{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:51:22Z","timestamp":1783036282268,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624173","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"962-972","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["GPU Graph Processing on CXL-Based Microsecond-Latency External Memory"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2988-9724","authenticated-orcid":false,"given":"Shintaro","family":"Sano","sequence":"first","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9150-6503","authenticated-orcid":false,"given":"Yosuke","family":"Bando","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3610-6496","authenticated-orcid":false,"given":"Kazuhiro","family":"Hiwada","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4784-8234","authenticated-orcid":false,"given":"Hirotsugu","family":"Kajihara","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3031-2693","authenticated-orcid":false,"given":"Tomoya","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3312-3395","authenticated-orcid":false,"given":"Yu","family":"Nakanishi","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7193-4723","authenticated-orcid":false,"given":"Daisuke","family":"Taki","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0066-0469","authenticated-orcid":false,"given":"Akiyuki","family":"Kaneko","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6679-3950","authenticated-orcid":false,"given":"Tatsuo","family":"Shiozawa","sequence":"additional","affiliation":[{"name":"Kioxia Corporation, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Advanced Micro Devices Inc.2023. AMD Expands Leadership Data Center Portfolio with New EPYC CPUs and Shares Details on Next-Generation AMD Instinct Accelerator and Software Enablement for Generative AI. https:\/\/www.amd.com\/en\/newsroom\/press-releases\/2023-6-13-amd-expands-leadership-data-center-portfolio-with-.html."},{"key":"e_1_3_2_2_2_1","volume-title":"The GAP benchmark suite. arXiv preprint arXiv:1508.03619","author":"Beamer Scott","year":"2015","unstructured":"Scott Beamer, Krste Asanovi\u0107, and David Patterson. 2015. The GAP benchmark suite. arXiv preprint arXiv:1508.03619 (2015)."},{"key":"e_1_3_2_2_3_1","volume-title":"Design and Analysis of CXL Performance Models for Tightly-Coupled Heterogeneous Computing. In the 1st International Workshop on Extreme Heterogeneity Solutions (ExHET). Article 1.","author":"Cabrera M","year":"2022","unstructured":"Anthony\u00a0M Cabrera, Aaron\u00a0R Young, and Jeffrey\u00a0S Vetter. 2022. Design and Analysis of CXL Performance Models for Tightly-Coupled Heterogeneous Computing. In the 1st International Workshop on Extreme Heterogeneity Solutions (ExHET). Article 1."},{"key":"e_1_3_2_2_4_1","unstructured":"The\u00a0CXL Consortium. [n. d.]. Compute Express Link\u2122. https:\/\/www.computeexpresslink.org\/."},{"key":"e_1_3_2_2_5_1","unstructured":"Intel Corporation. 2023. Compute Express Link (CXL)-Cache\/Mem Protocol Interface (CPI). https:\/\/cdrdv2-public.intel.com\/644330\/644330_CPI Specification_Rev1p0.pdf."},{"key":"e_1_3_2_2_6_1","unstructured":"NVIDIA Corporation. 2023. NVIDIA A100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/."},{"key":"e_1_3_2_2_7_1","unstructured":"NVIDIA Corporation. 2023. NVIDIA Grace Hopper Superchip. https:\/\/www.nvidia.com\/en-us\/data-center\/grace-hopper-superchip\/."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192404"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384358"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975269"},{"key":"e_1_3_2_2_12_1","volume-title":"High-Performance Memory Disaggregation with DirectCXL. In the 2022 USENIX Annual Technical Conference","author":"Gouk Donghyun","year":"2022","unstructured":"Donghyun Gouk, Sangwon Lee, Miryeong Kwon, and Myoungsoo Jung. 2022. Direct Access, High-Performance Memory Disaggregation with DirectCXL. In the 2022 USENIX Annual Technical Conference.Carlsbad, CA, USA."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.41"},{"key":"e_1_3_2_2_14_1","unstructured":"Mark Harris. 2013. How to Access Global Memory Efficiently in CUDA C\/C++ Kernels. https:\/\/developer.nvidia.com\/blog\/how-access-global-memory-efficiently-cuda-c-kernels\/."},{"key":"e_1_3_2_2_15_1","unstructured":"Mark Harris. 2017. Unified Memory for CUDA Beginners. https:\/\/developer.nvidia.com\/blog\/unified-memory-cuda-beginners\/."},{"key":"e_1_3_2_2_16_1","volume-title":"BigSparse: High-performance external graph analytics. arXiv preprint arXiv:1710.07736","author":"Jun Sang-Woo","year":"2017","unstructured":"Sang-Woo Jun, Andy Wright, Sizhuo Zhang, Shuotao Xu, 2017. BigSparse: High-performance external graph analytics. arXiv preprint arXiv:1710.07736 (2017)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00042"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3237548"},{"key":"e_1_3_2_2_20_1","volume-title":"10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12)","author":"Kyrola Aapo","year":"2012","unstructured":"Aapo Kyrola, Guy Blelloch, and Carlos Guestrin. 2012. GraphChi:Large-Scale Graph Computation on Just a PC. In 10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12). 31\u201346."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592980.3595311"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304044"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_2_2_24_1","unstructured":"Yuan Lin and Vinod Grover. 2018. Using CUDA Warp-Level Primitives. https:\/\/developer.nvidia.com\/blog\/using-cuda-warp-level-primitives\/."},{"key":"e_1_3_2_2_25_1","volume-title":"Graphene:Fine-Grained IO Management for Graph Computing. In 15th USENIX Conference on File and Storage Technologies (FAST 17)","author":"Liu Hang","year":"2017","unstructured":"Hang Liu and H\u00a0Howie Huang. 2017. Graphene:Fine-Grained IO Management for Graph Computing. In 15th USENIX Conference on File and Storage Technologies (FAST 17). 285\u2013300."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064191"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00035"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_3_2_2_30_1","volume-title":"15th Workshop on Hot Topics in Operating Systems (HotOS XV).","author":"McSherry Frank","year":"2015","unstructured":"Frank McSherry, Michael Isard, and Derek\u00a0G Murray. 2015. Scalability! but at what COST?. In 15th Workshop on Hot Topics in Operating Systems (HotOS XV)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3425879.3425883"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522739"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), Vol.\u00a02. 325\u2013339","author":"Qureshi Zaid","year":"2022","unstructured":"Zaid Qureshi, Vikram\u00a0Sharma Mailthody, Isaac Gelado, Seung\u00a0Won Min, Amna Masood, Jeongmin Park, Jinjun Xiong, CJ Newburn, Dmitri Vainbrand, I Chung, 2022. GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), Vol.\u00a02. 325\u2013339."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"e_1_3_2_2_35_1","volume-title":"15th European Conference on Computer Systems (EuroSys \u201920)","author":"Hossein\u00a0Nodehi Sabet Amir","year":"2020","unstructured":"Amir Hossein\u00a0Nodehi Sabet, Zhijia Zhao, and Rajiv Gupta. 2020. Subway: Minimizing Data Transfer during out-of-GPU-Memory Graph Processing. In 15th European Conference on Computer Systems (EuroSys \u201920). Heraklion, Greece, Article 12:1\u201316."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807655"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001200"},{"key":"e_1_3_2_2_38_1","volume-title":"Emerging Usage and Evaluation of Low Latency FLASH. In 2020 IEEE International Memory Workshop (IMW). IEEE, 1\u20134.","author":"Shiozawa Tatsuo","year":"2020","unstructured":"Tatsuo Shiozawa, Hirotsugu Kajihara, Tatsuro Endo, and Kazuhiro Hiwada. 2020. Emerging Usage and Evaluation of Low Latency FLASH. In 2020 IEEE International Memory Workshop (IMW). IEEE, 1\u20134."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2553081"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2963098"},{"key":"e_1_3_2_2_41_1","volume-title":"Demystifying CXL Memory with Genuine CXL-Ready Systems and Devices. arXiv preprint arXiv:2303.15375","author":"Sun Yan","year":"2023","unstructured":"Yan Sun, Yifan Yuan, Zeduo Yu, Reese Kuper, Ipoom Jeong, and Ren Wang Nam\u00a0Sung Kim. 2023. Demystifying CXL Memory with Genuine CXL-Ready Systems and Devices. arXiv preprint arXiv:2303.15375 (2023)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457397"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00075"},{"key":"e_1_3_2_2_44_1","volume-title":"Evaluating Emerging CXL-enabled Memory Pooling for HPC Systems. In SC Workshop on Memory Centric High Performance Computing (MCHPC\u201922)","author":"Wahlgren Jacob","year":"2022","unstructured":"Jacob Wahlgren, Maya Gokhale, and Ivy Peng. 2022. Evaluating Emerging CXL-enabled Memory Pooling for HPC Systems. In SC Workshop on Memory Centric High Performance Computing (MCHPC\u201922). Dallas, TX, USA."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2350190.2350193"},{"key":"e_1_3_2_2_46_1","volume-title":"CXLMemSim: A pure software simulated CXL.mem for performance characterization. arXiv preprint arXiv:2303.06153","author":"Yang Yiwei","year":"2023","unstructured":"Yiwei Yang, Pooneh Safayenikoo, Jiacheng Ma, Tanvir\u00a0Ahmed Khan, and Andrew Quinn. 2023. CXLMemSim: A pure software simulated CXL.mem for performance characterization. arXiv preprint arXiv:2303.06153 (2023)."},{"key":"e_1_3_2_2_47_1","volume-title":"13th USENIX Conference on File and Storage Technologies (FAST 15)","author":"Zheng Da","year":"2015","unstructured":"Da Zheng, Disa Mhembere, Randal Burns, Joshua Vogelstein, Carey\u00a0E Priebe, and Alexander\u00a0S Szalay. 2015. FlashGraph: Processing Billion-Node Graphs on an Array of Commodity SSDs. In 13th USENIX Conference on File and Storage Technologies (FAST 15). 45\u201358."}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624173","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:05:36Z","timestamp":1755745536000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":47,"alternative-id":["10.1145\/3624062.3624173","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624173","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}