{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T18:49:08Z","timestamp":1792954148684,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,6,9]],"date-time":"2007-06-09T00:00:00Z","timestamp":1181347200000},"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":[[2007,6,9]]},"DOI":"10.1145\/1250662.1250668","type":"proceedings-article","created":{"date-parts":[[2007,9,14]],"date-time":"2007-09-14T12:07:37Z","timestamp":1189771657000},"page":"35-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["Synchronization state buffer"],"prefix":"10.1145","author":[{"given":"Weirong","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Delaware, Newark, DE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vugranam C","family":"Sreedhar","sequence":"additional","affiliation":[{"name":"IBM TJ Watson Research Center, Howthorne, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziang","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Delaware, Newark, DE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Delaware, Newark, DE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2007,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"HPC challenge benchmark. http:\/\/icl.cs.utk.edu\/hpcc\/. HPC challenge benchmark. http:\/\/icl.cs.utk.edu\/hpcc\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Meet Larrabee Intel's answer to a GPU. http:\/\/www.theinquirer.net\/default.aspx?article=37548. Meet Larrabee Intel's answer to a GPU. http:\/\/www.theinquirer.net\/default.aspx?article=37548."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.216748"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019751632622"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/255129.255132"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/69558.69562"},{"key":"e_1_3_2_1_7_1","volume-title":"Platform 2015: Intel processor and platform evolution for the next decade","author":"Borkar S. Y.","year":"2005","unstructured":"S. Y. Borkar , H. Mulder , P. Dubey , S. S. Pawlowski , K. C. Kahn , J. R. Rattner , and D. J. Kuck . Platform 2015: Intel processor and platform evolution for the next decade , 2005 . S. Y. Borkar, H. Mulder, P. Dubey, S. S. Pawlowski, K. C. Kahn, J. R. Rattner, and D. J. Kuck. Platform 2015: Intel processor and platform evolution for the next decade, 2005."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/874076.876468"},{"key":"e_1_3_2_1_9_1","unstructured":"D.-K. Chen. Compiler Optimizations for Parallel Loops with Fine-Grained Synchronization. PhD thesis UIUC 1994. D.-K. Chen. Compiler Optimizations for Parallel Loops with Fine-Grained Synchronization. PhD thesis UIUC 1994."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370639"},{"key":"e_1_3_2_1_11_1","volume-title":"CSX processor architecture whitepaper","author":"Technology ClearSpeed","year":"2006","unstructured":"ClearSpeed Technology . CSX processor architecture whitepaper , 2006 . ClearSpeed Technology. CSX processor architecture whitepaper, 2006."},{"key":"e_1_3_2_1_12_1","volume-title":"Conf. on Comput. Design","author":"Dally W. J.","year":"2006","unstructured":"W. J. Dally . Computer architecture in the many-core era. In Keynote at the 24th Intl . Conf. on Comput. Design , 2006 . W. J. Dally. Computer architecture in the many-core era. In Keynote at the 24th Intl. Conf. on Comput. Design, 2006."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.127581"},{"key":"e_1_3_2_1_14_1","volume-title":"1st Workshop on Modeling, Benchmarking, and Simulation","author":"del Cuvillo J.","year":"2005","unstructured":"J. del Cuvillo , W. Zhu , Z. Hu , and G. R. Gao . FAST: A functionally accurate simulation toolset for the Cyclops64 cellular architecture . In 1st Workshop on Modeling, Benchmarking, and Simulation , Madison, WI , Jun. 2005 . J. del Cuvillo, W. Zhu, Z. Hu, and G. R. Gao. FAST: A functionally accurate simulation toolset for the Cyclops64 cellular architecture. In 1st Workshop on Modeling, Benchmarking, and Simulation, Madison, WI, Jun. 2005."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2006.48"},{"key":"e_1_3_2_1_16_1","volume-title":"Apr.","author":"Denneau M.","year":"2005","unstructured":"M. Denneau and H. S. Warren , Jr . 64-bit Cyclops: Principles of operation , Apr. 2005 . M. Denneau and H. S. Warren, Jr. 64-bit Cyclops: Principles of operation, Apr. 2005."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(88)90037-3"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062261.1062268"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.41"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165164"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/11823285_14"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264166"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/223982.224436"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/279358.279399"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183452"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264206"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.9"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/103727.103729"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/564870.564881"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2004.8"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1987.5009499"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1995.1117"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/522659.825640"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605399"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.54"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.23"},{"key":"e_1_3_2_1_38_1","series-title":"Scientific Computation Series","doi-asserted-by":"crossref","first-page":"41","DOI":"10.7551\/mitpress\/5239.003.0006","volume-title":"Parallel MIMD Computation: HEP Supercomputer and Its Applications","author":"Smith B.","year":"1985","unstructured":"B. Smith . The architecture of HEP. In Parallel MIMD Computation: HEP Supercomputer and Its Applications , Scientific Computation Series , pages 41 -- 55 . MIT Press , Cambridge, MA , 1985 . B. Smith. The architecture of HEP. In Parallel MIMD Computation: HEP Supercomputer and Its Applications, Scientific Computation Series, pages 41--55. MIT Press, Cambridge, MA, 1985."},{"key":"e_1_3_2_1_39_1","unstructured":"SPEC. SPEC OpenMP benchmark suite. SPEC. SPEC OpenMP benchmark suite."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1248377.1248399"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/520549.822786"},{"key":"e_1_3_2_1_42_1","volume-title":"CMOS. In Procs. of 2007 Intl. Solid-State Circuits Conf.","author":"Vangal S.","year":"2007","unstructured":"S. Vangal , J. Howard , G. Ruhl , and et. al. An 80-tile 1.28TFLOPS network-on-chip in 65nm CMOS. In Procs. of 2007 Intl. Solid-State Circuits Conf. , Feb. 2007 . S. Vangal, J. Howard, G. Ruhl, and et. al. An 80-tile 1.28TFLOPS network-on-chip in 65nm CMOS. In Procs. of 2007 Intl. Solid-State Circuits Conf., Feb. 2007."},{"key":"e_1_3_2_1_43_1","volume-title":"Optimizing the LU Benchmark for the Cyclops-64 Architecture. CAPSL Technical Memo 75","author":"Venetis I. E.","year":"2007","unstructured":"I. E. Venetis and G. R. Gao . Optimizing the LU Benchmark for the Cyclops-64 Architecture. CAPSL Technical Memo 75 , University of Delaware , Feb. 2007 . I. E. Venetis and G. R. Gao. Optimizing the LU Benchmark for the Cyclops-64 Architecture. CAPSL Technical Memo 75, University of Delaware, Feb. 2007."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155352"},{"key":"e_1_3_2_1_45_1","volume-title":"Procs. of 18th Intl. Parallel and Distrib. Processing Symp.","author":"Zhang L.","year":"2004","unstructured":"L. Zhang , Z. Fang , and J. B. Carter . Highly efficient synchronization based on active memory operations . In Procs. of 18th Intl. Parallel and Distrib. Processing Symp. , 2004 . L. Zhang, Z. Fang, and J. B. Carter. Highly efficient synchronization based on active memory operations. In Procs. of 18th Intl. Parallel and Distrib. Processing Symp., 2004."}],"event":{"name":"SPAA07: 19th ACM Symposium on Parallelism in Algorithms and Architectures","location":"San Diego California USA","acronym":"SPAA07","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 34th annual international symposium on Computer architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1250662.1250668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1250662.1250668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:52:18Z","timestamp":1750243938000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1250662.1250668"}},"subtitle":["supporting efficient fine-grain synchronization on many-core architectures"],"short-title":[],"issued":{"date-parts":[[2007,6,9]]},"references-count":44,"alternative-id":["10.1145\/1250662.1250668","10.1145\/1250662"],"URL":"https:\/\/doi.org\/10.1145\/1250662.1250668","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/1273440.1250668","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2007,6,9]]},"assertion":[{"value":"2007-06-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}