{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T14:10:09Z","timestamp":1726323009425},"reference-count":31,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"Intel as part of the Intel Center for Transformative Server Architecture (TSA),","award":["PID2021-126576NB-I00"]},{"name":"ERDF A way of making Europe","award":["MCIN\/AEI\/10.13039\/501100011033"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"\n The increasing demand for computing power and the emergence of heterogeneous computing architectures have driven the exploration of innovative techniques to address current limitations in both the compute and memory subsystems. One such solution is the use of\n Accelerated Processing Units<\/jats:italic>\n (APUs), processors that incorporate both a\n central processing unit<\/jats:italic>\n (CPU) and an\n integrated graphics processing unit<\/jats:italic>\n (iGPU).\n <\/jats:p>\n \n However, the performance of both APU and CPU systems can be significantly hampered by address translation overhead, leading to a decline in overall performance, especially for cache-resident workloads. To address this issue, we propose the introduction of a new\n intermediate address space<\/jats:italic>\n (IAS) in both APU and CPU systems. IAS serves as a bridge between\n virtual address<\/jats:italic>\n (VA) spaces and\n physical address<\/jats:italic>\n (PA) spaces, optimizing the address translation process. In the case of APU systems, our research indicates that the iGPU suffers from significant\n translation look-aside buffer<\/jats:italic>\n (TLB) misses in certain workload situations. Using an IAS, we can divide the initial address translation into front- and back-end phases, effectively shifting the bottleneck in address translation from the cache side to the memory controller side, a technique that proves to be effective for cache-resident workloads. Our simulations demonstrate that implementing IAS in the CPU system can boost performance by up to 40% compared to conventional CPU systems. Furthermore, we evaluate the effectiveness of APU systems, comparing the performance of IAS-based systems with traditional systems, showing up to a 185% improvement in APU system performance with our proposed IAS implementation.\n <\/jats:p>\n Furthermore, our analysis indicates that over 90% of TLB misses can be filtered by the cache, and employing a larger cache within the system could potentially result in even greater improvements. The proposed IAS offers a promising and practical solution to enhance the performance of both APU and CPU systems, contributing to state-of-the-art research in the field of computer architecture.<\/jats:p>","DOI":"10.1145\/3659207","type":"journal-article","created":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T10:23:00Z","timestamp":1713608580000},"page":"1-23","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Intermediate Address Space: virtual memory optimization of heterogeneous architectures for cache-resident workloads"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-7410-502X","authenticated-orcid":false,"given":"Qunyou","family":"Liu","sequence":"first","affiliation":[{"name":"Embedded Systems Laboratory (ESL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6579-0627","authenticated-orcid":false,"given":"Darong","family":"Huang","sequence":"additional","affiliation":[{"name":"Embedded Systems Laboratory (ESL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6922-2520","authenticated-orcid":false,"given":"Luis","family":"Costero","sequence":"additional","affiliation":[{"name":"Dpto. of Computer Architecture and Automatics, Universidad Complutense de Madrid, Madrid, Spain"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6971-1965","authenticated-orcid":false,"given":"Marina","family":"Zapater","sequence":"additional","affiliation":[{"name":"Institute of Reconfigurable & Embedded Digital Systems (REDS), School of Engineering and Management Vaud, University of Applied Sciences Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland and Embedded Systems Laboratory (ESL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9536-4947","authenticated-orcid":false,"given":"David","family":"Atienza","sequence":"additional","affiliation":[{"name":"Embedded Systems Laboratory (ESL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,9,14]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Advanced Micro Devices Inc. 2016. AMD GCN3 Instruction Set Architecture. Retrieved March 19 2024 from https:\/\/www.amd.com\/system\/files\/TechDocs\/gcn3-instruction-set-architecture.pdf. Version 1.1."},{"key":"e_1_3_2_3_2","unstructured":"Paul Alcorn. 2023. AMD instinct MI300 data center APU pictured up close: 13 chiplets 146 billion transistors. Retrieved March 19 2024 from https:\/\/www.tomshardware.com\/news\/amd-instinct-mi300-data-center-apu-pictured-up-close-15-chiplets-146-billion-transistors"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/1247360.1247401"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/1054907.1054910"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SAAHPC.2011.29"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038239"},{"key":"e_1_3_2_11_2","unstructured":"gem5. 2023. GCN3. Retrieved May 27 2023 from https:\/\/www.gem5.org\/documentation\/general_docs\/gpu_models\/GCN3"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00047"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00058"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00089"},{"key":"e_1_3_2_15_2","unstructured":"2010 9:28 pm UTC Jon Stokes; Feb 8. 2010. AMD reveals fusion CPU+GPU to challenge Intel in Laptops. Retrieved March 19 2024 from https:\/\/arstechnica.com\/information-technology\/2010\/02\/amd-reveals-fusion-cpugpu-to-challege-intel-in-laptops\/"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"I. Karlin. 2012. LULESH programming model and performance ports overview. (2012). https:\/\/www.osti.gov\/biblio\/1059462","DOI":"10.2172\/1059462"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3076113.3076115"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01244"},{"key":"e_1_3_2_20_2","first-page":"705-\u2013721","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI\u201916)","author":"Kwon Youngjin","year":"2016","unstructured":"Youngjin Kwon, Hangchen Yu, Simon Peter, Christopher J. Rossbach, and Emmett Witchel. 2016. Coordinated and efficient huge page management with ingens. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI\u201916). USENIX Association, USA, 705-\u2013721."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071063"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/bs.adcom.2015.10.002"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319647.3325839"},{"key":"e_1_3_2_24_2","unstructured":"U.S. Department of Energy. 2018. Coral-2 Benchmarks. Retrieved March 19 2024 from https:\/\/asc.llnl.gov\/coral-2-benchmarks"},{"key":"e_1_3_2_25_2","unstructured":"Adarsh Patil. 2020. TLB and pagewalk performance in multicore architectures with large die-stacked DRAM cache. arXiv:2002.01073. Retrieved from https:\/\/arxiv.org\/abs\/2002.01073"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2654822.2541942"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167781"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDC.2017.16"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/17407.17398"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173195"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810109"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00018"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3659207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T13:14:37Z","timestamp":1726319677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,14]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3659207"],"URL":"https:\/\/doi.org\/10.1145\/3659207","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"type":"print","value":"1544-3566"},{"type":"electronic","value":"1544-3973"}],"subject":[],"published":{"date-parts":[[2024,9,14]]},"assertion":[{"value":"2023-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
