{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:34:23Z","timestamp":1772724863658,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2341039, 2114514"],"award-info":[{"award-number":["2341039, 2114514"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731011","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"122-136","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Heliostat: Harnessing Ray Tracing Accelerators for Page Table Walks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2451-9568","authenticated-orcid":false,"given":"Yuan","family":"Feng","sequence":"first","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5806-7228","authenticated-orcid":false,"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6529-5333","authenticated-orcid":false,"given":"Jiwon","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5390-6445","authenticated-orcid":false,"given":"Won Woo","family":"Ro","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-8198","authenticated-orcid":false,"given":"Hyeran","family":"Jeon","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"AMD. 2025. OminiPerf Documentation. https:\/\/rocm.docs.amd.com\/projects\/omniperf\/en\/latest\/conceptual\/shader-engine.html#desc-sl1d"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387518"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Rachata Ausavarungnirun Vance Miller Joshua Landgraf Saugata Ghose Jayneel Gandhi Adwait Jog Christopher\u00a0J Rossbach and Onur Mutlu. 2018. Mask: Redesigning the gpu memory hierarchy to support multi-application concurrency. ACM SIGPLAN Notices 53 2 (2018) 503\u2013518.","DOI":"10.1145\/3296957.3173169"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569666"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00079"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414639"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2591635.2667188"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00019"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674994"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582021"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00080"},{"key":"e_1_3_3_1_16_2","unstructured":"Intel. 2024. Arc A-series GPU architecture whitepaper. https:\/\/cdrdv2-public.intel.com\/758302\/introduction-to-the-xe-hpg-architecture-white-paper.pdf"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Aamer Jaleel Eiman Ebrahimi and Sam Duncan. 2019. Ducati: High-performance address translation by extending tlb reach of gpu-accelerated systems. ACM Transactions on Architecture and Code Optimization (TACO) 16 1 (2019) 1\u201324.","DOI":"10.1145\/3309710"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Norman\u00a0P Jouppi. 1990. Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers. ACM SIGARCH Computer Architecture News 18 2SI (1990) 364\u2013373.","DOI":"10.1145\/325096.325162"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480105"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173198"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071063"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614269"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00031"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071054"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480083"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640360"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Yangming Lv Kai Zhang Ziming Wang Xiaodong Zhang Rubao Lee Zhenying He Yinan Jing and X\u00a0Sean Wang. 2024. RTScan: Efficient Scan with Ray Tracing Cores. Proceedings of the VLDB Endowment 17 6 (2024) 1460\u20131472.","DOI":"10.14778\/3648160.3648183"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656601"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Daniel Meister Paritosh Kulkarni Aaryaman Vasishta and Takahiro Harada. 2024. HIPRT: A Ray Tracing Framework in HIP. Proceedings of the ACM on Computer Graphics and Interactive Techniques 7 3 (2024) 1\u201318.","DOI":"10.1145\/3675378"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124534"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman\u00a0P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP laboratories 27 (2009) 28.","DOI":"10.1109\/MM.2008.2"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593738"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2004.10030"},{"key":"e_1_3_3_1_35_2","unstructured":"NVIDIA. 2024. Hopper architecture whitepaper. https:\/\/resources.nvidia.com\/en-us-tensor-core\/gtc22-whitepaper-hopper"},{"key":"e_1_3_3_1_36_2","unstructured":"NVIDIA. 2024. Turing architecture whitepaper. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/design-visualization\/technologies\/turing-architecture\/NVIDIA-Turing-Architecture-Whitepaper.pdf"},{"key":"e_1_3_3_1_37_2","unstructured":"PCI-SIG. 2025. PCI-SIG 6.0 Specification. https:\/\/pcisig.com\/pci-express-6.0-specification"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835964"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.32"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835965"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00059"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00036"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/1198555.1198798"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00027"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","unstructured":"Daniel Sanchez and Christos Kozyrakis. 2011. Vantage: scalable and efficient fine-grain cache partitioning. SIGARCH Comput. Archit. News 39 3 (June 2011) 57\u201368. 10.1145\/2024723.2000073","DOI":"10.1145\/2024723.2000073"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Carlo\u00a0H S\u00e9quin and Eliot\u00a0K Smyrl. 1989. Parameterized ray-tracing. ACM SIGGRAPH Computer Graphics 23 3 (1989) 307\u2013314.","DOI":"10.1145\/74334.74365"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00025"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00036"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614247"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414633"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00016"},{"key":"e_1_3_3_1_53_2","unstructured":"Vulkan. 2025. https:\/\/www.vulkan.org\/."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00085"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","unstructured":"Ziming Wang Kai Zhang Yangming Lv Yinglong Wang Zhigang Zhao Zhenying He Yinan Jing and X.\u00a0Sean Wang. 2024. RTOD: Efficient Outlier Detection With Ray Tracing Cores. IEEE Transactions on Knowledge and Data Engineering 36 12 (2024) 9192\u20139204. 10.1109\/TKDE.2024.3453901","DOI":"10.1109\/TKDE.2024.3453901"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304024"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628104"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527411"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508409"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"crossref","unstructured":"Xiaotong Zhuang and S\u00a0Lee Hsien-Hsin. 2006. Reducing cache pollution via dynamic data prefetch filtering. IEEE Trans. Comput. 56 1 (2006) 18\u201331.","DOI":"10.1109\/TC.2007.250620"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731011","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:04:10Z","timestamp":1750503850000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":60,"alternative-id":["10.1145\/3695053.3731011","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731011","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}