{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T13:08:43Z","timestamp":1720184923229},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,6,24]],"date-time":"2014-06-24T00:00:00Z","timestamp":1403568000000},"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":[[2014,9]]},"DOI":"10.1007\/s11227-014-1240-8","type":"journal-article","created":{"date-parts":[[2014,6,23]],"date-time":"2014-06-23T02:55:53Z","timestamp":1403492153000},"page":"1491-1516","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimizing memory access traffic via runtime thread migration for on-chip distributed memory systems"],"prefix":"10.1007","volume":"69","author":[{"given":"Weiwei","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianzhou","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,6,24]]},"reference":[{"issue":"1","key":"1240_CR1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/216585.216588","volume":"23","author":"WA Wulf","year":"1995","unstructured":"Wulf WA, McKee SA (1995) Hitting the memory wall: implications of the obvious. ACM SIGARCH Comput Archit News 23(1):20\u201324","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"1240_CR2","doi-asserted-by":"crossref","unstructured":"Dashti M, Fedorova A, Funston J, Gaud F, Lachaize R, Lepers B, and Roth M (2013) Traffic management: a holistic approach to memory placement on numa systems. In: Proceedings of the 18th international conference on architectural support for programming languages and operating systems, pp 381\u2013394, ACM","DOI":"10.1145\/2499368.2451157"},{"key":"1240_CR3","volume-title":"Sharing aware scheduling on multicore systems","author":"A Kamali","year":"2010","unstructured":"Kamali A (2010) Sharing aware scheduling on multicore systems. Applied Science, School of Computing Science, USA"},{"issue":"3","key":"1240_CR4","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1145\/1272998.1273004","volume":"41","author":"D Tam","year":"2007","unstructured":"Tam D, Azimi R, Stumm M (2007) Thread clustering: sharing-aware scheduling on SMP-CMP-SMT multiprocessors. ACM SIGOPS Oper Syst Rev 41(3):47\u201358","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"1240_CR5","doi-asserted-by":"crossref","unstructured":"Chen TS (1999) Task migration in 2D wormhole-routed mesh multicomputers. In: High performance computing. Springer, Berlin, pp 354\u2013362","DOI":"10.1007\/BFb0094937"},{"issue":"1s","key":"1240_CR6","first-page":"56","volume":"12","author":"M Misler","year":"2013","unstructured":"Misler M, Jerger NE (2013) Moths: mobile threads for on-chip networks. ACM Trans Embed Comput Syst (TECS) 12(1s):56","journal-title":"ACM Trans Embed Comput Syst (TECS)"},{"key":"1240_CR7","doi-asserted-by":"crossref","unstructured":"Wang C, Yu L, Liu L, Chen T (2012) Packet triggered prediction based task migration for network-on-chip. In: 20th IEEE Euromicro international conference on parallel, distributed and network-based processing (PDP), pp 491\u2013498","DOI":"10.1109\/PDP.2012.37"},{"key":"1240_CR8","unstructured":"Dally WJ, Towles B (2001) Route packets, not wires: on-chip interconnection networks. In: Proceedings of the IEEE design automation conference, pp 684\u2013689"},{"issue":"1","key":"1240_CR9","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/2.976921","volume":"35","author":"L Benini","year":"2002","unstructured":"Benini L, De Micheli G (2002) Networks on chips: a new SoC paradigm. Computer 35(1):70\u201378","journal-title":"Computer"},{"key":"1240_CR10","unstructured":"Dally WJ, Towles BP (2004) Principles and practices of interconnection networks. Access online via Elsevier, London"},{"key":"1240_CR11","doi-asserted-by":"crossref","unstructured":"Bienia C, Kumar S, Singh JP, Li K (2008) The PARSEC benchmark suite: characterization and architectural implications. In: Proceedings of the 17th international conference on parallel architectures and compilation techniques, ACM, pp 72\u201381","DOI":"10.1145\/1454115.1454128"},{"key":"1240_CR12","unstructured":"Lachaize R, Lepers B, Quma V (2012) MemProf: a memory profiler for NUMA multicore systems. In: USENIX ATC 12"},{"issue":"7","key":"1240_CR13","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.jpdc.2007.01.010","volume":"67","author":"X Shen","year":"2007","unstructured":"Shen X, Zhong Y, Ding C (2007) Predicting locality phases for dynamic memory optimization. J Parallel Distrib Comput 67(7):783\u2013796","journal-title":"J Parallel Distrib Comput"},{"key":"1240_CR14","doi-asserted-by":"crossref","unstructured":"Abts D, Enright Jerger ND, Kim J, Gibson D, Lipasti MH (2009) Achieving predictable performance through better memory controller placement in many-core CMPs. ACM SIGARCH Comput Archit News 37(3):451\u2013461","DOI":"10.1145\/1555815.1555810"},{"key":"1240_CR15","doi-asserted-by":"crossref","unstructured":"Rangan KK, Wei G, Brooks Y (2009) Thread motion: fine-grained power management for multi-core systems. In: Proceedings of the international symposium on computer architecture","DOI":"10.1145\/1555754.1555793"},{"key":"1240_CR16","unstructured":"Lei T, Kumar S (2003) A two-step genetic algorithm for mapping task graphs to a network on chip architecture. In: Proceedings of the Euromicro symposium on digital system design, pp 180C187"},{"key":"1240_CR17","doi-asserted-by":"crossref","unstructured":"Rixner S, Dally WJ, Kapasi UJ, Mattson P, Owens JD (2000) Memory access scheduling. ACM SIGARCH Comput Archit News 28(2):128\u2013138","DOI":"10.1145\/342001.339668"},{"key":"1240_CR18","doi-asserted-by":"crossref","unstructured":"Rixner S (2004) Memory controller optimizations for web servers. In: Proceedings of the 37th annual IEEE\/ACM international symposium on microarchitecture, pp 355\u2013366","DOI":"10.1109\/MICRO.2004.22"},{"key":"1240_CR19","unstructured":"Jog A, Bolotin E et al (2004) application-aware memory system for fair and efficient execution of concurrent GPGPU applications [C]. In: Proceedings of workshop on general purpose processing using GPUs"},{"key":"1240_CR20","unstructured":"(2003) Micron, 1gb, x4, x8, x16, ddr3 sdram datasheet. http:\/\/www.micron.com\/products\/dram\/ddr3-sdram . 25 Sep 2013"},{"key":"1240_CR21","doi-asserted-by":"crossref","unstructured":"Binkert N, Beckmann B, Black G, Reinhardt SK, Saidi A, Basu A, Hestness J, Hower DR, Krishna T, Sardashti S et al (2011) The gem5 simulator. ACM SIGARCH Comput Archit News 39:1C7","DOI":"10.1145\/2024716.2024718"},{"key":"1240_CR22","unstructured":"Wang HS, Zhu X, Peh L-S, Malik S (2002) Orion: a power-performance simulator for interconnection networks. In: Proceedingsof the 35th annual IEEE\/ACM international symposium on microarchitecture, MICRO-35, pp 294\u2013305"},{"key":"1240_CR23","unstructured":"Lozi JP, David F, Thomas G et al (2012) Remote core locking: migrating critical-section execution to improve the performance of multithreaded applications. In: Proceedings of the Usenix annual technical Conference, pp 65\u201376"},{"key":"1240_CR24","doi-asserted-by":"crossref","unstructured":"Bertozzi S, Acquaviva A, Bertozzi D, Poggiali A (2006) Supporting task migration in multi-processor systems-on-chip: a feasibility study. In: Proceedings of the conference on design, automation and test in Europe, pp 15\u201320. European Design and Automation Association","DOI":"10.1109\/DATE.2006.243952"},{"key":"1240_CR25","unstructured":"Katre KM, Ramaprasad H, Sarkar A, Mueller F (2009) Policies for migration of real-time tasks in embedded multi-core systems. In: Real-time systems symposium, pp 17\u201320"},{"key":"1240_CR26","doi-asserted-by":"crossref","unstructured":"Goodarzi B, Sarbazi-Azad H (2011) Task migration in mesh NoCs over virtual point-to-point connections. In: 19th IEEE Euromicro international conference on parallel, distributed and network-based processing (PDP), pp 463\u2013469","DOI":"10.1109\/PDP.2011.71"},{"key":"1240_CR27","doi-asserted-by":"crossref","unstructured":"Briao EW, Barcelos D, Wagner FR (2008) Dynamic task allocation strategies in MPSoC for soft real-time applications. In: Proceedings of the conference on design, automation and test in Europe, ACM, pp 1386\u20131389","DOI":"10.1145\/1403375.1403709"},{"key":"1240_CR28","doi-asserted-by":"crossref","unstructured":"Xie B, Chen T, Hu W, Tang X, Wang D (2013) An energy-aware online task mapping algorithm in NoC-based system. J Supercomput 64(3):1021\u20131037","DOI":"10.1007\/s11227-011-0678-1"},{"key":"1240_CR29","unstructured":"Shim KS, Lis M, Cho MH, Khan O, Devadas S (2011) System-level optimizations for memory access in the execution migration machine (EM2), CAOS"},{"key":"1240_CR30","doi-asserted-by":"crossref","unstructured":"Sarkar A, Mueller F, Ramaprasad H, Mohan S (2009) Push-assisted migration of real-time tasks in multi-core processors. ACM Sigplan Not 44(7):80\u201389","DOI":"10.1145\/1543136.1542464"},{"key":"1240_CR31","unstructured":"Hardy D, Puaut I (2009) Estimation of cache related migration delays for multi-core processors with shared instruction caches. In: 17th international conference on real-time and network systems, pp 45\u201354"},{"key":"1240_CR32","unstructured":"Bastoni A, Brandenburg B, Anderson J (2010) Cache-related preemption and migration delays: empirical approximation and impact on schedulability. In: Proceedings of the 6th international workshop on operating systems platforms for embedded real-time apps, pp 33\u201344"},{"key":"1240_CR33","doi-asserted-by":"crossref","unstructured":"Bakhoda A, Kim J, Aamodt TM (2010) Throughput-effective on-chip networks for manycore accelerators. In: Proceedings of the 2010 43rd annual IEEE\/ACM international symposium on microarchitecture, pp 421\u2013432, IEEE Computer Society","DOI":"10.1109\/MICRO.2010.50"},{"key":"1240_CR34","doi-asserted-by":"crossref","unstructured":"Kim D, Yoo S, Lee S (2010) A network congestion-aware memory controller. In: 2010 IEEE 4th ACM\/IEEE international symposium on networks-on-chip (NOCS), pp 257\u2013264","DOI":"10.1109\/NOCS.2010.36"},{"key":"1240_CR35","doi-asserted-by":"crossref","unstructured":"Kim D, Kim K, Kim JY, Lee SJ, Yoo HJ (2007) Solutions for real chip implementation issues of NoC and their application to memory-centric NoC. In: IEEE 1st international symposium on networks-on-chip, NOCS 2007, pp 30\u201339","DOI":"10.1109\/NOCS.2007.40"},{"key":"1240_CR36","doi-asserted-by":"crossref","unstructured":"Sharifi A, Kultursay E, Kandemir M, Das CR (2012) Addressing end-to-end memory access latency in NoC-based multicores. In: Proceedings of the 2012 45th annual IEEE\/ACM international symposium on microarchitecture, pp 294\u2013304, IEEE Computer Society","DOI":"10.1109\/MICRO.2012.35"},{"key":"1240_CR37","doi-asserted-by":"crossref","unstructured":"Chandra R, Devine S, Verghese B, Gupta A, Rosenblum M (1994) Scheduling and page migration for multiprocessor compute servers. ACM SIGPLAN Not 29(11):12\u201324","DOI":"10.1145\/195470.195485"},{"issue":"4","key":"1240_CR38","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1023\/B:IJPP.0000035815.13969.ec","volume":"32","author":"J Corbalan","year":"2004","unstructured":"Corbalan J, Martorell X, Labarta J (2004) Page migration with dynamic space-sharing scheduling policies: the case of the SGIO 2000. Int J Parallel Program 32(4):263\u2013288","journal-title":"Int J Parallel Program"},{"issue":"2","key":"1240_CR39","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/0743-7315(91)90117-R","volume":"11","author":"RP LaRowe Jr","year":"1991","unstructured":"LaRowe RP Jr, Ellis CS (1991) Page placement policies for NUMA multiprocessors. J Parallel Distrib Comput 11(2):112\u2013129","journal-title":"J Parallel Distrib Comput"},{"issue":"6","key":"1240_CR40","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1109\/71.180624","volume":"3","author":"RP LaRowe Jr","year":"1992","unstructured":"LaRowe RP Jr, Ellis CS, Holliday MA (1992) Evaluation of NUMA memory management through modeling and measurements. IEEE Trans Parallel Distrib Syst 3(6):686\u2013701","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1240_CR41","doi-asserted-by":"crossref","unstructured":"Blagodurov S, Zhuravlev S, Fedorova A et al (2010) A case for NUMA-aware contention management on multicore systems. In: Proceedings of the 19th international conference on parallel architectures and compilation techniques, ACM, pp 557\u2013558","DOI":"10.1145\/1854273.1854350"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1240-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-014-1240-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1240-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T02:23:02Z","timestamp":1649470982000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-014-1240-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,24]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["1240"],"URL":"https:\/\/doi.org\/10.1007\/s11227-014-1240-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,6,24]]}}}