{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:45:24Z","timestamp":1767167124735,"version":"build-2238731810"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2013,8,1]],"date-time":"2013-08-01T00:00:00Z","timestamp":1375315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100005595","name":"University of California","doi-asserted-by":"publisher","award":["#DIG07-10227"],"award-info":[{"award-number":["#DIG07-10227"]}],"id":[{"id":"10.13039\/100005595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","award":["#024894"],"award-info":[{"award-number":["#024894"]}],"id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","award":["#024263"],"award-info":[{"award-number":["#024263"]}],"id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Syst."],"published-print":{"date-parts":[[2013,8]]},"abstract":"<jats:p>We present a taxonomy and modular implementation approach for data-parallel accelerators, including the MIMD, vector-SIMD, subword-SIMD, SIMT, and vector-thread (VT) architectural design patterns. We introduce Maven, a new VT microarchitecture based on the traditional vector-SIMD microarchitecture, that is considerably simpler to implement and easier to program than previous VT designs. Using an extensive design-space exploration of full VLSI implementations of many accelerator design points, we evaluate the varying tradeoffs between programmability and implementation efficiency among the MIMD, vector-SIMD, and VT patterns on a workload of compiled microbenchmarks and application kernels. We find the vector cores provide greater efficiency than the MIMD cores, even on fairly irregular kernels. Our results suggest that the Maven VT microarchitecture is superior to the traditional vector-SIMD architecture, providing both greater efficiency and easier programmability.<\/jats:p>","DOI":"10.1145\/2491464","type":"journal-article","created":{"date-parts":[[2020,4,4]],"date-time":"2020-04-04T03:41:33Z","timestamp":1585971693000},"page":"1-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Exploring the Tradeoffs between Programmability and Efficiency in Data-Parallel Accelerators"],"prefix":"10.1145","volume":"31","author":[{"given":"Yunsup","family":"Lee","sequence":"first","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rimas","family":"Avizienis","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Bishara","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Xia","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derek","family":"Lockhart","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Batten","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krste","family":"Asanovi\u0107","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362646"},{"key":"e_1_2_1_2_1","unstructured":"Randy Allen and Ken Kennedy. 2001. Optimizing Compilers for Modern Architectures. Morgan Kaufmann.  Randy Allen and Ken Kennedy. 2001. Optimizing Compilers for Modern Architectures . Morgan Kaufmann."},{"key":"e_1_2_1_3_1","unstructured":"Krste Asanovi\u0107. 1998. Vector microprocessors. Ph.D. dissertation EECS Department University of California Berkeley.   Krste Asanovi\u0107. 1998. Vector microprocessors. Ph.D. dissertation EECS Department University of California Berkeley."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/197405.197406"},{"key":"e_1_2_1_5_1","unstructured":"Christopher Batten. 2010. Simplified vector-thread architectures for flexible and efficient data-parallel accelerators. Ph.D. dissertation MIT.   Christopher Batten. 2010. Simplified vector-thread architectures for flexible and efficient data-parallel accelerators. Ph.D. dissertation MIT."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.9"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.251.0051"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015800"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of SUIF Compiler Workshop.","author":"DeVries Derek"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.848475"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/525424.822650"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1966.5273"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1455567.1455593"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1543753.1543756"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2005.239"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.41"},{"key":"e_1_2_1_17_1","first-page":"15","article-title":"Digital, MIPS add multimedia extensions","volume":"10","author":"Gwennap Linley","year":"1996","journal-title":"Microprocessor Forum"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356085"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555774"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.16"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.35"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.612252"},{"key":"e_1_2_1_23_1","unstructured":"Ronny Krashinsky. 2007. Vector-thread architecture and implementation. Ph.D. dissertation MIT.   Ronny Krashinsky. 2007. Vector-thread architecture and implementation. Ph.D. dissertation MIT."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367045.1367050"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/998680.1006736"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.526925"},{"key":"e_1_2_1_27_1","unstructured":"Yunsup Lee. 2011. Efficient VLSI implementations of vector-thread architectures. Master\u2019s thesis UC Berkeley.  Yunsup Lee. 2011. Efficient VLSI implementations of vector-thread architectures. Master\u2019s thesis UC Berkeley."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000080"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"e_1_2_1_30_1","unstructured":"Chris Lomont. 2011. Introduction to Intel advanced vector extensions. Intel White Paper.  Chris Lomont. 2011. Introduction to Intel advanced vector extensions. Intel White Paper."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771788"},{"key":"e_1_2_1_32_1","unstructured":"Microsoft. 2009. Graphics guide for Windows 7: A guide For hardware and system manufacturers. Microsoft White Paper. http:\/\/www.microsoft.com\/whdc\/device\/display\/graphicsguidewin7.mspx.  Microsoft. 2009. Graphics guide for Windows 7: A guide For hardware and system manufacturers. Microsoft White Paper. http:\/\/www.microsoft.com\/whdc\/device\/display\/graphicsguidewin7.mspx."},{"key":"e_1_2_1_33_1","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman P. Jouppi. 2009. CACTI 6.0: A tool to model large caches. Tech. rep. Hewlett Packard HPL-2009-85.  Naveen Muralimanohar Rajeev Balasubramonian and Norman P. Jouppi. 2009. CACTI 6.0: A tool to model large caches. Tech. rep. Hewlett Packard HPL-2009-85."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2007.373611"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"e_1_2_1_36_1","unstructured":"NVIDIA. 2009. NVIDIA\u2019s next gen CUDA compute architecture: Fermi. NVIDIA White Paper. http:\/\/www.nvidia.com\/content\/pdf\/fermi_white_papers\/nvidia_fermi_compute_architecture _whitepaper.pdf.  NVIDIA. 2009. NVIDIA\u2019s next gen CUDA compute architecture: Fermi. NVIDIA White Paper. http:\/\/www.nvidia.com\/content\/pdf\/fermi_white_papers\/nvidia_fermi_compute_architecture _whitepaper.pdf."},{"key":"e_1_2_1_37_1","unstructured":"OpenCL. 2008. The OpenCL specification. Khronos OpenCL Working Group. http:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-1.0.48.pdf.  OpenCL. 2008. The OpenCL specification. Khronos OpenCL Working Group. http:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-1.0.48.pdf."},{"key":"e_1_2_1_38_1","unstructured":"OpenMP. 2008. OpenMP application program interface. OpenMP Architecture Review Board. http:\/\/www.openmp.org\/mp-documents\/spec30.pdf.  OpenMP. 2008. OpenMP application program interface. OpenMP Architecture Review Board. http:\/\/www.openmp.org\/mp-documents\/spec30.pdf."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.526924"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.865866"},{"key":"e_1_2_1_41_1","unstructured":"James Reinders. 2007. Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism. O\u2019Reilly Media.   James Reinders. 2007. Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism . O\u2019Reilly Media."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2006.74"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/359327.359336"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/956417.956548"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339693"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654088"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(85)90022-5"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.526921"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.485896"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073211"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/125826.126164"}],"container-title":["ACM Transactions on Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2491464","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2491464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:28:49Z","timestamp":1750217329000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2491464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8]]},"references-count":52,"aliases":["10.1145\/2518037.2491464"],"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,8]]}},"alternative-id":["10.1145\/2491464"],"URL":"https:\/\/doi.org\/10.1145\/2491464","relation":{},"ISSN":["0734-2071","1557-7333"],"issn-type":[{"value":"0734-2071","type":"print"},{"value":"1557-7333","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8]]},"assertion":[{"value":"2013-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2013-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2013-08-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}