{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T00:10:09Z","timestamp":1709424609410},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2024,2,25]]},"DOI":"10.1587\/elex.21.20230520","type":"journal-article","created":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:11:26Z","timestamp":1704838286000},"page":"20230520-20230520","source":"Crossref","is-referenced-by-count":0,"title":["Reuse distance-based shared LLC management mechanism for heterogeneous CPU-GPU systems"],"prefix":"10.1587","volume":"21","author":[{"given":"Jiaheng","family":"Liu","sequence":"first","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University"}]},{"given":"Ryusuke","family":"Egawa","sequence":"additional","affiliation":[{"name":"School of Engineering, Tokyo Denki University"}]},{"given":"Keichi","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Cyberscience Center, Tohoku University"}]},{"given":"Yoichi","family":"Shimomura","sequence":"additional","affiliation":[{"name":"Cyberscience Center, Tohoku University"}]},{"given":"Hiroyuki","family":"Takizawa","sequence":"additional","affiliation":[{"name":"Cyberscience Center, Tohoku University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] E. Rotem, <i>et al.<\/i>: \u201cAlder lake architecture,\u201d IEEE Hot Chips 33 Symposium (2021) 1 (DOI: 10.1109\/hcs52781.2021.9567097).","DOI":"10.1109\/HCS52781.2021.9567097"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] M. Ditty: \u201cNVIDIA ORIN system-on-chip,\u201d IEEE Hot Chips 34 Symposium (2022) 1 (DOI: 10.1109\/hcs55958.2022.9895609).","DOI":"10.1109\/HCS55958.2022.9895609"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] T. Burd, <i>et al.<\/i>: \u201cZen3: The amd 2nd generation 7nm x86-64 microprocessor core,\u201d IEEE ISSCC <b>65<\/b> IEEE (2022) 1 (DOI: 10.1109\/HCS55958.2022.9895609).","DOI":"10.1109\/ISSCC42614.2022.9731678"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] V. Garc\u0131a, <i>et al.<\/i>: \u201cEvaluating the effect of last-level cache sharing on integrated gpu-cpu systems with heterogeneous applications,\u201d IEEE IISWC (2016) 1 (DOI: 10.1109\/iiswc.2016.7581277).","DOI":"10.1109\/IISWC.2016.7581277"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] J. Lee, <i>et al.<\/i>: \u201cTAP: A TLP-aware cache management policy for a CPU-GPU heterogeneous architecture,\u201d IEEE HPCA (2012) 1 (DOI: 10.1109\/hpca.2012.6168947).","DOI":"10.1109\/HPCA.2012.6168947"},{"key":"6","unstructured":"[6] V. Mekkat, <i>et al.<\/i>: \u201cManaging shared last-level cache in a heterogeneous multicore processor,\u201d Proc. 22nd International Conference on Parallel Architectures and Compilation Techniques (2013) 225 (DOI: 10.1109\/PACT.2013.6618819)."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] X. Wang and W. Zhang: \u201cA sample-based dynamic CPU and GPU LLC bypassing method for heterogeneous CPU-GPU architectures,\u201d IEEE Trustcom\/BigDataSE\/ICESS (2017) 753 (DOI: 10.1109\/trustcom\/bigdatase\/icess.2017.309).","DOI":"10.1109\/Trustcom\/BigDataSE\/ICESS.2017.309"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] J. Zhan, <i>et al.<\/i>: \u201cOSCAR: Orchestrating STT-RAM cache traffic for heterogeneous CPU-GPU architectures,\u201d 49th Annual IEEE\/ACM MICRO (2016) 1 (DOI: 10.1109\/micro.2016.7783731).","DOI":"10.1109\/MICRO.2016.7783731"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] L. Gao, <i>et al.<\/i>: \u201cSRAM-and STT-RAM-based hybrid, shared last-level cache for on-chip CPU-GPU heterogeneous architectures,\u201d The Journal of Supercomputing <b>74<\/b> (2018) 3388 (DOI: 10.1007\/s11227-018-2389-3).","DOI":"10.1007\/s11227-018-2389-3"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] A. Jaleel, <i>et al.<\/i>: \u201cHigh performance cache replacement using re-reference interval prediction (rrip),\u201d ACM SIGARCH Computer Architecture News <b>38<\/b> (2010) 60 (DOI: 10.1145\/1816038.1815971).","DOI":"10.1145\/1816038.1815971"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Albericio, <i>et al.<\/i>: \u201cExploiting reuse locality on inclusive shared last-level caches,\u201d ACM TACO <b>9<\/b> (2010) 1 (DOI: 10.1145\/2400682.2400697).","DOI":"10.1145\/2400682.2400697"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] N. Duong, <i>et al.<\/i>: \u201cImproving cache management policies using dynamic reuse distances,\u201d 45th Annual IEEE\/ACM MICRO (2012) 389 (DOI: 10.1109\/micro.2012.43).","DOI":"10.1109\/MICRO.2012.43"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] S. Das, <i>et al.<\/i>: \u201cReuse distance-based probabilistic cache replacement,\u201d ACM TACO <b>12<\/b> (2015) 1 (DOI: 10.1145\/2818374).","DOI":"10.1145\/2818374"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] S. Sethumurugan, <i>et al.<\/i>: \u201cDesigning a cost-effective cache replacement policy using machine learning,\u201d IEEE HPCA (2021) 291 (DOI: 10.1109\/hpca51647.2021.00033).","DOI":"10.1109\/HPCA51647.2021.00033"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Y. Arafa, <i>et al.<\/i>: \u201cFast, accurate, and scalable memory modeling of GPGPUs using reuse profiles,\u201d the 34th ACM International Conference on Supercomputing (2020) 1 (DOI: 10.1145\/3392717.3392761).","DOI":"10.1145\/3392717.3392761"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] S.N. Ghosh, <i>et al.<\/i>: \u201cSRCP: sharing and reuse-aware replacement policy for the partitioned cache in multicore systems,\u201d Design Automation for Embedded Systems <b>25<\/b> (2021) 193 (DOI: 10.1007\/s10617-021-09251-z).","DOI":"10.1007\/s10617-021-09251-z"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] M.K. Qureshi, <i>et al.<\/i>: \u201cAdaptive insertion policies for high performance caching,\u201d ACM SIGARCH Computer Architecture News <b>35<\/b> (2007) 381 (DOI: 10.1145\/1273440.1250709).","DOI":"10.1145\/1273440.1250709"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Z. Li, <i>et al.<\/i>: \u201cSet variation-aware shared LLC management for CPU-GPU heterogeneous architecture,\u201d DATE (2018) 79 (DOI: 10.23919\/date.2018.8341983).","DOI":"10.23919\/DATE.2018.8341983"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] A. Patil and R. Govindarajan: \u201cHashCache: Heterogeneity-aware shared dramcache for integrated heterogeneous systems,\u201d ACM TACO <b>14<\/b> (2017) 1 (DOI: 10.1145\/3158641).","DOI":"10.1145\/3158641"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] J. Alsop, <i>et al.<\/i>: \u201cSpandex: A flexible interface for efficient heterogeneous coherence,\u201d ACM\/IEEE 45th Annual ISCA (2018) 261 (DOI: 10.1109\/isca.2018.00031).","DOI":"10.1109\/ISCA.2018.00031"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] K. Bhardwaj, <i>et al.<\/i>: \u201cA comprehensive methodology to determine optimal coherence interfaces for many-accelerator socs,\u201d ACM\/IEEE International Symposium on Low Power Electronics and Design (2020) 145 (DOI: 10.1145\/3370748.3406564).","DOI":"10.1145\/3370748.3406564"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] A. Gutierrez, <i>et al.<\/i>: \u201cLost in abstraction: Pitfalls of analyzing gpus at the intermediate language level,\u201d IEEE HPCA (2018) 608 (DOI: 10.1109\/hpca.2018.00058).","DOI":"10.1109\/HPCA.2018.00058"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Power, <i>et al.<\/i>: \u201cHeterogeneous system coherence for integrated CPU-GPU systems,\u201d 46th Annual IEEE\/ACM MICRO (2013) 457 (DOI: 10.1145\/2540708.2540747).","DOI":"10.1145\/2540708.2540747"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] J. G\u00f3mez-Luna, <i>et al.<\/i>: \u201cChai: Collaborative heterogeneous applications for integrated-architectures,\u201d IEEE ISPASS (2017) 43 (DOI: 10.1109\/ispass.2017.7975269).","DOI":"10.1109\/ISPASS.2017.7975269"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Che, <i>et al.<\/i>: \u201cRodinia: A benchmark suite for heterogeneous computing,\u201d IEEE IISWC (2009) 44 (DOI: 10.1109\/iiswc.2009.5306797).","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"26","unstructured":"[26] Hipify reference guide v5.1 (2022) https:\/\/docs.amd.com\/bundle\/HIPify-Reference-Guidev5.1\/page\/HIPify.html."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] D.P. Ravipati, <i>et al.<\/i>: \u201cFN-CACTI: Advanced cacti for FinFET and NC-FinFET technologies,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>30<\/b> (2021) 339 (DOI: 10.1109\/TVLSI.2021.3123112).","DOI":"10.1109\/TVLSI.2021.3123112"},{"key":"28","unstructured":"[28] International Roadmap for Devices and Systems (IRDS<sup>TM<\/sup>) (2023) https:\/\/irds.ieee.org\/editions."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] C. Meinhardt, <i>et al.<\/i>: \u201cPredictive evaluation of electrical characteristics of sub-22 nm finfet technologies under device geometry variations,\u201d Microelectronics Reliability <b>54<\/b> (2014) 2319 (DOI: 10.1016\/j.microrel.2014.07.023).","DOI":"10.1016\/j.microrel.2014.07.023"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] S. Li, <i>et al.<\/i>: \u201cDRAMsim3: A cycle-accurate, thermal-capable dram simulator,\u201d IEEE Comput. Archit. Lett. <b>19<\/b> (2020) 106 (DOI: 10.1109\/LCA.2020.2973991).","DOI":"10.1109\/LCA.2020.2973991"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/21\/4\/21_21.20230520\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T03:31:36Z","timestamp":1709350296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/21\/4\/21_21.20230520\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,25]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.21.20230520","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,25]]},"article-number":"21.20230520"}}