{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:46:47Z","timestamp":1772164007677,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,6,13]],"date-time":"2015-06-13T00:00:00Z","timestamp":1434153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Center for Future Architectures Research"},{"name":"Qualcomm Innovation Fellowship"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1018796, CCF-1302641"],"award-info":[{"award-number":["CCF-1018796, CCF-1302641"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Illinois Intel Parallelism Center"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,13]]},"DOI":"10.1145\/2749469.2750374","type":"proceedings-article","created":{"date-parts":[[2015,5,26]],"date-time":"2015-05-26T10:36:25Z","timestamp":1432636585000},"page":"707-719","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Stash"],"prefix":"10.1145","author":[{"given":"Rakesh","family":"Komuravelli","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew D.","family":"Sinclair","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johnathan","family":"Alsop","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Huzaifa","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Kotsifakou","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prakalp","family":"Srivastava","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarita V.","family":"Adve","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikram S.","family":"Adve","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign and \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,6,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"\"HSA Platform System Architecture Specification \" 2015.  \"HSA Platform System Architecture Specification \" 2015."},{"key":"e_1_3_2_1_2_1","volume-title":"GARNET: A detailed on-chip network model inside a full-system simulator,\" in ISPASS","author":"Agarwal N.","year":"2009","unstructured":"N. Agarwal , T. Krishna , L.-S. Peh , and N. Jha , \" GARNET: A detailed on-chip network model inside a full-system simulator,\" in ISPASS , 2009 . N. Agarwal, T. Krishna, L.-S. Peh, and N. Jha, \"GARNET: A detailed on-chip network model inside a full-system simulator,\" in ISPASS, 2009."},{"key":"e_1_3_2_1_3_1","unstructured":"AMD \"Compute Cores \" https:\/\/www.amd.com\/Documents\/Compute_Cores_Whitepaper.pdf.  AMD \"Compute Cores \" https:\/\/www.amd.com\/Documents\/Compute_Cores_Whitepaper.pdf."},{"key":"e_1_3_2_1_4_1","unstructured":"AMD \"Sea Islands Series Instruction Set Architecture \" http:\/\/developer.amd.com\/wordpress\/media\/2013\/07\/AMD_Sea_Islands_Instruction_Set_Architecture.pdf.  AMD \"Sea Islands Series Instruction Set Architecture \" http:\/\/developer.amd.com\/wordpress\/media\/2013\/07\/AMD_Sea_Islands_Instruction_Set_Architecture.pdf."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/581888.581891"},{"key":"e_1_3_2_1_6_1","volume-title":"Analyzing CUDA Workloads Using a Detailed GPU Simulator,\" in ISPASS","author":"Bakhoda A.","year":"2009","unstructured":"A. Bakhoda , G. L. Yuan , W. W. L. Fung , H. Wong , and T. M. Aamodt , \" Analyzing CUDA Workloads Using a Detailed GPU Simulator,\" in ISPASS , 2009 . A. Bakhoda, G. L. Yuan, W. W. L. Fung, H. Wong, and T. M. Aamodt, \"Analyzing CUDA Workloads Using a Detailed GPU Simulator,\" in ISPASS, 2009."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/774789.774805"},{"key":"e_1_3_2_1_8_1","volume-title":"Reducing Memory Reference Energy with Opportunistic Virtual Caching,\" in ISCA","author":"Basu A.","year":"2012","unstructured":"A. Basu , M. D. Hill , and M. M. Swift , \" Reducing Memory Reference Energy with Opportunistic Virtual Caching,\" in ISCA , 2012 . A. Basu, M. D. Hill, and M. M. Swift, \"Reducing Memory Reference Energy with Opportunistic Virtual Caching,\" in ISCA, 2012."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063400"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"e_1_3_2_1_11_1","volume-title":"Impulse: Building a Smarter Memory Controller,\" in HPCA","author":"Carter J.","year":"1999","unstructured":"J. Carter , W. Hsieh , L. Stoller , M. Swanson , L. Zhang , E. Brunvand , A. Davis , C.-C. Kuo , R. Kuramkote , M. Parker , L. Schaelicke , and T. Tateyama , \" Impulse: Building a Smarter Memory Controller,\" in HPCA , 1999 . J. Carter, W. Hsieh, L. Stoller, M. Swanson, L. Zhang, E. Brunvand, A. Davis, C.-C. Kuo, R. Kuramkote, M. Parker, L. Schaelicke, and T. Tateyama, \"Impulse: Building a Smarter Memory Controller,\" in HPCA, 1999."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063401"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.21"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2333660.2333715"},{"key":"e_1_3_2_1_16_1","volume-title":"An Energy-efficient Adaptive Hybrid Cache,\" in ISLPED","author":"Cong J.","year":"2011","unstructured":"J. Cong , K. Gururaj , H. Huang , C. Liu , G. Reinman , and Y. Zou , \" An Energy-efficient Adaptive Hybrid Cache,\" in ISLPED , 2011 . J. Cong, K. Gururaj, H. Huang, C. Liu, G. Reinman, and Y. Zou, \"An Energy-efficient Adaptive Hybrid Cache,\" in ISLPED, 2011."},{"key":"e_1_3_2_1_18_1","unstructured":"DoE \"Top Ten Exascale Research Challenges \" http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf 2014.  DoE \"Top Ten Exascale Research Challenges \" http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf 2014."},{"key":"e_1_3_2_1_19_1","volume-title":"QuickRelease: A throughput-oriented approach to release consistency on GPUs,\" in HPCA","author":"Hechtman B.","year":"2014","unstructured":"B. Hechtman , S. Che , D. Hower , Y. Tian , B. Beckmann , M. Hill , S. Reinhardt , and D. Wood , \" QuickRelease: A throughput-oriented approach to release consistency on GPUs,\" in HPCA , 2014 . B. Hechtman, S. Che, D. Hower, Y. Tian, B. Beckmann, M. Hill, S. Reinhardt, and D. Wood, \"QuickRelease: A throughput-oriented approach to release consistency on GPUs,\" in HPCA, 2014."},{"key":"e_1_3_2_1_20_1","unstructured":"IntelPR \"Intel Discloses Newest Microarchitecture and 14 Nanometer Manufacturing Process Technical Details \" Intel Newsroom 2014.  IntelPR \"Intel Discloses Newest Microarchitecture and 14 Nanometer Manufacturing Process Technical Details \" Intel Newsroom 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628072"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145878"},{"key":"e_1_3_2_1_24_1","volume-title":"dissertation","author":"Komuravelli R.","year":"2014","unstructured":"R. Komuravelli , \"Exploiting Software Information for an Efficient Memory Hierarchy,\" Ph. D. dissertation , The University of Illinois at Urbana-Champaign, 2014 . R. Komuravelli, \"Exploiting Software Information for an Efficient Memory Hierarchy,\" Ph.D. dissertation, The University of Illinois at Urbana-Champaign, 2014."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_26_1","volume-title":"Understanding the Tradeoffs Between Software-Managed vs. Hardware-Managed Caches in GPUs,\" in ISPASS","author":"Li C.","year":"2014","unstructured":"C. Li , Y. Yang , D. Hongwen , Y. Shengen , F. Mueller , and H. Zhou , \" Understanding the Tradeoffs Between Software-Managed vs. Hardware-Managed Caches in GPUs,\" in ISPASS , 2014 . C. Li, Y. Yang, D. Hongwen, Y. Shengen, F. Mueller, and H. Zhou, \"Understanding the Tradeoffs Between Software-Managed vs. Hardware-Managed Caches in GPUs,\" in ISPASS, 2014."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2086696.2086727"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1105734.1105747"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1509288.1509293"},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA \"CUDA SDK 3.1 \" http:\/\/developer.nvidia.com\/object\/cuda_3_1_downloads.html.  NVIDIA \"CUDA SDK 3.1 \" http:\/\/developer.nvidia.com\/object\/cuda_3_1_downloads.html."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540747"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540714"},{"key":"e_1_3_2_1_34_1","volume-title":"A Revised Benchmark Suite for Scientific and Commercial Throughput Computing,\" Dept. of ECE and CS","author":"Stratton J. A.","year":"2012","unstructured":"J. A. Stratton , C. Rodrigues , I.-J. Sung , N. Obeid , L.-W. Chang , N. Anssari , G. D. Liu , and W.-M. Hwu , \"Parboil : A Revised Benchmark Suite for Scientific and Commercial Throughput Computing,\" Dept. of ECE and CS , Univ. of Illinois at Urbana-Champaign, Tech. Rep., 2012 . J. A. Stratton, C. Rodrigues, I.-J. Sung, N. Obeid, L.-W. Chang, N. Anssari, G. D. Liu, and W.-M. Hwu, \"Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing,\" Dept. of ECE and CS, Univ. of Illinois at Urbana-Champaign, Tech. Rep., 2012."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694356"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451119"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/951710.951747"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1151074.1151085"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627606"}],"event":{"name":"ISCA '15: The 42nd Annual International Symposium on Computer Architecture","location":"Portland Oregon","acronym":"ISCA '15","sponsor":["IEEE TCCA IEEE Computer Society Technical Committee on Computer Architecture","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 42nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2749469.2750374","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2749469.2750374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:00:39Z","timestamp":1750215639000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2749469.2750374"}},"subtitle":["have your scratchpad and cache it too"],"short-title":[],"issued":{"date-parts":[[2015,6,13]]},"references-count":38,"alternative-id":["10.1145\/2749469.2750374","10.1145\/2749469"],"URL":"https:\/\/doi.org\/10.1145\/2749469.2750374","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2872887.2750374","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2015,6,13]]},"assertion":[{"value":"2015-06-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}