{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:00Z","timestamp":1750309560928,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3723851.3723860","type":"proceedings-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:42:19Z","timestamp":1745379739000},"page":"45-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Vendor GPU Programming: Extending CUDA Beyond NVIDIA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8341-3083","authenticated-orcid":false,"given":"Manos","family":"Pavlidakis","sequence":"first","affiliation":[{"name":"Spectral Compute, Iraklio, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3224-5021","authenticated-orcid":false,"given":"Chris","family":"Kitching","sequence":"additional","affiliation":[{"name":"Spectral Compute, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4216-7524","authenticated-orcid":false,"given":"Nicholas","family":"Tomlinson","sequence":"additional","affiliation":[{"name":"Spectral Compute, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0304-5341","authenticated-orcid":false,"given":"Michael","family":"S\u00f8ndergaard","sequence":"additional","affiliation":[{"name":"Spectral Compute, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,19]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"AMD. 2022. Fundamentals of HIP Programming. Retrieved April 2023 from https:\/\/www.amd.com\/system\/files\/documents\/hip-coding-3.pdf"},{"key":"e_1_3_3_1_3_2","unstructured":"AMD. 2025. rocThrust. Retrieved January 2025 from https:\/\/github.com\/ROCm\/rocThrust\/tree\/release\/rocm-rel-6.2"},{"key":"e_1_3_3_1_4_2","volume-title":"PACT \u201922","author":"Bao Yuhui","year":"2023","unstructured":"Yuhui Bao, Yifan Sun, Zlatan Feric, Michael\u00a0Tian Shen, Micah Weston, Jos\u00e9\u00a0L. Abell\u00e1n, Trinayan Baruah, John Kim, Ajay Joshi, and David Kaeli. 2023. NaviSim: A Highly Accurate GPU Simulator for AMD RDNA GPUs. In PACT \u201922."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2742060.2743766"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_1_8_2","volume-title":"OSDI \u201918","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et\u00a0al. 2018. TVM: An automated { End-to-End} optimizing compiler for deep learning. In OSDI \u201918."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"e_1_3_3_1_10_2","unstructured":"Milosz Ciznicki. 2013. GPU JPEG2K. Retrieved January 2025 from https:\/\/github.com\/ePirat\/gpu_jpeg2k"},{"key":"e_1_3_3_1_11_2","unstructured":"Advanced\u00a0Micro Devices. 2020. HIPify. Retrieved May 2023 from https:\/\/docs.amd.com\/bundle\/HIPify-Reference-Guide-v5.1\/page\/HIPify.html"},{"key":"e_1_3_3_1_12_2","volume-title":"ArXiv","author":"Douze Matthijs","year":"2024","unstructured":"Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazar\u00e9, Maria Lomeli, Lucas Hosseini, and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. In ArXiv."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6474"},{"key":"e_1_3_3_1_14_2","volume-title":"ISCA \u201917","author":"al. Jouppi\u00a0Norman et.","year":"2017","unstructured":"Jouppi\u00a0Norman et. al.2017. In-Datacenter Performance Analysis of a Tensor Processing Unit. In ISCA \u201917."},{"key":"e_1_3_3_1_15_2","unstructured":"Georgi Gerganov. 2024. Inference of Meta\u2019s LLaMA model (and others) in pure C\/C++. Retrieved November 2024 from https:\/\/github.com\/ggerganov\/llama.cpp"},{"key":"e_1_3_3_1_16_2","unstructured":"Kronos Group. 2022. SYCL2020. Retrieved May 2023 from https:\/\/www.khronos.org\/sycl\/"},{"key":"e_1_3_3_1_17_2","unstructured":"hashcat. 2022. hashcat. Retrieved January 2025 from https:\/\/github.com\/hashcat\/hashcat"},{"key":"e_1_3_3_1_18_2","unstructured":"Christian Heinemann. 2025. ALIEN - Explore worlds of artificial life. Retrieved January 2025 from https:\/\/github.com\/chrxh\/alien"},{"key":"e_1_3_3_1_19_2","unstructured":"Intel. 2020. oneAPI. Retrieved May 2023 from https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/tools\/oneapi.html#gs.4ac4fz"},{"key":"e_1_3_3_1_20_2","unstructured":"Andrzej Janik. 2024. ZLUDA\u2019s third life. Retrieved October 2024 from https:\/\/vosen.github.io\/ZLUDA\/blog\/zludas-third-life\/"},{"key":"e_1_3_3_1_21_2","volume-title":"Advances in Computers","author":"Lee Kyuho\u00a0J","year":"2021","unstructured":"Kyuho\u00a0J Lee. 2021. Architecture of neural processing unit for deep neural networks. In Advances in Computers."},{"key":"e_1_3_3_1_22_2","unstructured":"LLVM. 2025. Compiling CUDA with clang. Retrieved January 2025 from https:\/\/llvm.org\/docs\/CompileCudaWithLLVM.html#id11"},{"key":"e_1_3_3_1_23_2","unstructured":"B. Martin J. Jan M. Martin P. Jiri H. Martin and H. Petr. 2019. JPEG Encoder and Decoder Library and Console Application for NVIDIA GPUs. Retrieved January 2025 from https:\/\/github.com\/CESNET\/GPUJPEG"},{"key":"e_1_3_3_1_24_2","unstructured":"Modular. 2025. Welcome to MAX. Retrieved January 2025 from https:\/\/docs.modular.com\/max\/intro"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3648115.3648124"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1137\/140980260"},{"key":"e_1_3_3_1_28_2","volume-title":"SoftwareX","author":"Nejahi Younes","year":"2021","unstructured":"Younes Nejahi, Mohammad\u00a0Soroush Barhaghi, Gregory Schwing, Loren Schwiebert, and Jeffrey Potoff. 2021. Update 2.70 to \u201cGOMC: GPU Optimized Monte Carlo for the simulation of phase equilibria and physical properties of complex fluids\u201d. In SoftwareX."},{"key":"e_1_3_3_1_29_2","unstructured":"NVIDIA. 2023. Parallel Thread Execution ISA. Retrieved May 2023 from https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html"},{"key":"e_1_3_3_1_30_2","unstructured":"NVIDIA. 2023. Thrust: The C++ Parallel Algorithms Library. Retrieved November 2024 from https:\/\/github.com\/NVIDIA\/thrust"},{"key":"e_1_3_3_1_31_2","unstructured":"OpenXLA. 2025. OpenXLA. Retrieved January 2025 from https:\/\/openxla.org\/xla"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3704440.3704779"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563467"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652892.3700768"},{"key":"e_1_3_3_1_35_2","volume-title":"Software: Practice and Experience","author":"Richmond Paul","year":"2023","unstructured":"Paul Richmond, Robert Chisholm, Peter Heywood, Mozhgan\u00a0Kabiri Chimeh, and Matthew Leach. 2023. FLAME GPU 2: A framework for flexible and performant agent based simulation on GPUs. In Software: Practice and Experience."},{"key":"e_1_3_3_1_36_2","volume-title":"MICRO \u201921","author":"Shao Yakun\u00a0Sophia","year":"2021","unstructured":"Yakun\u00a0Sophia Shao, Jason Cemons, Rangharajan Venkatesan, Brian Zimmer, Matthew Fojtik, Nan Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Stephen\u00a0G. Tell, Yanqing Zhang, William\u00a0J. Dally, Joel Emer, C.\u00a0Thomas Gray, Brucek Khailany, and Stephen\u00a0W. Keckler. 2021. Simba: Scaling Deep-Learning Inference with Chiplet-Based Architecture. In MICRO \u201921."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2899231"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_3_1_39_2","volume-title":"Morgan Kaufmann","author":"Wen-mei W\u00a0Hwu","year":"2015","unstructured":"W\u00a0Hwu Wen-mei. 2015. Heterogeneous System Architecture: A new compute platform infrastructure. In Morgan Kaufmann."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854041"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378466"}],"event":{"name":"HCDS '25: 4th Workshop on Heterogeneous Composable and Disaggregated Systems","acronym":"HCDS '25","location":"Rotterdam Netherlands"},"container-title":["Proceedings of the 4th Workshop on Heterogeneous Composable and Disaggregated Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723851.3723860","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723851.3723860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:00Z","timestamp":1750295940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723851.3723860"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":40,"alternative-id":["10.1145\/3723851.3723860","10.1145\/3723851"],"URL":"https:\/\/doi.org\/10.1145\/3723851.3723860","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}