{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T16:11:54Z","timestamp":1746115914089,"version":"3.40.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,5,1]],"date-time":"2013-05-01T00:00:00Z","timestamp":1367366400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s10766-013-0247-8","type":"journal-article","created":{"date-parts":[[2013,5,1]],"date-time":"2013-05-01T12:52:12Z","timestamp":1367412732000},"page":"435-455","source":"Crossref","is-referenced-by-count":0,"title":["Bandwidth Adaptive Cache Coherence Optimizations for Chip Multiprocessors"],"prefix":"10.1007","volume":"42","author":[{"given":"Abdullah","family":"Kayi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Serres","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarek","family":"El-Ghazawi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,5,1]]},"reference":[{"key":"247_CR1","unstructured":"NAS Parallel Benchmarks: OpenMP version developed by the Omni group http:\/\/www.hpcs.cs.tsukuba.ac.jp\/omni-openmp"},{"key":"247_CR2","doi-asserted-by":"crossref","unstructured":"Acacio, M., Gonz\u00e1lez, J., Garc\u00eda, J., Duato, J.: Owner prediction for accelerating cache-to-cache transfer misses in a cc-NUMA architecture. In: Proceedings of the 2002 ACM\/IEEE Conference on Supercomputing, pp. 1\u201312. IEEE Computer Society Press Los Alamitos, CA, USA (2002)","DOI":"10.1109\/SC.2002.10063"},{"key":"247_CR3","doi-asserted-by":"crossref","unstructured":"Acacio, M.E., Gonz\u00e1lez, J., Garc\u00eda, J.M., Duato, J.: The use of prediction for accelerating upgrade misses in cc-NUMA multiprocessors. In: IEEE PACT, pp. 155\u2013164. IEEE Computer Society (2002)","DOI":"10.1109\/PACT.2002.1106014"},{"key":"247_CR4","doi-asserted-by":"crossref","unstructured":"Alam, S.R., Barrett, R.F., Kuehn, J.A., Roth, P.C., Vetter, J.S.: Characterization of scientific workloads on systems with multi-core processors. In: IISWC, pp. 225\u2013236. IEEE (2006)","DOI":"10.1109\/IISWC.2006.302747"},{"key":"247_CR5","doi-asserted-by":"crossref","unstructured":"Anderson, C., Karlin, A.R.: Two adaptive hybrid cache coherency protocols. In: International Symposium on High-Performance Computer Architecture (HPCA), pp. 303\u2013313 (1996)","DOI":"10.1109\/HPCA.1996.501195"},{"key":"247_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, L., Carter, J.B.: Extending cc-numa systems to support write update optimizations. In: SC \u201908: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, p. 30. IEEE\/ACM (2008)","DOI":"10.1109\/SC.2008.5215354"},{"key":"247_CR7","doi-asserted-by":"crossref","unstructured":"Chu, M., Ravindran, R., Mahlke, S.: Data access partitioning for fine-grain parallelism on multicore architectures. In: MICRO \u201907: Proceedings of the 40th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 369\u2013380. IEEE Computer Society, Washington, DC, USA (2007). doi: 10.1109\/MICRO.2007.11","DOI":"10.1109\/MICRO.2007.11"},{"key":"247_CR8","doi-asserted-by":"crossref","unstructured":"Cox, A.L., Fowler, R.J.: Adaptive cache coherency for detecting migratory shared data. In: International Symposium on Computer Architecture (ISCA), pp. 98\u2013108 (1993)","DOI":"10.1109\/ISCA.1993.698549"},{"key":"247_CR9","doi-asserted-by":"crossref","unstructured":"Dahlgren, F.: Boosting the performance of hybrid snooping cache protocols. In: ISCA \u201995: Proceedings of the 22nd Annual International Symposium on Computer Architecture, pp. 60\u201369. ACM, New York, NY, USA (1995). doi: 10.1145\/223982.223998","DOI":"10.1145\/223982.223998"},{"key":"247_CR10","doi-asserted-by":"crossref","unstructured":"Dahlgren, F., Stenstr\u00f6m, P.: Reducing the write traffic for a hybrid cache protocol. In: International Conference on Parallel Processing (ICPP), pp. 166\u2013173 (1994)","DOI":"10.1109\/ICPP.1994.175"},{"key":"247_CR11","doi-asserted-by":"crossref","unstructured":"Eggers, S.J., Katz, R.H.: Evaluating the performance of four snooping cache coherency protocols. SIGARCH Comput. Archit. News 17(3), 2\u201315 (1989). doi: 10.1145\/74926.74927","DOI":"10.1145\/74926.74927"},{"key":"247_CR12","doi-asserted-by":"crossref","unstructured":"Eisley, N., Peh, L.S., Shang, L.: In-network cache coherence. In: MICRO 39: Proceedings of the 39th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 321\u2013332. IEEE Computer Society, Washington, DC, USA (2006). doi: 10.1109\/MICRO.2006.27","DOI":"10.1109\/MICRO.2006.27"},{"key":"247_CR13","doi-asserted-by":"crossref","unstructured":"Eisley, N., Peh, L.S., Shang, L.: Leveraging on-chip networks for data cache migration in chip multiprocessors. In: PACT \u201908, pp. 197\u2013207. ACM, New York, NY, USA (2008). doi: 10.1145\/1454115.1454144","DOI":"10.1145\/1454115.1454144"},{"key":"247_CR14","doi-asserted-by":"crossref","unstructured":"Fensch, C., Cintra, M.: An OS-based alternative to full hardware coherence on tiled CMPs. In: 14th International Symposium on High Performance Computer Architecture (HPCA), pp. 355\u2013366. IEEE (2008). doi: 10.1109\/HPCA.2008.4658652","DOI":"10.1109\/HPCA.2008.4658652"},{"issue":"5","key":"247_CR15","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/MC.2005.160","volume":"38","author":"D Geer","year":"2005","unstructured":"Geer, D.: Industry trends: chip makers turn to multicore processors. IEEE Comput. 38(5), 11\u201313 (2005)","journal-title":"IEEE Comput."},{"key":"247_CR16","unstructured":"Ghosh, D., Carter, J.B., III, H.D.: Perceptron-based coherence predictors. In: Proceedings of 2nd Workshop on Chip Multiprocessor Memory Systems and Interconnects (CMP-MSI), in Conjunction with ISCA 2008 (2008)"},{"key":"247_CR17","doi-asserted-by":"crossref","unstructured":"Gorder, P.F.: Multicore processors for science and engineering. Comput. Sci. Eng. 9(2), 3\u20137 (2007). doi: 10.1109\/MCSE.2007.35","DOI":"10.1109\/MCSE.2007.35"},{"key":"247_CR18","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1006\/jpdc.1996.0164","volume":"39","author":"HK Grahn","year":"1996","unstructured":"Grahn, H.K., Stenstr\u00f6m, P.: Evaluation of a competitive-update cache coherence protocol with migratory data detection. J. Parallel Distrib Comput 39, 39\u201342 (1996)","journal-title":"J. Parallel Distrib Comput"},{"key":"247_CR19","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/BF01762111","volume":"3","author":"AR Karlin","year":"1988","unstructured":"Karlin, A.R., Manasse, M.S., Rudolph, L., Sleator, D.D.: Competitive snoopy caching. Algorithmica 3, 77\u2013119 (1988)","journal-title":"Algorithmica"},{"key":"247_CR20","doi-asserted-by":"crossref","unstructured":"Kaxiras, S., Goodman, J.R.: Improving cc-NUMA performance using instruction-based prediction. In: International Symposium on High-Performance Computer Architecture (HPCA), pp. 161 (1999)","DOI":"10.1109\/HPCA.1999.744359"},{"key":"247_CR21","doi-asserted-by":"crossref","unstructured":"Kaxiras, S., Young, C.: Coherence communication prediction in shared-memory multiprocessors. In: International Symposium on High-Performance Computer Architecture (HPCA), pp. 156\u2013167 (2000)","DOI":"10.1109\/HPCA.2000.824347"},{"key":"247_CR22","doi-asserted-by":"crossref","unstructured":"Kayi, A., Kornkven, E., El-Ghazawi, T., Al-Bahra, S., Newby, G.: Performance evaluation of clusters with ccNUMA nodes: a case study. In: HPCC \u201908, pp. 320\u2013327 (2008)","DOI":"10.1109\/HPCC.2008.111"},{"key":"247_CR23","doi-asserted-by":"crossref","unstructured":"Lai, A.C., Falsafi, B.: Memory sharing predictor: The key to a speculative coherent dsm. In: ISCA \u201999: Proceedings of the 26th, Annual International Symposium on Computer Architecture, pp. 172\u2013183 (1999)","DOI":"10.1145\/307338.300994"},{"key":"247_CR24","doi-asserted-by":"crossref","unstructured":"Leventhal, S., Franklin, M.: Perceptron based consumer prediction in shared-memory multiprocessors. In: ICCD 2006: International Conference on, Computer Design, pp. 148\u2013154 (2006). doi: 10.1109\/ICCD.2006.4380808","DOI":"10.1109\/ICCD.2006.4380808"},{"issue":"2","key":"247_CR25","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/2.982916","volume":"35","author":"PS Magnusson","year":"2002","unstructured":"Magnusson, P.S., Christensson, M., Eskilson, J., Forsgren, D., H\u00e5llberg, G., H\u00f6gberg, J., Larsson, F., Moestedt, A., Werner, B.: Simics: a full system simulation platform. IEEE Comput. 35(2), 50\u201358 (2002)","journal-title":"IEEE Comput."},{"key":"247_CR26","doi-asserted-by":"crossref","unstructured":"Martin, M.M.K.: Formal verification and its impact on the snooping versus directory protocol debate. In: ICCD 2005: International Conference on Computer Design, pp. 543\u2013449. IEEE Computer Society (2005)","DOI":"10.1109\/ICCD.2005.58"},{"key":"247_CR27","doi-asserted-by":"crossref","unstructured":"Martin, M.M.K., Harper, P.J., Sorin, D.J., Hill, M.D., Wood, D.A.: Using destination-set prediction to improve the latency\/bandwidth tradeoff in shared-memory multiprocessors. In: International Symposium on Computer Architecture (ISCA), pp. 206\u2013217. IEEE Computer Society (2003)","DOI":"10.1145\/859618.859642"},{"key":"247_CR28","doi-asserted-by":"crossref","unstructured":"Martin, M.M.K., Sorin, D.J., Hill, M.D., Wood, D.A.: Bandwidth adaptive snooping. In: International Symposium on High-Performance Computer Architecture (HPCA), pp. 251\u2013262 (2002)","DOI":"10.1109\/HPCA.2002.995715"},{"key":"247_CR29","doi-asserted-by":"crossref","unstructured":"Marty, M.R., Bingham, J.D., Hill, M.D., Hu, A.J., Martin, M.M.K., Wood, D.A.: Improving multiple-cmp systems using token coherence. In: ISCA \u201905: Proceedings of the 32nd Annual International Symposium on Computer Architecture, pp. 328\u2013339. IEEE Computer Society (2005)","DOI":"10.1109\/HPCA.2005.17"},{"issue":"8","key":"247_CR30","first-page":"114","volume":"38","author":"GE Moore","year":"1965","unstructured":"Moore, G.E.: Cramming more components onto integrated circuits. Electronics 38(8), 114\u2013117 (1965)","journal-title":"Electronics"},{"key":"247_CR31","doi-asserted-by":"crossref","unstructured":"Mukherjee, S.S., Hill, M.D.: Using prediction to accelerate coherence protocols. In: International Symposium on Computer Architecture (ISCA), pp. 179\u2013190 (1998)","DOI":"10.1145\/279361.279386"},{"key":"247_CR32","doi-asserted-by":"crossref","unstructured":"Nilsson, H., Stenstr\u00f6m, P.: An adaptive update-based cache coherence protocol for reduction of miss rate and traffic. In: Proceedings of Parallel Architectures and Languages Europe (PARLE), pp. 363\u2013374. Springer (1994)","DOI":"10.1007\/3-540-58184-7_115"},{"key":"247_CR33","doi-asserted-by":"crossref","unstructured":"Nilsson, J., Landin, A., Stenstr\u00f6m, P.: The coherence predictor cache: a resource-efficient and accurate coherence prediction infrastructure. In: IPDPS \u201903: Proceedings of the International Parallel and Distributed Processing Symposium, p. 10. IEEE Computer Society (2003)","DOI":"10.1109\/IPDPS.2003.1213084"},{"key":"247_CR34","doi-asserted-by":"crossref","unstructured":"Raghavan, A., Blundell, C., Martin, M.M.K.: Token tenure: patching token counting using directory-based cache coherence. In: MICRO, pp. 47\u201358. IEEE Computer Society (2008)","DOI":"10.1109\/MICRO.2008.4771778"},{"key":"247_CR35","doi-asserted-by":"crossref","unstructured":"Raynaud, A., Zhang, Z., Torrellas, J.: Distance-adaptive update protocols for scalable shared-memory multiprocessors. In: HPCA \u201996: Proceedings of the Second International Symposium on High-Performance Computer, Architecture, pp. 323\u2013334 (1996). doi: 10.1109\/HPCA.1996.501197","DOI":"10.1109\/HPCA.1996.501197"},{"key":"247_CR36","doi-asserted-by":"crossref","unstructured":"Stenstr\u00f6m, P., Brorsson, M., Sandberg, L.: An adaptive cache coherence protocol optimized for migratory sharing. In: International Symposium on Computer Architecture (ISCA), pp. 109\u2013118 (1993)","DOI":"10.1109\/ISCA.1993.698550"},{"key":"247_CR37","doi-asserted-by":"crossref","unstructured":"Woo, S.C., Ohara, M., Torrie, E., Singh, J.P., Gupta, A.: The SPLASH-2 Programs: characterization and methodological considerations. In: ISCA \u201995, pp. 24\u201336 (1995)","DOI":"10.1145\/225830.223990"},{"key":"247_CR38","doi-asserted-by":"crossref","unstructured":"Yeh, T.Y., Patt, Y.N.: Alternative implementations of two-level adaptive branch prediction. In: International Symposium on Computer Architecture (ISCA), pp. 124\u2013134 (1992)","DOI":"10.1145\/146628.139709"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0247-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-013-0247-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0247-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T07:46:20Z","timestamp":1745999180000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-013-0247-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,1]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["247"],"URL":"https:\/\/doi.org\/10.1007\/s10766-013-0247-8","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2013,5,1]]}}}