{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T22:59:49Z","timestamp":1792969189905,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,6,4]],"date-time":"2011-06-04T00:00:00Z","timestamp":1307145600000},"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":[[2011,6,4]]},"DOI":"10.1145\/2000064.2000093","type":"proceedings-article","created":{"date-parts":[[2011,6,28]],"date-time":"2011-06-28T13:34:50Z","timestamp":1309268090000},"page":"235-246","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":188,"title":["Energy-efficient mechanisms for managing thread context in throughput processors"],"prefix":"10.1145","author":[{"given":"Mark","family":"Gebhart","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel R.","family":"Johnson","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Tarjan","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen W.","family":"Keckler","sequence":"additional","affiliation":[{"name":"NVIDIA \/ The University of Texas at Austin, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William J.","family":"Dally","sequence":"additional","affiliation":[{"name":"NVIDIA \/ Stanford University, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Lindholm","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Skadron","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2011,6,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325119"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/77726.255132"},{"key":"e_1_3_2_2_3_1","unstructured":"AMD. R600-Family Instruction Set Architecture. http:\/\/developer.amd.com\/ gpu_assets\/ R600_Instruction_Set_Architecture.pdf January 2009.  AMD. R600-Family Instruction Set Architecture. http:\/\/developer.amd.com\/ gpu_assets\/ R600_Instruction_Set_Architecture.pdf January 2009."},{"key":"e_1_3_2_2_4_1","unstructured":"AMD. ATI Stream Computing OpenCL Programming Guide. http:\/\/developer.amd.com\/gpu\/ ATIStreamSDK\/assets\/ ATI_Stream_SDK_OpenCL_Programming_Guide.pdf August 2010.  AMD. ATI Stream Computing OpenCL Programming Guide. http:\/\/developer.amd.com\/gpu\/ ATIStreamSDK\/assets\/ ATI_Stream_SDK_OpenCL_Programming_Guide.pdf August 2010."},{"key":"e_1_3_2_2_5_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_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_2_7_1","first-page":"237","volume-title":"Reducing the Complexity of the Register File in Dynamic Susperscalar Processors. In International Symposium on Microarchitecture","author":"Balasubramonian R.","year":"2001","unstructured":"R. Balasubramonian , S. Dwarkadas , and D. H. Albonesi . Reducing the Complexity of the Register File in Dynamic Susperscalar Processors. In International Symposium on Microarchitecture , pages 237 -- 248 , December 2001 . R. Balasubramonian, S. Dwarkadas, and D. H. Albonesi. Reducing the Complexity of the Register File in Dynamic Susperscalar Processors. In International Symposium on Microarchitecture, pages 237--248, December 2001."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2009.45"},{"key":"e_1_3_2_2_9_1","first-page":"299","volume-title":"Loose Loops Sink Chips. In International Symposium on High Performance Computer Architecture","author":"Borch E.","year":"2002","unstructured":"E. Borch , E. Tune , S. Manne , and J. Emer . Loose Loops Sink Chips. In International Symposium on High Performance Computer Architecture , pages 299 -- 310 , February 2002 . E. Borch, E. Tune, S. Manne, and J. Emer. Loose Loops Sink Chips. In International Symposium on High Performance Computer Architecture, pages 299--310, February 2002."},{"key":"e_1_3_2_2_10_1","first-page":"27","volume-title":"Hierarchical Scheduling Windows. In International Symposium on Microarchitecture","author":"Brekelbaum E.","year":"2002","unstructured":"E. Brekelbaum , J. Rupley , C. Wilkerson , and B. Black . Hierarchical Scheduling Windows. In International Symposium on Microarchitecture , pages 27 -- 36 , November 2002 . E. Brekelbaum, J. Rupley, C. Wilkerson, and B. Black. Hierarchical Scheduling Windows. In International Symposium on Microarchitecture, pages 27--36, November 2002."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339708"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/859618.859647"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1400181.1400197"},{"key":"e_1_3_2_2_14_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_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.121"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815998"},{"key":"e_1_3_2_2_17_1","volume-title":"Workshop on Complexity-Effective Design","author":"Hu Z.","year":"2000","unstructured":"Z. Hu and M. Martonosi . Reducing Register File Power Consumption by Exploiting Value Lifetime Characteristics . In Workshop on Complexity-Effective Design , June 2000 . Z. Hu and M. Martonosi. Reducing Register File Power Consumption by Exploiting Value Lifetime Characteristics. In Workshop on Complexity-Effective Design, June 2000."},{"key":"e_1_3_2_2_18_1","volume-title":"http:\/\/itrs.net\/links\/2009ITRS\/Home2009.htm","year":"2009","unstructured":"International Technology Roadmap for Semiconductors. http:\/\/itrs.net\/links\/2009ITRS\/Home2009.htm , 2009 . International Technology Roadmap for Semiconductors. http:\/\/itrs.net\/links\/2009ITRS\/Home2009.htm, 2009."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1596510.1596511"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.35"},{"key":"e_1_3_2_2_22_1","first-page":"59","volume-title":"Fast Instruction Window for Tolerating Cache Misses. In International Symposium on Computer Architecture","author":"Lebeck A. R.","year":"2002","unstructured":"A. R. Lebeck , J. Koppanalil , T. Li , J. Patwardhan , and E. Rotenberg . A Large , Fast Instruction Window for Tolerating Cache Misses. In International Symposium on Computer Architecture , pages 59 -- 70 , May 2002 . A. R. Lebeck, J. Koppanalil, T. Li, J. Patwardhan, and E. Rotenberg. A Large, Fast Instruction Window for Tolerating Cache Misses. In International Symposium on Computer Architecture, pages 59--70, May 2002."},{"key":"e_1_3_2_2_23_1","first-page":"555","volume-title":"IEEE Custom Integrated Circuits Conference","author":"Leon A. S.","year":"2007","unstructured":"A. S. Leon , B. Langley , and J. L. Shin . The UltraSPARC T1 Processor: CMT Reliability . In IEEE Custom Integrated Circuits Conference , pages 555 -- 562 , September 2007 . A. S. Leon, B. Langley, and J. L. Shin. The UltraSPARC T1 Processor: CMT Reliability. In IEEE Custom Integrated Circuits Conference, pages 555--562, September 2007."},{"key":"e_1_3_2_2_24_1","volume-title":"HP Laboratories","author":"Muralimanohar N.","year":"2009","unstructured":"N. Muralimanohar , R. Balasubramonian , and N. P. Jouppi . CACTI 6.0: A Tool to Model Large Caches. Technical report , HP Laboratories , April 2009 . N. Muralimanohar, R. Balasubramonian, and N. P. Jouppi. CACTI 6.0: A Tool to Model Large Caches. Technical report, HP Laboratories, April 2009."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/645460.654100"},{"key":"e_1_3_2_2_26_1","first-page":"4","volume-title":"The Named-State Register File: Implementation and Performance. In International Symposium on High Performance Computer Architecture","author":"Nuth P. R.","year":"1995","unstructured":"P. R. Nuth and W. J. Dally . The Named-State Register File: Implementation and Performance. In International Symposium on High Performance Computer Architecture , pages 4 -- 13 , January 1995 . P. R. Nuth and W. J. Dally. The Named-State Register File: Implementation and Performance. In International Symposium on High Performance Computer Architecture, pages 4--13, January 1995."},{"key":"e_1_3_2_2_27_1","unstructured":"NVIDIA. Compute Unified Device Architecture Programming Guide Version 2.0. http:\/\/devloper.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:\/\/devloper.download.nvidia.com\/ compute\/cuda\/2_0\/docs\/NVIDIA_CUDA_Programming_Guide_2.0.pdf June 2008."},{"key":"e_1_3_2_2_28_1","unstructured":"NVIDIA. NVIDIA's Next Generation CUDA Compute Architecture: Fermi. http:\/\/nvidia.com\/content\/ PDF\/fermi_white_papers\/NVIDIA_ Fermi_Compute_Architecture_Whitepaper.pdf 2009.  NVIDIA. NVIDIA's Next Generation CUDA Compute Architecture: Fermi. http:\/\/nvidia.com\/content\/ PDF\/fermi_white_papers\/NVIDIA_ Fermi_Compute_Architecture_Whitepaper.pdf 2009."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/545215.545251"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360617"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.43"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/55364.55398"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.8"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/641865.641867"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1165573.1165633"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/942806.943845"}],"event":{"name":"ISCA '11: The 38th Annual International Symposium on Computer Architecture","location":"San Jose California USA","acronym":"ISCA '11","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE CS"]},"container-title":["Proceedings of the 38th annual international symposium on Computer architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2000064.2000093","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2000064.2000093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:48:56Z","timestamp":1750225736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2000064.2000093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6,4]]},"references-count":36,"alternative-id":["10.1145\/2000064.2000093","10.1145\/2000064"],"URL":"https:\/\/doi.org\/10.1145\/2000064.2000093","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2024723.2000093","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2011,6,4]]},"assertion":[{"value":"2011-06-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}