{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T09:19:10Z","timestamp":1774257550947,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,12,7]],"date-time":"2019-12-07T00:00:00Z","timestamp":1575676800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,12,7]],"date-time":"2019-12-07T00:00:00Z","timestamp":1575676800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s11704-018-7386-4","type":"journal-article","created":{"date-parts":[[2019,12,7]],"date-time":"2019-12-07T08:02:37Z","timestamp":1575705757000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Transparent partial page migration between CPU and GPU"],"prefix":"10.1007","volume":"14","author":[{"given":"Shiqing","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zheng","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Yaohua","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Zhiying","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,7]]},"reference":[{"key":"7386_CR1","unstructured":"Harris M. Unified memory in CUDA 6. GTC On-Demand, NVIDIA, 2013"},{"issue":"2","key":"7386_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MM.2008.31","volume":"28","author":"E Lindholm","year":"2008","unstructured":"Lindholm E, Nickolls J, Oberman S, Montrym J. Nvidia tesla: a unified graphics and computing architecture. IEEE Micro, 2008, 28(2): 39\u201355","journal-title":"IEEE Micro"},{"key":"7386_CR3","doi-asserted-by":"crossref","unstructured":"Di Carlo S, Gambardella G, Martella I, Prinetto P, Rolfo D, Trotta P. Fault mitigation strategies for CUDA GPUs. In: Proceedings of IEEE International Test Conference. 2013, 1\u20138","DOI":"10.1109\/TEST.2013.6651908"},{"key":"7386_CR4","doi-asserted-by":"crossref","unstructured":"Power J, Hill M D, Wood D A. Supporting x86-64 address translation for 100s of GPU lanes. In: Proceedings of IEEE International Symposium on High Performance Computer Architecture. 2014, 568\u2013578","DOI":"10.1109\/HPCA.2014.6835965"},{"key":"7386_CR5","doi-asserted-by":"crossref","unstructured":"Landaverde R, Zhang T, Coskun A K, Herbordt M. An investigation of unified memory access performance in CUDA. In: Proceedings of IEEE High Performance Extreme Computing Conference. 2014, 1\u20136","DOI":"10.1109\/HPEC.2014.7040988"},{"key":"7386_CR6","doi-asserted-by":"crossref","unstructured":"Zheng T, Nellans D, Zulfiqar A, Stephenson M, Keckler S W. Towards high performance paged memory for GPUs. In: Proceedings of IEEE International Symposium on High Performance Computer Architecture. 2016, 345\u2013357","DOI":"10.1109\/HPCA.2016.7446077"},{"key":"7386_CR7","doi-asserted-by":"crossref","unstructured":"Lustig D, Martonosi M. Reducing GPU offload latency via fine-grained CPU-GPU synchronization. In: Proceedings of IEEE International Symposium on High Performance Computer Architecture. 2013, 354\u2013365","DOI":"10.1109\/HPCA.2013.6522332"},{"key":"7386_CR8","doi-asserted-by":"crossref","unstructured":"Kirk D. Nvidia CUDA software and GPU parallel computing architecture. In: Proceedings of International Symposium on Memory Management. 2007, 103\u2013104","DOI":"10.1145\/1296907.1296909"},{"key":"7386_CR9","unstructured":"Patterson D. The top 10 innovations in the new nvidia fermi architecture, and the top 3 next challenges. Nvidia Whitepaper, 2009, 47"},{"issue":"2","key":"7386_CR10","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/MM.2014.10","volume":"34","author":"P Hammarlund","year":"2014","unstructured":"Hammarlund P, Martinez A J, Bajwa A A, Hill D L, Hallnor E, Jiang H, Dixon M, Derr M, Hunsaker M, Kumar R, Osborne R B, Rajwar R, Singhal R, D\u2019Sa R, Chappell R, Kaushik S, Chennupaty S, Jourdun S, Gunther S, Piazza T, Burton T. Haswell: the fourth-generation intel core processor. IEEE Micro, 2014, 34(2): 6\u201320","journal-title":"IEEE Micro"},{"issue":"1","key":"7386_CR11","first-page":"105","volume":"3","author":"J Ghorpade","year":"2012","unstructured":"Ghorpade J, Parande J, Kulkarni M, Bawaskar A. GGGPU processing in CUDA architecture. Advanced Computing, 2012, 3(1): 105","journal-title":"Advanced Computing"},{"key":"7386_CR12","doi-asserted-by":"crossref","unstructured":"Rogers P. Heterogeneous system architecture overview. In: Proceedings of Hot Chip: A Symposium on High Performance Chips. 2013","DOI":"10.1109\/HOTCHIPS.2013.7478286"},{"issue":"2","key":"7386_CR13","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/L-CA.2013.19","volume":"13","author":"Y Kim","year":"2014","unstructured":"Kim Y, Lee J, Kim D, Kim J. Scalegpu: GPU architecture for memory-unaware GPU programming. IEEE Computer Architecture Letters, 2014, 13(2): 101\u2013104","journal-title":"IEEE Computer Architecture Letters"},{"key":"7386_CR14","unstructured":"Cao Y, Chen L, Zhang Z. Flexible memory: a novel main memory architecture with block-level memory compression. In: Proceedings of IEEE International Conference on Networking, Architecture and Storage. 2015, 285\u2013294"},{"key":"7386_CR15","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1145\/2775054.2694381","volume":"50","author":"N Agarwal","year":"2015","unstructured":"Agarwal N, Nellans D, Stephenson M, O\u2019Connor M, Keckler S W. Page placement strategies for GPUs within heterogeneous memory systems. ACM SIGPLAN Notices, 2015, 50: 607\u2013618","journal-title":"ACM SIGPLAN Notices"},{"key":"7386_CR16","doi-asserted-by":"crossref","unstructured":"Agarwal N, Nellans D, O\u2019Connor M, Keckler S W, Wenisch T F. Unlocking bandwidth for GPUs in CC-NUMA systems. In: Proceedings of IEEE International Symposium on High Performance Computer Architecture. 2015, 354\u2013365","DOI":"10.1109\/HPCA.2015.7056046"},{"issue":"5","key":"7386_CR17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MM.2011.89","volume":"31","author":"S W Keckler","year":"2011","unstructured":"Keckler S W, Dally W J, Khailany B, Garland M, Glasco D. GPUs and the future of parallel computing. IEEE Micro, 2011, 31(5): 7\u201317","journal-title":"IEEE Micro"},{"key":"7386_CR18","doi-asserted-by":"crossref","unstructured":"Vesely J, Basu A, Oskin M, Loh G H, Bhattacharjee A. Observations and opportunities in architecting shared virtual memory for heterogeneous systems. In: Proceedings of IEEE International Symposium on Performance Analysis of Systems and Software. 2016, 161\u2013171","DOI":"10.1109\/ISPASS.2016.7482091"},{"key":"7386_CR19","doi-asserted-by":"crossref","unstructured":"Awasthi M, Nellans D, Sudan K, Balasubramonian R, Davis A. Handling the problems and opportunities posed by multiple on-chip memory controllers. In: Proceedings of International Conference on Parallel Architectures and Compilation Techniques. 2010, 319\u2013330","DOI":"10.1145\/1854273.1854314"},{"key":"7386_CR20","doi-asserted-by":"crossref","unstructured":"Pattnaik A, Tang X, Jog A, Kayiran O, Mishra A K, Kandemir M T, Mutlu O, Das C R. Scheduling techniques for GPU architectures with processing-in-memory capabilities. In: Proceedings of International Conference on Parallel Architecture and Compilation Techniques. 2016, 31\u201344","DOI":"10.1145\/2967938.2967940"},{"key":"7386_CR21","doi-asserted-by":"crossref","unstructured":"Chan C, Didem Unat D, Lijewski M, Zhang W, Bell J, Shalf J. Software design space exploration for exascale combustion co-design. In: Proceedings of International Supercomputing Conference. 2013, 196\u2013212","DOI":"10.1007\/978-3-642-38750-0_15"},{"issue":"9","key":"7386_CR22","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/3156685.3092256","volume":"52","author":"Mohammad Dashti","year":"2017","unstructured":"Dashti M, Fedorova A. Analyzing memory management methods on integrated CPU-GPU systems. In: Proceedings of ACM SIGPLAN International Symposium on Memory Management. 2017, 59\u201369","journal-title":"ACM SIGPLAN Notices"},{"key":"7386_CR23","doi-asserted-by":"crossref","unstructured":"Bakhoda A, Yuan G L, Fung W W L, Wong H, Aamodt T M. Analyzing CUDA workloads using a detailed GPU simulator. In: Proceedings of IEEE International Symposium on Performance Analysis of Systems and Software. 2009, 163\u2013174","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"7386_CR24","first-page":"2015","volume":"1","author":"T M Aamodt","year":"2013","unstructured":"Aamodt T M, Fung W W L, Singh I, El-Shafiey A, Kwa J, Hetherington T, Gubran A, Boktor A, Rogers T, Bakhoda A. GPGPU-Sim 3.x manual. Retrieved February, 2013, 1: 2015","journal-title":"Retrieved February"},{"key":"7386_CR25","doi-asserted-by":"crossref","unstructured":"Ajanovic J. PCI express 3.0 overview. In: Proceedings of Hot Chips: A Symposium on High Performance Chips. 2009","DOI":"10.1109\/HOTCHIPS.2009.7478337"},{"key":"7386_CR26","unstructured":"Gonzales D. PCI express 4.0 electrical previews. In: Proceedings of PCI-SIG Developers Conference. 2015"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-018-7386-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11704-018-7386-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-018-7386-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,6]],"date-time":"2020-12-06T00:10:18Z","timestamp":1607213418000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11704-018-7386-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,7]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["7386"],"URL":"https:\/\/doi.org\/10.1007\/s11704-018-7386-4","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,7]]},"assertion":[{"value":"5 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"143101"}}