{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T11:12:50Z","timestamp":1773918770587,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,12,3]],"date-time":"2011-12-03T00:00:00Z","timestamp":1322870400000},"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":[[2011,12,3]]},"DOI":"10.1145\/2155620.2155675","type":"proceedings-article","created":{"date-parts":[[2012,3,6]],"date-time":"2012-03-06T13:18:26Z","timestamp":1331039906000},"page":"465-476","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["A compile-time managed multi-level register file hierarchy"],"prefix":"10.1145","author":[{"given":"Mark","family":"Gebhart","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, Austin, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen W.","family":"Keckler","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, TX, and NVIDIA, Santa Clara, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William J.","family":"Dally","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, and Stanford University, Stanford, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2011,12,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. HD 6900 Series Instruction Set Architecture. http:\/\/developer.amd.com\/gpu\/amdappsdk\/assets\/AMD_HD_6900_Series_Instruction_ Set_Architecture.pdf February 2011.  AMD. HD 6900 Series Instruction Set Architecture. http:\/\/developer.amd.com\/gpu\/amdappsdk\/assets\/AMD_HD_6900_Series_Instruction_ Set_Architecture.pdf February 2011."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJPP.0000004510.66751.2e"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2009.45"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2245737.2245881"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/291069.291010"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000079"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050187"},{"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","first-page":"236","volume-title":"Register Traffic Analysis for Streamlining Inter-operation Communication in Fine-grain Parallel Processors. In International Symposium on Microarchitecture","author":"Franklin M.","year":"1992","unstructured":"M. Franklin and G. S. Sohi . Register Traffic Analysis for Streamlining Inter-operation Communication in Fine-grain Parallel Processors. In International Symposium on Microarchitecture , pages 236 -- 245 , November 1992 . M. Franklin and G. S. Sohi. Register Traffic Analysis for Streamlining Inter-operation Communication in Fine-grain Parallel Processors. In International Symposium on Microarchitecture, pages 236--245, November 1992."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000093"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/266021.266192"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815998"},{"key":"e_1_3_2_1_15_1","unstructured":"NVIDIA. Compute Unified Device Architecture Programming Guide Version 2.0. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_0\/docs\/NVIDIA_CUDA_Programming_Guide_2.0.pdf June 2008.  NVIDIA. Compute Unified Device Architecture Programming Guide Version 2.0. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_0\/docs\/NVIDIA_CUDA_Programming_Guide_2.0.pdf June 2008."},{"key":"e_1_3_2_1_16_1","unstructured":"NVIDIA. PTX: Parallel Thread Execution ISA Version 2.3. http:\/\/developer.download.nvidia.com\/compute\/cuda\/4_0_rc2\/toolkit\/docs\/ptx_isa_2.3.pdf 2011.  NVIDIA. PTX: Parallel Thread Execution ISA Version 2.3. http:\/\/developer.download.nvidia.com\/compute\/cuda\/4_0_rc2\/toolkit\/docs\/ptx_isa_2.3.pdf 2011."},{"key":"e_1_3_2_1_17_1","unstructured":"Parboil Benchmark Suite. http:\/\/impact.crhc.illinois.edu\/parboil.php.  Parboil Benchmark Suite. http:\/\/impact.crhc.illinois.edu\/parboil.php."},{"key":"e_1_3_2_1_18_1","first-page":"171","volume-title":"Reducing Register Ports for Higher Speed and Lower Energy. In International Symposium on Microarchitecture","author":"Park I.","year":"2002","unstructured":"I. Park , M. D. Powell , and T. N. Vijaykumar . Reducing Register Ports for Higher Speed and Lower Energy. In International Symposium on Microarchitecture , pages 171 -- 182 , December 2002 . I. Park, M. D. Powell, and T. N. Vijaykumar. Reducing Register Ports for Higher Speed and Lower Energy. In International Symposium on Microarchitecture, pages 171--182, December 2002."},{"key":"e_1_3_2_1_19_1","volume-title":"Guaranteeing Forward Progress of Unified Register Allocation and Instruction Scheduling","author":"Park J.","year":"2011","unstructured":"J. Park and W. J. Dally . Guaranteeing Forward Progress of Unified Register Allocation and Instruction Scheduling . Technical Report Concurrent VLSI Architecture Group Memo 127, Stanford University , March 2011 . J. Park and W. J. Dally. Guaranteeing Forward Progress of Unified Register Allocation and Instruction Scheduling. Technical Report Concurrent VLSI Architecture Group Memo 127, Stanford University, March 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1134650.1134675"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/330249.330250"},{"key":"e_1_3_2_1_22_1","first-page":"375","volume-title":"Register Organization for Media Processing. In International Symposium on High Performance Computer Architecture","author":"Rixner S.","year":"2000","unstructured":"S. Rixner , W. Dally , B. Khailany , P. Mattson , U. Kapasi , and J. Owens . Register Organization for Media Processing. In International Symposium on High Performance Computer Architecture , pages 375 -- 386 , 2000 . S. Rixner, W. Dally, B. Khailany, P. Mattson, U. Kapasi, and J. Owens. Register Organization for Media Processing. In International Symposium on High Performance Computer Architecture, pages 375--386, 2000."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/359327.359336"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/55364.55398"},{"key":"e_1_3_2_1_25_1","first-page":"377","volume-title":"Energy-Efficient Register Access. In Symposium on Integrated Circuits and Systems Design","author":"Tseng J. H.","year":"2000","unstructured":"J. H. Tseng and K. Asanovic . Energy-Efficient Register Access. In Symposium on Integrated Circuits and Systems Design , pages 377 -- 382 , September 2000 . J. H. Tseng and K. Asanovic. Energy-Efficient Register Access. In Symposium on Integrated Circuits and Systems Design, pages 377--382, September 2000."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/377792.377861"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000094"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/360128.360143"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJPP.0000042082.31819.6d"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1120725.1120979"}],"event":{"name":"MICRO-44: The 44th Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Porto Alegre Brazil","acronym":"MICRO-44","sponsor":["IEEE","ACM Association for Computing Machinery","UFRGS Universidade Federal do Rio Grande do Sul","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 44th Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2155620.2155675","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2155620.2155675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:07:59Z","timestamp":1750273679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2155620.2155675"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12,3]]},"references-count":29,"alternative-id":["10.1145\/2155620.2155675","10.1145\/2155620"],"URL":"https:\/\/doi.org\/10.1145\/2155620.2155675","relation":{},"subject":[],"published":{"date-parts":[[2011,12,3]]},"assertion":[{"value":"2011-12-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}