Auto-tuning a high-level language targeted to gpu codes,\" In InPar '12, May 2012."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815971"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304582"},{"key":"e_1_3_2_1_13_1","volume-title":"Shaw et al., \"MRPB: Memory request prioritization for massively parallel processors,\" In HPCA-20 '14","author":"Jia K. A.","year":"2014","unstructured":"W. Jia , K. A. Shaw et al., \"MRPB: Memory request prioritization for massively parallel processors,\" In HPCA-20 '14 , 2014 . W. Jia, K. A. Shaw et al., \"MRPB: Memory request prioritization for massively parallel processors,\" In HPCA-20 '14, 2014."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.24"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.70816"},{"key":"e_1_3_2_1_17_1","volume-title":"Khronos OpenCL Working Group","author":"The Open CL C","year":"2013","unstructured":"The Open CL C Specification Version : 2.0 , Khronos OpenCL Working Group , July 2013 . The OpenCL C Specification Version: 2.0, Khronos OpenCL Working Group, July 2013."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/379240.379259"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168947"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771793"},{"key":"e_1_3_2_1_21_1","volume-title":"Holey et al., \"Managing shared last-level cache in a heterogeneous multicore processor,\" In PACT '13","author":"Mekkat A.","year":"2013","unstructured":"V. Mekkat , A. Holey et al., \"Managing shared last-level cache in a heterogeneous multicore processor,\" In PACT '13 . Piscataway, NJ, USA : IEEE Press , 2013 . V. Mekkat, A. Holey et al., \"Managing shared last-level cache in a heterogeneous multicore processor,\" In PACT '13. Piscataway, NJ, USA: IEEE Press, 2013."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_23_1","volume-title":"Fermi TM","author":"A's Next Generation CUDA TM","year":"2009","unstructured":"NVIDI A's Next Generation CUDA TM Compute Architecture : Fermi TM , NVIDIA Corporation , 2009 . NVIDIA's Next Generation CUDA TM Compute Architecture: Fermi TM, NVIDIA Corporation, 2009."},{"key":"e_1_3_2_1_24_1","volume-title":"Kepler TM GK110","author":"A's Next Generation CUDA TM","year":"2012","unstructured":"NVIDI A's Next Generation CUDA TM Compute Architecture : Kepler TM GK110 , NVIDIA Corporation , 2012 . NVIDIA's Next Generation CUDA TM Compute Architecture: Kepler TM GK110, NVIDIA Corporation, 2012."},{"key":"e_1_3_2_1_25_1","unstructured":"CUDA C Programming Guide v5.5 NVIDIA Corporation July 2013.  CUDA C Programming Guide v5.5 NVIDIA Corporation July 2013."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"key":"e_1_3_2_1_29_1","volume-title":"Rodrigrues et al., \"Parboil: A revised benchmark suite for scientific and commercial throughput computing,\" UIUC","author":"Stratton C.","year":"2012","unstructured":"J. A. Stratton , C. Rodrigrues et al., \"Parboil: A revised benchmark suite for scientific and commercial throughput computing,\" UIUC , Urbana, Tech . Rep. IMPACT- 12-01, Mar. 2012 . J. A. Stratton, C. Rodrigrues et al., \"Parboil: A revised benchmark suite for scientific and commercial throughput computing,\" UIUC, Urbana, Tech. Rep. IMPACT-12-01, Mar. 2012."},{"key":"e_1_3_2_1_30_1","volume-title":"Liang et al., \"An efficient compiler framework for cache bypassing on GPUs,\" In ICCAD '13","author":"Xie Y.","year":"2013","unstructured":"X. Xie , Y. Liang et al., \"An efficient compiler framework for cache bypassing on GPUs,\" In ICCAD '13 , 2013 . X. Xie, Y. Liang et al., \"An efficient compiler framework for cache bypassing on GPUs,\" In ICCAD '13, 2013."}],"event":{"name":"MES '14: International Workshop on Manycore Embedded Systems","sponsor":["Univ. Turku University of Turku"],"location":"Minneapolis MN USA","acronym":"MES '14"},"container-title":["Proceedings of International Workshop on Manycore Embedded Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2613908.2613909","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2613908.2613909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:22:03Z","timestamp":1750278123000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2613908.2613909"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,15]]},"references-count":30,"alternative-id":["10.1145\/2613908.2613909","10.1145\/2613908"],"URL":"https:\/\/doi.org\/10.1145\/2613908.2613909","relation":{},"subject":[],"published":{"date-parts":[[2014,6,15]]},"assertion":[{"value":"2014-06-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}