{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:51Z","timestamp":1740123531055,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T00:00:00Z","timestamp":1551052800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s11227-019-02789-7","type":"journal-article","created":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T01:59:38Z","timestamp":1551059978000},"page":"5161-5188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cache control techniques to provide QoS on real systems"],"prefix":"10.1007","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5488-0651","authenticated-orcid":false,"given":"Krupa","family":"Sivakumaran","sequence":"first","affiliation":[]},{"given":"Arul","family":"Siromoney","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,25]]},"reference":[{"key":"2789_CR1","unstructured":"Advanced Micro Devices Inc. (2019) AMD64 Architecture programmer\u2019s manual volume 2: system programming. \n                    http:\/\/support.amd.com\/TechDocs\/24593.pdf\n                    \n                  . Accessed 11 Feb 2019"},{"key":"2789_CR2","doi-asserted-by":"crossref","unstructured":"Chang J, Sohi GS (2007) Cooperative cache partitioning for chip multiprocessors. In: Proceedings of the 21st Annual ACM International Conference on Supercomputing, pp 242\u2013252","DOI":"10.1145\/1274971.1275005"},{"issue":"3","key":"2789_CR3","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1145\/2508148.2485949","volume":"41","author":"H Cook","year":"2013","unstructured":"Cook H, Moreto M, Bird S, Dao K, Patterson DA, Asanovic K (2013) A hardware evaluation of cache partitioning to improve utilization and energy-efficiency while preserving responsiveness. ACM SIGARCH Comput Architect News 41(3):308\u2013319","journal-title":"ACM SIGARCH Comput Architect News"},{"issue":"3","key":"2789_CR4","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1145\/1735971.1736058","volume":"45","author":"E Ebrahimi","year":"2010","unstructured":"Ebrahimi E, Lee CJ, Mutlu O, Patt YN (2010) Fairness via source throttling: a configurable and high-performance fairness substrate for multi-core memory systems. ACM SIGPLAN Not 45(3):335\u2013346","journal-title":"ACM SIGPLAN Not"},{"key":"2789_CR5","doi-asserted-by":"crossref","unstructured":"El-Sayed N, Mukkara A, Tsai PA, Kasture H, Ma X, Sanchez D (2018) Kpart: a hybrid cache partitioning-sharing technique for commodity multicores. In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp 104\u2013117. IEEE","DOI":"10.1109\/HPCA.2018.00019"},{"issue":"3","key":"2789_CR6","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/MM.2008.44","volume":"28","author":"S Eyerman","year":"2008","unstructured":"Eyerman S, Eeckhout L (2008) System-level performance metrics for multiprogram workloads. IEEE Micro 28(3):42\u201353","journal-title":"IEEE Micro"},{"issue":"4","key":"2789_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1186736.1186737","volume":"34","author":"JL Henning","year":"2006","unstructured":"Henning JL (2006) SPEC CPU2006 benchmark descriptions. ACM SIGARCH Comput Architect News 34(4):1\u201317","journal-title":"ACM SIGARCH Comput Architect News"},{"key":"2789_CR8","doi-asserted-by":"crossref","unstructured":"Herdrich A, Illikkal R, Iyer R, Newell D, Chadha V, Moses J (2009) Rate-based QoS techniques for cache\/memory in CMP platforms. In: Proceedings of the 23rd ACM International Conference on Supercomputing, pp 479\u2013488","DOI":"10.1145\/1542275.1542342"},{"key":"2789_CR9","doi-asserted-by":"crossref","unstructured":"Herdrich A, Verplanke E, Autee P, Illikkal R, Gianos C, Singhal R, Iyer R (2016) Cache QoS: from concept to reality in the Intel\u00ae Xeon\u00ae processor E5-2600 v3 product family. In: Proceedings of the 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp 657\u2013668","DOI":"10.1109\/HPCA.2016.7446102"},{"key":"2789_CR10","doi-asserted-by":"crossref","unstructured":"Hsu LR, Reinhardt SK, Iyer R, Makineni S (2006) Communist, utilitarian, and capitalist cache policies on CMPs: caches as a shared resource. In: Proceedings of the 15th ACM International Conference on Parallel Architectures and Compilation Techniques, pp 13\u201322","DOI":"10.1145\/1152154.1152161"},{"issue":"4","key":"2789_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/1773394.1773396","volume":"37","author":"R Illikkal","year":"2010","unstructured":"Illikkal R, Chadha V, Herdrich A, Iyer R, Newell D (2010) PIRATE: QoS and performance management in CMP architectures. ACM SIGMETRICS Perform Eval Rev 37(4):3\u201310","journal-title":"ACM SIGMETRICS Perform Eval Rev"},{"key":"2789_CR12","unstructured":"Intel Corporation (2019) Intel 64 and IA-32 architectures software developer\u2019s manual. \n                    http:\/\/www.intel.in\/content\/www\/in\/en\/processors\/architectures-software-developer-manuals.html\n                    \n                  . Accessed 11 Feb 2019"},{"key":"2789_CR13","doi-asserted-by":"crossref","unstructured":"Iyer R (2004) CQoS: a framework for enabling QoS in shared caches of CMP platforms. In: Proceedings of the 18th Annual ACM International Conference on Supercomputing, pp 257\u2013266","DOI":"10.1145\/1006209.1006246"},{"issue":"1","key":"2789_CR14","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/1269899.1254886","volume":"35","author":"R Iyer","year":"2007","unstructured":"Iyer R, Zhao L, Guo F, Illikkal R, Makineni S, Newell D, Solihin Y, Hsu L, Reinhardt S (2007) QoS policies and architecture for cache\/memory in CMP platforms. ACM SIGMETRICS Perform Eval Rev 35(1):25\u201336","journal-title":"ACM SIGMETRICS Perform Eval Rev"},{"issue":"4","key":"2789_CR15","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1109\/TC.2013.18","volume":"63","author":"D Kaseridis","year":"2014","unstructured":"Kaseridis D, Iqbal MF, John LK (2014) Cache friendliness-aware management of shared last-level caches for high performance multi-core systems. IEEE Trans Comput 63(4):874\u2013887","journal-title":"IEEE Trans Comput"},{"key":"2789_CR16","unstructured":"Kim S, Chandra D, Solihin Y (2004) Fair cache sharing and partitioning in a chip multiprocessor architecture. In: Proceedings of the 13th IEEE International Conference on Parallel Architectures and Compilation Techniques, pp 111\u2013122"},{"issue":"3","key":"2789_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2355585.2355590","volume":"9","author":"B Li","year":"2012","unstructured":"Li B, Peh LS, Zhao L, Iyer R (2012) Dynamic QoS management for chip multiprocessors. ACM Trans Archit Code Optim (TACO) 9(3):1\u201329","journal-title":"ACM Trans Archit Code Optim (TACO)"},{"issue":"5","key":"2789_CR18","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1016\/j.jpdc.2010.10.013","volume":"71","author":"B Li","year":"2011","unstructured":"Li B, Zhao L, Iyer R, Peh LS, Leddige M, Espig M, Lee SE, Newell D (2011) CoQoS: coordinating QoS-aware shared resources in NoC-based SoCs. J Parallel Distrib Comput 71(5):700\u2013713","journal-title":"J Parallel Distrib Comput"},{"key":"2789_CR19","unstructured":"Lin J, Lu Q, Ding X, Zhang Z, Zhang X, Sadayappan P (2008) Gaining insights into multicore cache partitioning: bridging the gap between simulation and real systems. In: Proceedings of the 14th IEEE International Symposium on High Performance Computer Architecture (HPCA), pp 367\u2013378"},{"key":"2789_CR20","unstructured":"Luo K, Gummaraju J, Franklin M (2001) Balancing thoughput and fairness in SMT processors. In: Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, pp 164\u2013171"},{"key":"2789_CR21","doi-asserted-by":"crossref","unstructured":"Mars J, Tang L, Hundt R, Skadron K, Soffa ML (2011) Bubble-up: increasing utilization in modern warehouse scale computers via sensible co-locations. In: Proceedings of the 44th Annual IEEE\/ACM International Symposium on Microarchitecture, pp 248\u2013259","DOI":"10.1145\/2155620.2155650"},{"issue":"2","key":"2789_CR22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1145\/1273440.1250671","volume":"35","author":"KJ Nesbit","year":"2007","unstructured":"Nesbit KJ, Laudon J, Smith JE (2007) Virtual private caches. ACM SIGARCH Comput Archit News 35(2):57\u201368","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"2789_CR23","unstructured":"Papadakis I, Nikas K, Karakostas V, Goumas G, Koziris N (2017) Improving QoS and utilisation in modern multi-core servers with dynamic cache partitioning. In: Proceedings of the Joint Workshops on Co-Scheduling of HPC Applications (COSH 2017) and Virtualization Solutions for High-Performance Computing, pp 21\u201326"},{"key":"2789_CR24","unstructured":"Qureshi MK, Patt YN (2006) Utility-based cache partitioning: a low-overhead, high-performance, runtime mechanism to partition shared caches. In: Proceedings of the 39th Annual IEEE\/ACM International Symposium on Microarchitecture, pp 423\u2013432"},{"key":"2789_CR25","doi-asserted-by":"crossref","unstructured":"Rafique N, Lim WT, Thottethodi M (2006) Architectural support for operating system-driven CMP cache management. In: Proceedings of the 15th ACM International Conference on Parallel Architectures and Compilation Techniques, pp 2\u201312","DOI":"10.1145\/1152154.1152160"},{"key":"2789_CR26","doi-asserted-by":"crossref","unstructured":"Reddy R, Petrov P (2007) Eliminating inter-process cache interference through cache reconfigurability for real-time and low-power embedded multi-tasking systems. In: Proceedings of the 2007 ACM International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, pp 198\u2013207","DOI":"10.1145\/1289881.1289917"},{"key":"2789_CR27","doi-asserted-by":"crossref","unstructured":"Sharifi A, Srikantaiah S, Mishra AK, Kandemir M, Das CR (2011) METE: meeting end-to-end QoS in multicores through system-wide resource management. In: Proceedings of the ACM SIGMETRICS Joint International Conference on Measurement and Modeling of Computer Systems, pp 13\u201324","DOI":"10.1145\/1993744.1993747"},{"issue":"3","key":"2789_CR28","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1007\/s10766-016-0443-4","volume":"45","author":"K Sivakumaran","year":"2017","unstructured":"Sivakumaran K, Siromoney A (2017) Priority based yield of shared cache to provide cache QoS in multicore systems. Int J Parallel Program 45(3):634\u2013656","journal-title":"Int J Parallel Program"},{"issue":"11","key":"2789_CR29","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1145\/356989.357011","volume":"35","author":"A Snavely","year":"2000","unstructured":"Snavely A, Tullsen DM (2000) Symbiotic jobscheduling for a simultaneous mutlithreading processor. ACM SIGPLAN Not 35(11):234\u2013244","journal-title":"ACM SIGPLAN Not"},{"issue":"1","key":"2789_CR30","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1145\/1353534.1346299","volume":"36","author":"S Srikantaiah","year":"2008","unstructured":"Srikantaiah S, Kandemir M, Irwin MJ (2008) Adaptive set pinning: managing shared caches in chip multiprocessors. ACM SIGARCH Comput Archit News 36(1):135\u2013144","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"2789_CR31","unstructured":"Subramanian L, Seshadri V, Kim Y, Jaiyen B, Mutlu O (2018) Predictable performance and fairness through accurate slowdown estimation in shared main memory systems. arXiv preprint \n                    arXiv:1805.05926"},{"issue":"1","key":"2789_CR32","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/B:SUPE.0000014800.27383.8f","volume":"28","author":"GE Suh","year":"2004","unstructured":"Suh GE, Rudolph L, Devadas S (2004) Dynamic partitioning of shared cache memory. J Supercomput 28(1):7\u201326","journal-title":"J Supercomput"},{"key":"2789_CR33","doi-asserted-by":"crossref","unstructured":"Suo G, Yang X (2009) Balancing parallel applications on multi-core processors based on cache partitioning. In: Proceedings of the 2009 IEEE International Symposium on Parallel and Distributed Processing with Applications, pp 190\u2013195","DOI":"10.1109\/ISPA.2009.37"},{"key":"2789_CR34","unstructured":"Tam D, Azimi R, Soares L, Stumm M (2007) Managing shared L2 caches on multicore systems in software. In: Proceedings of the Workshop on the Interaction Between Operating Systems and Computer Architecture, pp 26\u201333"},{"key":"2789_CR35","doi-asserted-by":"crossref","unstructured":"Wang X, Chen S, Setter J, Mart\u00ednez JF (2017) Swap: effective fine-grain management of shared last-level caches with minimum hardware support. In: 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp 121\u2013132. IEEE","DOI":"10.1109\/HPCA.2017.65"},{"issue":"3","key":"2789_CR36","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1145\/1555815.1555778","volume":"37","author":"Y Xie","year":"2009","unstructured":"Xie Y, Loh GH (2009) PIPP: promotion\/insertion pseudo-partitioning of multi-core shared caches. ACM SIGARCH Comput Archit News 37(3):174\u2013183","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"2789_CR37","doi-asserted-by":"crossref","unstructured":"Ye Y, West R, Cheng Z, Li Y (2014) COLORIS: a dynamic cache partitioning system using page coloring. In: Proceedings of the 23rd ACM International Conference on Parallel Architectures and Compilation, pp 381\u2013392","DOI":"10.1145\/2628071.2628104"},{"key":"2789_CR38","doi-asserted-by":"crossref","unstructured":"Zhang X, Dwarkadas S, Shen K (2009) Towards practical page coloring-based multicore cache management. In: Proceedings of the 4th ACM European Conference on Computer Systems, pp 89\u2013102","DOI":"10.1145\/1519065.1519076"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-02789-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02789-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02789-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,24]],"date-time":"2020-02-24T19:22:16Z","timestamp":1582572136000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-02789-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,25]]},"references-count":38,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["2789"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-02789-7","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2019,2,25]]},"assertion":[{"value":"25 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}