{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T08:43:04Z","timestamp":1780994584157,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["111-2221-E-A49 -131 -MY3"],"award-info":[{"award-number":["111-2221-E-A49 -131 -MY3"]}],"id":[{"id":"10.13039\/100020595","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\/3695053.3731104","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:46:17Z","timestamp":1750437977000},"page":"374-387","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AQB8: Energy-Efficient Ray Tracing Accelerator through Multi-Level Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5756-1785","authenticated-orcid":false,"given":"Yen-Chieh","family":"Huang","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2134-5294","authenticated-orcid":false,"given":"Chen-Pin","family":"Yang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2401-9916","authenticated-orcid":false,"given":"Tsung Tai","family":"Yeh","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Advanced Micro Devices Inc.2023. \"RDNA3\" Instruction Set Architecture: Reference Guide. Retrieved Feb. 10 2025 from https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/radeon-tech-docs\/instruction-set-architectures\/rdna3-shader-instruction-set-architecture-feb-2023_0.pdf"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/1921479.1921497"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572792"},{"key":"e_1_3_3_1_5_2","unstructured":"Ars\u00e8ne P\u00e9rard-Gayot. 2024. madmann91\/bvh: A modern C++ BVH construction and traversal library. Retrieved Feb. 10 2025 from https:\/\/github.com\/madmann91\/bvh"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Rajeev Balasubramonian Andrew\u00a0B. Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New Tools for Interconnect Exploration in Innovative Off-Chip Memories. ACM Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00079"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3231578.3231581"},{"key":"e_1_3_3_1_9_2","first-page":"41","volume-title":"Proceedings of the Conference on High Performance Graphics (HPG)","author":"Binder Nikolaus","year":"2016","unstructured":"Nikolaus Binder and Alexander Keller. 2016. Efficient stackless hierarchy traversal on GPUs with backtracking in constant time.. In Proceedings of the Conference on High Performance Graphics (HPG). 41\u201350."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Benedikt Bitterli. 2024. Rendering Resources | Benedikt Bitterli\u2019s Portfolio. Retrieved Feb. 10 2025 from https:\/\/benedikt-bitterli.me\/resources\/","DOI":"10.46499\/2339.2958"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614288"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Yangdong Deng Yufei Ni Zonghui Li Shuai Mu and Wenjun Zhang. 2017. Toward Real-Time Ray Tracing: A Survey on Hardware Acceleration and Microarchitecture Techniques. ACM Computing Surveys (CSUR) 50 4 (2017) 1\u201341.","DOI":"10.1145\/3104067"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Kirill Garanzha and Charles Loop. 2010. Fast ray sorting and breadth-first packet traversal for GPU ray tracing. Computer Graphics Forum 29 2 (2010) 289\u2013298.","DOI":"10.1111\/j.1467-8659.2009.01598.x"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771789"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2008.4634622"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00080"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2007.4342599"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2461217.2461219"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jacob Haydel Cem Yuksel and Larry Seiler. 2023. Locally-Adaptive Level-of-Detail for Hardware-Accelerated Ray Tracing. ACM Transactions on Graphics (TOG) 42 6 (2023) 1\u201315.","DOI":"10.1145\/3618359"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00062"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818427.2818446"},{"key":"e_1_3_3_1_22_2","unstructured":"Intel Corporation. 2023. Intel\u00ae Arc\u2122 Graphics Developer Guide for Real-Time Ray Tracing in Games. Retrieved Feb. 10 2025 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/guide\/real-time-ray-tracing-in-games.html\/"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0L Kay and James\u00a0T Kajiya. 1986. Ray tracing complex scenes. ACM SIGGRAPH Computer Graphics 20 4 (1986) 269\u2013278.","DOI":"10.1145\/15886.15916"},{"key":"e_1_3_3_1_24_2","first-page":"29","volume-title":"Proceedings of the Conference on High Performance Graphics (HPG)","author":"Keely Sean","year":"2014","unstructured":"Sean Keely. 2014. Reduced Precision for Hardware Ray Tracing in GPUs. In Proceedings of the Conference on High Performance Graphics (HPG). 29\u201340."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Hong-Yun Kim Young-Jun Kim and Lee-Sup Kim. 2011. MRTP: Mobile Ray Tracing Processor With Reconfigurable Stream Multi-Processors for High Datapath Utilization. IEEE Journal of Solid-State Circuits (JSSC) 47 2 (2011) 518\u2013535.","DOI":"10.1109\/JSSC.2011.2171417"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Hong-Yun Kim Young-Jun Kim Jie-Hwan Oh and Lee-Sup Kim. 2013. A Reconfigurable SIMT Processor for Mobile Ray Tracing With Contention Reduction in Shared Memory. IEEE Transactions on Circuits and Systems I: Regular Papers 60 4 (2013) 938\u2013950.","DOI":"10.1109\/TCSI.2012.2209302"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Tae-Joon Kim Bochang Moon Duksu Kim and Sung-Eui Yoon. 2009. RACBVHs: Random-Accessible Compressed Bounding Volume Hierarchies. IEEE Transactions on Visualization and Computer Graphics (TVCG) 16 2 (2009) 273\u2013286.","DOI":"10.1109\/TVCG.2009.71"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2010.5647555"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/1921479.1921496"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2492045.2492060"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2790060.2790064"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2492045.2492057"},{"key":"e_1_3_3_1_33_2","first-page":"51","volume-title":"Proceedings of the Conference on High Performance Graphics (HPG)","author":"Liktor G\u00e1bor","year":"2016","unstructured":"G\u00e1bor Liktor and Karthikeyan Vaidyanathan. 2016. Bandwidth-efficient BVH layout for incremental hardware traversal.. In Proceedings of the Conference on High Performance Graphics (HPG). 51\u201361."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480097"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC59245.2023.00011"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640360"},{"key":"e_1_3_3_1_37_2","first-page":"560","volume-title":"Proceedings of the International Symposium on Microarchitecture (MICRO)","author":"L\u00fc Yashuai","year":"2017","unstructured":"Yashuai L\u00fc, Libo Huang, Li Shen, and Zhiying Wang. 2017. Unleashing the power of GPU for physically-based rendering via dynamic ray shuffling. In Proceedings of the International Symposium on Microarchitecture (MICRO). 560\u2013573."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2006.00933.x"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656601"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384382.3384534"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Daniel Meister Shinji Ogaki Carsten Benthin Michael\u00a0J Doyle Michael Guthe and Ji\u0159\u00ed Bittner. 2021. A survey on bounding volume hierarchies for ray tracing. Computer Graphics Forum 40 2 (2021) 683\u2013712.","DOI":"10.1111\/cgf.142662"},{"key":"e_1_3_3_1_42_2","unstructured":"Micron. 2024. Graphics memory | Micron Technology Inc.Retrieved Feb. 10 2025 from https:\/\/www.micron.com\/products\/memory\/graphics-memory"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Bochang Moon Yongyoung Byun Tae-Joon Kim Pio Claudio Hye-Sun Kim Yun-Ji Ban Seung\u00a0Woo Nam and Sung-Eui Yoon. 2010. Cache-oblivious ray reordering. ACM Transactions on Graphics (TOG) 29 3 (2010) 1\u201310.","DOI":"10.1145\/1805964.1805972"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00100"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593738"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Jae-Ho Nah Jin-Woo Kim Junho Park Won-Jong Lee Jeong-Soo Park Seok-Yoon Jung Woo-Chan Park Dinesh Manocha and Tack-Don Han. 2014. HART: A Hybrid Architecture for Ray Tracing Animated Scenes. IEEE Transactions on Visualization and Computer Graphics (TVCG) 21 3 (2014) 389\u2013401.","DOI":"10.1109\/TVCG.2014.2371855"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Jae-Ho Nah Hyuck-Joo Kwon Dong-Seok Kim Cheol-Ho Jeong Jinhong Park Tack-Don Han Dinesh Manocha and Woo-Chan Park. 2014. RayCore: A Ray-Tracing Hardware Architecture for Mobile Devices. ACM Transactions on Graphics (TOG) 33 5 (2014) 1\u201315.","DOI":"10.1145\/2629634"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/1899950.1900005"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2024156.2024194"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2007.4342596"},{"key":"e_1_3_3_1_51_2","unstructured":"Nvidia Corporation. 2023. NVIDIA ADA GPU ARCHITECTURE. Retrieved Feb. 10 2025 from https:\/\/images.nvidia.com\/aem-dam\/Solutions\/geforce\/ada\/nvidia-ada-gpu-architecture.pdf"},{"key":"e_1_3_3_1_52_2","unstructured":"Matt Pharr Wenzel Jakob and Greg Humphreys. 2023. mmp\/pbrt-v4-scenes: Example scenes for pbrt-v4. Retrieved Feb. 10 2025 from https:\/\/github.com\/mmp\/pbrt-v4-scenes"},{"key":"e_1_3_3_1_53_2","volume-title":"Physically based rendering: From theory to implementation","author":"Pharr Matt","year":"2023","unstructured":"Matt Pharr, Wenzel Jakob, and Greg Humphreys. 2023. Physically based rendering: From theory to implementation. MIT Press."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258791"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"crossref","unstructured":"Krishna Rajan Soheil Hashemi Ulya Karpuzcu Michael Doggett and Sherief Reda. 2020. Dual-precision fixed-point arithmetic for low-power ray-triangle intersections. Computers & Graphics 87 (2020) 72\u201379.","DOI":"10.1016\/j.cag.2020.01.006"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Karthik Ramani Christiaan\u00a0P. Gribble and Al Davis. 2009. StreamRay: a stream filtering architecture for coherent ray tracing. ACM SIGARCH Computer Architecture News 37 1 (2009) 325\u2013336.","DOI":"10.1145\/2528521.1508282"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00027"},{"key":"e_1_3_3_1_58_2","first-page":"27","volume-title":"Proceedings of the ACM SIGGRAPH\/EUROGRAPHICS conference on Graphics hardware","author":"Schmittler J\u00f6rg","year":"2002","unstructured":"J\u00f6rg Schmittler, Ingo Wald, and Philipp Slusallek. 2002. SaarCOR: a hardware architecture for ray tracing. In Proceedings of the ACM SIGGRAPH\/EUROGRAPHICS conference on Graphics hardware. 27\u201336."},{"key":"e_1_3_3_1_59_2","first-page":"153","volume-title":"Proceedings of Graphics Interface","author":"Segovia Benjamin","year":"2010","unstructured":"Benjamin Segovia and Manfred Ernst. 2010. Memory efficient ray tracing with hierarchical mesh quantization. In Proceedings of Graphics Interface. 153\u2013160."},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3105762.3105771"},{"key":"e_1_3_3_1_61_2","unstructured":"Siemens AG. 2024. Catapult High-Level Synthesis & Verification | Siemens Software. Retrieved Feb. 10 2025 from https:\/\/eda.sw.siemens.com\/en-US\/ic\/catapult-high-level-synthesis\/"},{"key":"e_1_3_3_1_62_2","unstructured":"Siemens AG. 2024. Questa Advanced Simulator | Siemens Software. Retrieved Feb. 10 2025 from https:\/\/eda.sw.siemens.com\/en-US\/ic\/questa\/simulation\/advanced-simulator\/"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"Josef Spjut Andrew Kensler Daniel Kopta and Erik Brunvand. 2009. TRaX: A Multicore Hardware Architecture for Real-Time Ray Tracing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 28 12 (2009) 1802\u20131815.","DOI":"10.1109\/TCAD.2009.2028981"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.45"},{"key":"e_1_3_3_1_65_2","unstructured":"Synopsys Inc.2024. Design Compiler: Timing Area Power & Test Optimization | Synopsys. Retrieved Feb. 10 2025 from https:\/\/www.synopsys.com\/implementation-and-signoff\/rtl-synthesis-test\/dc-ultra.html"},{"key":"e_1_3_3_1_66_2","unstructured":"Synopsys Inc.2024. PrimePower: RTL to Signoff Power Analysis | Synopsys. Retrieved Feb. 10 2025 from https:\/\/www.synopsys.com\/implementation-and-signoff\/signoff\/primepower.html"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14759"},{"key":"e_1_3_3_1_68_2","unstructured":"The Khronos Group Inc.2024. Home | Vulkan | Cross platform 3D Graphics. Retrieved Feb. 10 2025 from https:\/\/www.vulkan.org\/"},{"key":"e_1_3_3_1_69_2","unstructured":"TSMC. 2024. 40nm Technology - Taiwan Semiconductor Manufacturing Company Limited. Retrieved Feb. 10 2025 from https:\/\/www.tsmc.com\/english\/dedicatedFoundry\/technology\/logic\/l_40nm"},{"key":"e_1_3_3_1_70_2","first-page":"33","volume-title":"Proceedings of the Conference on High Performance Graphics (HPG)","author":"Vaidyanathan Karthikeyan","year":"2016","unstructured":"Karthikeyan Vaidyanathan, Tomas Akenine-M\u00f6ller, and Marco Salvi. 2016. Watertight Ray Traversal with Reduced Precision. In Proceedings of the Conference on High Performance Graphics (HPG). 33\u201340."},{"key":"e_1_3_3_1_71_2","first-page":"15","volume-title":"Proceedings of the Conference on High Performance Graphics (HPG)","author":"Vaidyanathan Karthik","year":"2019","unstructured":"Karthik Vaidyanathan, Sven Woop, and Carsten Benthin. 2019. Wide BVH traversal with a short stack. In Proceedings of the Conference on High Performance Graphics (HPG). 15\u201319."},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/2018323.2018330"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"crossref","unstructured":"Elena Vasiou Konstantin Shkurko Erik Brunvand and Cem Yuksel. 2020. Mach-RT: A Many Chip Architecture for High Performance Ray Tracing. IEEE Transactions on Visualization and Computer Graphics (TVCG) 28 3 (2020) 1585\u20131596.","DOI":"10.1109\/TVCG.2020.3021048"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2007.4342588"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/2018323.2018331"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"crossref","unstructured":"Ingo Wald Sven Woop Carsten Benthin Gregory\u00a0S Johnson and Manfred Ernst. 2014. Embree: a kernel framework for efficient CPU ray tracing. ACM Transactions on Graphics (TOG) 33 4 (2014) 1\u20138.","DOI":"10.1145\/2601097.2601199"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"crossref","unstructured":"Sven Woop J\u00f6rg Schmittler and Philipp Slusallek. 2005. RPU: a programmable ray processing unit for realtime ray tracing. ACM Transactions on Graphics (TOG) 24 3 (2005) 434\u2013444.","DOI":"10.1145\/1073204.1073211"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3105762.3105773"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"crossref","unstructured":"Sung-Eui Yoon and Dinesh Manocha. 2006. Cache-efficient layouts of bounding volume hierarchies. Computer Graphics Forum 25 3 (2006) 507\u2013516.","DOI":"10.1111\/j.1467-8659.2006.00970.x"}],"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\/3695053.3731104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:02:31Z","timestamp":1750503751000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":78,"alternative-id":["10.1145\/3695053.3731104","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731104","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"}}]}}