{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:37:44Z","timestamp":1781714264619,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,6,13]]},"DOI":"10.1145\/2749469.2750407","type":"proceedings-article","created":{"date-parts":[[2015,5,26]],"date-time":"2015-05-26T10:36:25Z","timestamp":1432636585000},"page":"272-284","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["The load slice core microarchitecture"],"prefix":"10.1145","author":[{"given":"Trevor E.","family":"Carlson","sequence":"first","affiliation":[{"name":"Uppsala University, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wim","family":"Heirman","sequence":"additional","affiliation":[{"name":"Intel, ExaScience Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osman","family":"Allam","sequence":"additional","affiliation":[{"name":"Ghent University, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanos","family":"Kaxiras","sequence":"additional","affiliation":[{"name":"Uppsala University, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lieven","family":"Eeckhout","sequence":"additional","affiliation":[{"name":"Ghent University, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,6,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"ARM \"2GHz capable Cortex-A9 dual core processor implementation \" http:\/\/www.arm.com\/files\/downloads\/Osprey_Analyst_Presentation_v2a.pdf archived at the Internet Archive (http:\/\/archive.org).  ARM \"2GHz capable Cortex-A9 dual core processor implementation \" http:\/\/www.arm.com\/files\/downloads\/Osprey_Analyst_Presentation_v2a.pdf archived at the Internet Archive (http:\/\/archive.org)."},{"key":"e_1_3_2_1_2_1","unstructured":"ARM \"ARM Cortex-A7 processor \" http:\/\/www.arm.com\/products\/processors\/cortex-a\/cortex-a7.php.  ARM \"ARM Cortex-A7 processor \" http:\/\/www.arm.com\/products\/processors\/cortex-a\/cortex-a7.php."},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"Eds.","volume":"2104","author":"Aslot V.","year":"2001","unstructured":"V. Aslot , M. Domeika , R. Eigenmann , G. Gaertner , W. Jones , and B. Parady , \" SPEComp: A new benchmark suite for measuring parallel computer performance,\" in OpenMP Shared Memory Parallel Programming, R. Eigenmann and M. Voss , Eds. , Jul. 2001 , vol. 2104 , pp. 1 -- 10 . V. Aslot, M. Domeika, R. Eigenmann, G. Gaertner, W. Jones, and B. Parady, \"SPEComp: A new benchmark suite for measuring parallel computer performance,\" in OpenMP Shared Memory Parallel Programming, R. Eigenmann and M. Voss, Eds., Jul. 2001, vol. 2104, pp. 1--10."},{"key":"e_1_3_2_1_4_1","first-page":"18","volume-title":"Jan. 2003","author":"Barnes R. D.","unstructured":"R. D. Barnes , E. M. Nystrom , J. W. Sias , S. J. Patel , N. Navarro , and W. W. Hwu , \" Beating in-order stalls with \"flea-flicker\" two-pass pipelining,\" in Proceedings of the 36th International Symposium on Microarchitecture (MICRO) , Jan. 2003 , pp. 18 -- 33 . R. D. Barnes, E. M. Nystrom, J. W. Sias, S. J. Patel, N. Navarro, and W. W. Hwu, \"Beating in-order stalls with \"flea-flicker\" two-pass pipelining,\" in Proceedings of the 36th International Symposium on Microarchitecture (MICRO), Jan. 2003, pp. 18--33."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2005.1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063454"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629677"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.49"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555814"},{"key":"e_1_3_2_1_10_1","first-page":"76","volume-title":"Jun. 2004","author":"Chou Y.","unstructured":"Y. Chou , B. Fahs , and S. Abraham , \" Microarchitecture optimizations for exploiting memory-level parallelism,\" in Proceedings of the International Symposium on Computer Architecture (ISCA) , Jun. 2004 , pp. 76 -- 87 . Y. Chou, B. Fahs, and S. Abraham, \"Microarchitecture optimizations for exploiting memory-level parallelism,\" in Proceedings of the International Symposium on Computer Architecture (ISCA), Jun. 2004, pp. 76--87."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 24th Hot Chips Symposium","author":"Chrysos G.","year":"2012","unstructured":"G. Chrysos , \"Intel\u00ae Xeon Phi coprocessor (codename Knights Corner),\" in Proceedings of the 24th Hot Chips Symposium , Aug. 2012 . G. Chrysos, \"Intel\u00ae Xeon Phi coprocessor (codename Knights Corner),\" in Proceedings of the 24th Hot Chips Symposium, Aug. 2012."},{"key":"e_1_3_2_1_12_1","first-page":"306","volume-title":"Dec. 2001","author":"Collins J. D.","unstructured":"J. D. Collins , D. M. Tullsen , H. Wang , and J. P. Shen , \" Dynamic speculative precomputation,\" in Proceedings of the 34th Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO) , Dec. 2001 , pp. 306 -- 317 . J. D. Collins, D. M. Tullsen, H. Wang, and J. P. Shen, \"Dynamic speculative precomputation,\" in Proceedings of the 34th Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO), Dec. 2001, pp. 306--317."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/379240.379248"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000079"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263597"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_1_17_1","volume-title":"Feb.","author":"Heirman W.","year":"2014","unstructured":"W. Heirman , T. E. Carlson , K. Van Craeynest , I. Hur , A. Jaleel , and L. Eeckhout , \" Undersubscribed threading on clustered cache architectures,\" in Proceedings of the IEEE 20th International Symposium on High Performance Computer Architecture (HPCA) , Feb. 2014 . W. Heirman, T. E. Carlson, K. Van Craeynest, I. Hur, A. Jaleel, and L. Eeckhout, \"Undersubscribed threading on clustered cache architectures,\" in Proceedings of the IEEE 20th International Symposium on High Performance Computer Architecture (HPCA), Feb. 2014."},{"key":"e_1_3_2_1_18_1","first-page":"431","volume-title":"Feb. 2009","author":"Hilton A.","unstructured":"A. Hilton , S. Nagarakatte , and A. Roth , \" iCFP: Tolerating all-level cache misses in in-order processors,\" in 15th International Symposium on High Performance Computer Architecture (HPCA) , Feb. 2009 , pp. 431 -- 442 . A. Hilton, S. Nagarakatte, and A. Roth, \"iCFP: Tolerating all-level cache misses in in-order processors,\" in 15th International Symposium on High Performance Computer Architecture (HPCA), Feb. 2009, pp. 431--442."},{"key":"e_1_3_2_1_20_1","first-page":"27","volume-title":"Mar. 2004","author":"Kim D.","unstructured":"D. Kim , S. S. Liao , P. H. Wang , J. del Cuvillo , X. Tian , X. Zou , H. Wang , D. Yeung , M. Girkar , and J. P. Shen , \" Physical experimentation with prefetching helper threads on Intel's hyper-threaded processors,\" in International Symposium on Code Generation and Optimization (CGO) , Mar. 2004 , p. 27 . D. Kim, S. S. Liao, P. H. Wang, J. del Cuvillo, X. Tian, X. Zou, H. Wang, D. Yeung, M. Girkar, and J. P. Shen, \"Physical experimentation with prefetching helper threads on Intel's hyper-threaded processors,\" in International Symposium on Code Generation and Optimization (CGO), Mar. 2004, p. 27."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1012268.1012270"},{"key":"e_1_3_2_1_22_1","first-page":"59","volume-title":"May 2002","author":"Lebeck A.","unstructured":"A. Lebeck , J. Koppanalil , T. Li , J. Patwardhan , and E. Rotenberg , \" A large, fast instruction window for tolerating cache misses,\" in Proceedings of the 29th Annual International Symposium on Computer Architecture (ISCA) , May 2002 , pp. 59 -- 70 . A. Lebeck, J. Koppanalil, T. Li, J. Patwardhan, and E. Rotenberg, \"A large, fast instruction window for tolerating cache misses,\" in Proceedings of the 29th Annual International Symposium on Computer Architecture (ISCA), May 2002, pp. 59--70."},{"key":"e_1_3_2_1_23_1","first-page":"694","volume-title":"Nov. 2011","author":"Li S.","unstructured":"S. Li , K. Chen , J. H. Ahn , J. B. Brockman , and N. P. Jouppi , \" CACTI-P: Architecture-level modeling for SRAM-based structures with advanced leakage reduction techniques,\" in 2011 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD) , Nov. 2011 , pp. 694 -- 701 . S. Li, K. Chen, J. H. Ahn, J. B. Brockman, and N. P. Jouppi, \"CACTI-P: Architecture-level modeling for SRAM-based structures with advanced leakage reduction techniques,\" in 2011 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 2011, pp. 694--701."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/377792.377856"},{"key":"e_1_3_2_1_25_1","first-page":"129","volume-title":"Feb. 2003","author":"Mutlu O.","unstructured":"O. Mutlu , J. Stark , C. Wilkerson , and Y. N. Patt , \" Runahead execution: An alternative to very large instruction windows for out-of-order processors,\" in Proceedings of the Ninth International Symposium on High-Performance Computer Architecture (HPCA) , Feb. 2003 , pp. 129 -- 140 . O. Mutlu, J. Stark, C. Wilkerson, and Y. N. Patt, \"Runahead execution: An alternative to very large instruction windows for out-of-order processors,\" in Proceedings of the Ninth International Symposium on High-Performance Computer Architecture (HPCA), Feb. 2003, pp. 129--140."},{"key":"e_1_3_2_1_26_1","first-page":"384","volume-title":"Oct. 2008","author":"Nekkalapu S.","unstructured":"S. Nekkalapu , H. Akkary , K. Jothi , R. Retnamma , and X. Song , \" A simple latency tolerant processor,\" in IEEE International Conference on Computer Design (ICCD) , Oct. 2008 , pp. 384 -- 389 . S. Nekkalapu, H. Akkary, K. Jothi, R. Retnamma, and X. Song, \"A simple latency tolerant processor,\" in IEEE International Conference on Computer Design (ICCD), Oct. 2008, pp. 384--389."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264201"},{"key":"e_1_3_2_1_28_1","unstructured":"F. J. Pollack \"New microarchitecture challenges in the coming generations of CMOS process technologies (keynote address) \" in Proceedings of the 32nd Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO) Nov. 1999.   F. J. Pollack \"New microarchitecture challenges in the coming generations of CMOS process technologies (keynote address) \" in Proceedings of the 32nd Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO) Nov. 1999."},{"key":"e_1_3_2_1_29_1","volume-title":"Aug.","author":"Ramey C.","year":"2011","unstructured":"C. Ramey , \"TILE-Gx10 0 manycore processor : Acceleration interfaces and architecture,\" in Proceedings of the 23th Hot Chips Symposium , Aug. 2011 . C. Ramey, \"TILE-Gx100 manycore processor: Acceleration interfaces and architecture,\" in Proceedings of the 23th Hot Chips Symposium, Aug. 2011."},{"key":"e_1_3_2_1_30_1","first-page":"37","volume-title":"Jan. 2001","author":"Roth A.","unstructured":"A. Roth and G. S. Sohi , \" Speculative data-driven multithreading,\" in Proceedings of the Seventh International Symposium on High-Performance Computer Architecture (HPCA) , Jan. 2001 , pp. 37 -- 48 . A. Roth and G. S. Sohi, \"Speculative data-driven multithreading,\" in Proceedings of the Seventh International Symposium on High-Performance Computer Architecture (HPCA), Jan. 2001, pp. 37--48."},{"key":"e_1_3_2_1_31_1","volume-title":"Jun.","author":"Salverda P.","year":"2007","unstructured":"P. Salverda and C. Zilles , \" Dependence-based scheduling revisited: A tale of two baselines,\" in Sixth Annual Workshop on Duplicating, Deconstructing, and Debunking (WDDD) , Jun. 2007 . P. Salverda and C. Zilles, \"Dependence-based scheduling revisited: A tale of two baselines,\" in Sixth Annual Workshop on Duplicating, Deconstructing, and Debunking (WDDD), Jun. 2007."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605403"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/285930.285982"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1024393.1024407"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/378993.379247"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1464039.1464045"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.111.0025"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.23"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/232973.232993"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1984.5010248"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/379240.379246"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339676"}],"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\/2749469.2750407","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2749469.2750407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:00:40Z","timestamp":1750215640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2749469.2750407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,13]]},"references-count":42,"alternative-id":["10.1145\/2749469.2750407","10.1145\/2749469"],"URL":"https:\/\/doi.org\/10.1145\/2749469.2750407","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2872887.2750407","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"}}]}}