{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:38:01Z","timestamp":1768030681329,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"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":[[2023,4,18]]},"DOI":"10.1145\/3585341.3585372","type":"proceedings-article","created":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T14:05:24Z","timestamp":1680789924000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Experiences Migrating CUDA to SYCL: A Molecular Docking Case Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-9879","authenticated-orcid":false,"given":"Leonardo","family":"Solis-Vasquez","sequence":"first","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4717-3481","authenticated-orcid":false,"given":"Edward","family":"Mascarenhas","sequence":"additional","affiliation":[{"name":"Intel Corporation, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1164-3082","authenticated-orcid":false,"given":"Andreas","family":"Koch","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,4,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.jpdc.2022.03.017","article-title":"Evaluation of Intel\u2019s DPC++ Compatibility Tool in heterogeneous computing","volume":"165","author":"Casta\u00f1o Germ\u00e1n","year":"2022","unstructured":"Germ\u00e1n Casta\u00f1o , Youssef Faqir-Rhazoui , Carlos Garc\u00eda , and Manuel Prieto-Mat\u00edas . 2022 . Evaluation of Intel\u2019s DPC++ Compatibility Tool in heterogeneous computing . J. Parallel and Distrib. Comput. 165 (2022), 120 \u2013 129 . https:\/\/doi.org\/10.1016\/j.jpdc.2022.03.017 10.1016\/j.jpdc.2022.03.017 Germ\u00e1n Casta\u00f1o, Youssef Faqir-Rhazoui, Carlos Garc\u00eda, and Manuel Prieto-Mat\u00edas. 2022. Evaluation of Intel\u2019s DPC++ Compatibility Tool in heterogeneous computing. J. Parallel and Distrib. Comput. 165 (2022), 120\u2013129. https:\/\/doi.org\/10.1016\/j.jpdc.2022.03.017","journal-title":"J. Parallel and Distrib. Comput."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 359\u2013367","author":"Christgau Steffen","year":"2020","unstructured":"Steffen Christgau and Thomas Steinke . 2020 . Porting a Legacy CUDA Stencil Code to oneAPI . In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 359\u2013367 . https:\/\/doi.org\/10.1109\/IPDPSW50202.2020.00070 10.1109\/IPDPSW50202.2020.00070 Steffen Christgau and Thomas Steinke. 2020. Porting a Legacy CUDA Stencil Code to oneAPI. In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 359\u2013367. https:\/\/doi.org\/10.1109\/IPDPSW50202.2020.00070"},{"key":"e_1_3_2_1_3_1","unstructured":"Codeplay. 2022. SYCL Guide. https:\/\/developer.codeplay.com\/products\/computecpp\/ce\/2.11.0\/guides\/sycl-guide  Codeplay. 2022. SYCL Guide. https:\/\/developer.codeplay.com\/products\/computecpp\/ce\/2.11.0\/guides\/sycl-guide"},{"key":"e_1_3_2_1_4_1","volume-title":"Bioinformatics and Biomedical Engineering (IWBBIO)","author":"Costanzo Manuel","unstructured":"Manuel Costanzo , Enzo Rucci , Carlos Garc\u00eda-S\u00e1nchez , Marcelo Naiouf , and Manuel Prieto-Mat\u00edas . 2022. Migrating CUDA to oneAPI: A Smith-Waterman Case Study . In Bioinformatics and Biomedical Engineering (IWBBIO) . Springer , 103\u2013116. https:\/\/doi.org\/10.1007\/978-3-031-07802-6_9 10.1007\/978-3-031-07802-6_9 Manuel Costanzo, Enzo Rucci, Carlos Garc\u00eda-S\u00e1nchez, Marcelo Naiouf, and Manuel Prieto-Mat\u00edas. 2022. Migrating CUDA to oneAPI: A Smith-Waterman Case Study. In Bioinformatics and Biomedical Engineering (IWBBIO). Springer, 103\u2013116. https:\/\/doi.org\/10.1007\/978-3-031-07802-6_9"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.10115"},{"key":"e_1_3_2_1_6_1","unstructured":"Intel. 2021. Intel DPC++ Compatibility Tool. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compatibility-tool.html  Intel. 2021. Intel DPC++ Compatibility Tool. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compatibility-tool.html"},{"key":"e_1_3_2_1_7_1","unstructured":"Intel. 2022. Intel Xeon Platinum 8360Y Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/212459\/intel-xeon-platinum-8360y-processor-54m-cache-2-40-ghz\/specifications.html  Intel. 2022. Intel Xeon Platinum 8360Y Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/212459\/intel-xeon-platinum-8360y-processor-54m-cache-2-40-ghz\/specifications.html"},{"key":"e_1_3_2_1_8_1","unstructured":"Intel. 2022. oneAPI Centers of Excellence. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/training\/academic-program\/centers-of-excellence.htm  Intel. 2022. oneAPI Centers of Excellence. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/training\/academic-program\/centers-of-excellence.htm"},{"key":"e_1_3_2_1_9_1","unstructured":"Intel. 2022. oneAPI DPC++ Compiler Documentation - Considerations for Programming to Multi-Tile and Multi-Card under Level-Zero Backend. https:\/\/intel.github.io\/llvm-docs\/MultiTileCardWithLevelZero.html  Intel. 2022. oneAPI DPC++ Compiler Documentation - Considerations for Programming to Multi-Tile and Multi-Card under Level-Zero Backend. https:\/\/intel.github.io\/llvm-docs\/MultiTileCardWithLevelZero.html"},{"key":"e_1_3_2_1_10_1","unstructured":"Intel. 2022. SYCL Thread Mapping and GPU Occupancy. https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/oneapi-gpu-optimization-guide\/top\/thread-mapping.html  Intel. 2022. SYCL Thread Mapping and GPU Occupancy. https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/oneapi-gpu-optimization-guide\/top\/thread-mapping.html"},{"key":"e_1_3_2_1_11_1","unstructured":"Intel. 2022. SYCLomatic: A New CUDA-to-SYCL Code Migration Tool. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/syclomatic-new-cuda-to-sycl-code-migration-tool.html  Intel. 2022. SYCLomatic: A New CUDA-to-SYCL Code Migration Tool. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/syclomatic-new-cuda-to-sycl-code-migration-tool.html"},{"key":"e_1_3_2_1_12_1","unstructured":"Intel. 2022. Xe-HPC GPU Architecture. https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/oneapi-gpu-optimization-guide\/top\/xe-arch.html  Intel. 2022. Xe-HPC GPU Architecture. https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/oneapi-gpu-optimization-guide\/top\/xe-arch.html"},{"key":"e_1_3_2_1_13_1","unstructured":"Intel. 2023. Intel Data Center GPU Max 1550. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/232873\/intel-data-center-gpu-max-1550.html  Intel. 2023. Intel Data Center GPU Max 1550. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/232873\/intel-data-center-gpu-max-1550.html"},{"key":"e_1_3_2_1_14_1","series-title":"Max Series CPUs","volume-title":"Intel Launches 4th Gen Xeon Scalable Processors","unstructured":"Intel. 2023. Intel Launches 4th Gen Xeon Scalable Processors , Max Series CPUs . https:\/\/www.intel.com\/content\/www\/us\/en\/newsroom\/news\/4th-gen-xeon-scalable-processors-max-series-cpus-gpus.htm Intel. 2023. Intel Launches 4th Gen Xeon Scalable Processors, Max Series CPUs. https:\/\/www.intel.com\/content\/www\/us\/en\/newsroom\/news\/4th-gen-xeon-scalable-processors-max-series-cpus-gpus.htm"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 371\u2013376","author":"Jin Zheming","year":"2021","unstructured":"Zheming Jin and Jeffrey Vetter . 2021 . Evaluating CUDA Portability with HIPCL and DPCT . In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 371\u2013376 . https:\/\/doi.org\/10.1109\/IPDPSW52791.2021.00065 10.1109\/IPDPSW52791.2021.00065 Zheming Jin and Jeffrey Vetter. 2021. Evaluating CUDA Portability with HIPCL and DPCT. In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 371\u2013376. https:\/\/doi.org\/10.1109\/IPDPSW52791.2021.00065"},{"key":"e_1_3_2_1_16_1","unstructured":"Khronos Group. 2022. SYCL Resources. https:\/\/www.khronos.org\/sycl\/resources  Khronos Group. 2022. SYCL Resources. https:\/\/www.khronos.org\/sycl\/resources"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 11th International Conference on Bioinformatics, Computational Biology and Health Informatics. ACM. https:\/\/doi.org\/10","author":"LeGrand Scott","year":"2020","unstructured":"Scott LeGrand , Aaron Scheinberg , Andreas\u00a0 F. Tillack , Mathialakan Thavappiragasam , Josh\u00a0 V. Vermaas , Rupesh Agarwal , Jeff Larkin , Duncan Poole , Diogo Santos-Martins , Leonardo Solis-Vasquez , Andreas Koch , Stefano Forli , Oscar Hernandez , Jeremy\u00a0 C. Smith , and Ada Sedova . 2020 . GPU-Accelerated Drug Discovery with Docking on the Summit Supercomputer: Porting, Optimization, and Application to COVID-19 Research . In Proceedings of the 11th International Conference on Bioinformatics, Computational Biology and Health Informatics. ACM. https:\/\/doi.org\/10 .1145\/3388440.3412472 10.1145\/3388440.3412472 Scott LeGrand, Aaron Scheinberg, Andreas\u00a0F. Tillack, Mathialakan Thavappiragasam, Josh\u00a0V. Vermaas, Rupesh Agarwal, Jeff Larkin, Duncan Poole, Diogo Santos-Martins, Leonardo Solis-Vasquez, Andreas Koch, Stefano Forli, Oscar Hernandez, Jeremy\u00a0C. Smith, and Ada Sedova. 2020. GPU-Accelerated Drug Discovery with Docking on the Summit Supercomputer: Porting, Optimization, and Application to COVID-19 Research. In Proceedings of the 11th International Conference on Bioinformatics, Computational Biology and Health Informatics. ACM. https:\/\/doi.org\/10.1145\/3388440.3412472"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-987X(19981115)19:14<1639::AID-JCC10>3.0.CO;2-B"},{"key":"e_1_3_2_1_19_1","unstructured":"NVIDIA. 2022. Accelerated Apps Catalog. https:\/\/www.nvidia.com\/en-us\/gpu-accelerated-applications  NVIDIA. 2022. Accelerated Apps Catalog. https:\/\/www.nvidia.com\/en-us\/gpu-accelerated-applications"},{"key":"e_1_3_2_1_20_1","unstructured":"NVIDIA. 2022. NVIDIA A100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/a100  NVIDIA. 2022. NVIDIA A100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/a100"},{"key":"e_1_3_2_1_21_1","unstructured":"NVIDIA. 2022. NVIDIA Nsight Compute. https:\/\/developer.nvidia.com\/nsight-compute  NVIDIA. 2022. NVIDIA Nsight Compute. https:\/\/developer.nvidia.com\/nsight-compute"},{"key":"e_1_3_2_1_22_1","unstructured":"oneAPI. 2022. oneAPI Spec Elements. https:\/\/www.oneapi.io\/spec  oneAPI. 2022. oneAPI Spec Elements. https:\/\/www.oneapi.io\/spec"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.0c01006"},{"key":"e_1_3_2_1_24_1","unstructured":"Scripps Research. [n. d.]. AutoDock-GPU: AutoDock for GPUs and other accelerators. https:\/\/github.com\/ccsb-scripps\/AutoDock-GPU  Scripps Research. [n. d.]. AutoDock-GPU: AutoDock for GPUs and other accelerators. https:\/\/github.com\/ccsb-scripps\/AutoDock-GPU"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.6.1.19"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 11th Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 1\u201310","author":"Solis-Vasquez Leonardo","year":"2021","unstructured":"Leonardo Solis-Vasquez , Erich Focht , and Andreas Koch . 2021 . Mapping Irregular Computations for Molecular Docking to the SX-Aurora TSUBASA Vector Engine . In Proceedings of the 11th Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 1\u201310 . https:\/\/doi.org\/10.1109\/IA354616.2021.00008 10.1109\/IA354616.2021.00008 Leonardo Solis-Vasquez, Erich Focht, and Andreas Koch. 2021. Mapping Irregular Computations for Molecular Docking to the SX-Aurora TSUBASA Vector Engine. In Proceedings of the 11th Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 1\u201310. https:\/\/doi.org\/10.1109\/IA354616.2021.00008"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 5th International Workshop on FPGAs for Software Programmers (FSP)","author":"Solis-Vasquez Leonardo","year":"2018","unstructured":"Leonardo Solis-Vasquez and Andreas Koch . 2018 . A Case Study in Using OpenCL on FPGAs: Creating an Open-Source Accelerator of the AutoDock Molecular Docking Software . In Proceedings of the 5th International Workshop on FPGAs for Software Programmers (FSP) ( Dublin, Ireland). VDE Verlag, 1\u201310. Leonardo Solis-Vasquez and Andreas Koch. 2018. A Case Study in Using OpenCL on FPGAs: Creating an Open-Source Accelerator of the AutoDock Molecular Docking Software. In Proceedings of the 5th International Workshop on FPGAs for Software Programmers (FSP) (Dublin, Ireland). VDE Verlag, 1\u201310."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 10th International Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 12\u201321","author":"Solis-Vasquez Leonardo","year":"2020","unstructured":"Leonardo Solis-Vasquez , Diogo Santos-Martins , Andreas Tillack , Andreas F.\u00a0 Koch , J\u00e9r\u00f4me Eberhardt , and Stefano Forli . 2020 . Parallelizing Irregular Computations for Molecular Docking . In Proceedings of the 10th International Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 12\u201321 . https:\/\/doi.org\/10.1109\/IA351965.2020.00008 10.1109\/IA351965.2020.00008 Leonardo Solis-Vasquez, Diogo Santos-Martins, Andreas Tillack, Andreas F.\u00a0Koch, J\u00e9r\u00f4me Eberhardt, and Stefano Forli. 2020. Parallelizing Irregular Computations for Molecular Docking. In Proceedings of the 10th International Workshop on Irregular Applications: Architectures and Algorithms (IA3). IEEE, 12\u201321. https:\/\/doi.org\/10.1109\/IA351965.2020.00008"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"102861","DOI":"10.1016\/j.parco.2021.102861","article-title":"Benchmarking the performance of irregular computations in AutoDock-GPU molecular docking","volume":"109","author":"Solis-Vasquez Leonardo","year":"2022","unstructured":"Leonardo Solis-Vasquez , Andreas\u00a0 F. Tillack , Diogo Santos-Martins , Andreas Koch , Scott LeGrand , and Stefano Forli . 2022 . Benchmarking the performance of irregular computations in AutoDock-GPU molecular docking . Parallel Comput. 109 (2022), 102861 . https:\/\/doi.org\/10.1016\/j.parco.2021.102861 10.1016\/j.parco.2021.102861 Leonardo Solis-Vasquez, Andreas\u00a0F. Tillack, Diogo Santos-Martins, Andreas Koch, Scott LeGrand, and Stefano Forli. 2022. Benchmarking the performance of irregular computations in AutoDock-GPU molecular docking. Parallel Comput. 109 (2022), 102861. https:\/\/doi.org\/10.1016\/j.parco.2021.102861","journal-title":"Parallel Comput."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 36\u201344","author":"Thavappiragasam Mathialakan","year":"2020","unstructured":"Mathialakan Thavappiragasam , Aaron Scheinberg , Wael Elwasif , Oscar Hernandez , and Ada Sedova . 2020 . Performance Portability of Molecular Docking Miniapp On Leadership Computing Platforms . In Proceedings of the International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 36\u201344 . https:\/\/doi.org\/10.1109\/P3HPC51967.2020.00009 10.1109\/P3HPC51967.2020.00009 Mathialakan Thavappiragasam, Aaron Scheinberg, Wael Elwasif, Oscar Hernandez, and Ada Sedova. 2020. Performance Portability of Molecular Docking Miniapp On Leadership Computing Platforms. In Proceedings of the International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 36\u201344. https:\/\/doi.org\/10.1109\/P3HPC51967.2020.00009"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 360\u2013370","author":"Wang Yong","year":"2021","unstructured":"Yong Wang , Yongfa Zhou , Qi\u00a0Scott Wang , Yang Wang , Qing Xu , Chen Wang , Bo Peng , Zhaojun Zhu , Katayama Takuya , and Dylan Wang . 2021 . Developing medical ultrasound beamforming application on GPU and FPGA using oneAPI . In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 360\u2013370 . https:\/\/doi.org\/10.1109\/IPDPSW52791.2021.00064 10.1109\/IPDPSW52791.2021.00064 Yong Wang, Yongfa Zhou, Qi\u00a0Scott Wang, Yang Wang, Qing Xu, Chen Wang, Bo Peng, Zhaojun Zhu, Katayama Takuya, and Dylan Wang. 2021. Developing medical ultrasound beamforming application on GPU and FPGA using oneAPI. In Proceedings of the International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 360\u2013370. https:\/\/doi.org\/10.1109\/IPDPSW52791.2021.00064"},{"key":"e_1_3_2_1_32_1","unstructured":"World Community Grid. 2021. OpenPandemics - COVID-19 Now Running on Machines with Graphics Processing Units. https:\/\/www.worldcommunitygrid.org\/about_us\/viewNewsArticle.do?articleId=693  World Community Grid. 2021. OpenPandemics - COVID-19 Now Running on Machines with Graphics Processing Units. https:\/\/www.worldcommunitygrid.org\/about_us\/viewNewsArticle.do?articleId=693"},{"key":"e_1_3_2_1_33_1","volume-title":"ADADELTA: An Adaptive Learning Rate Method. arXiv abs\/1212.5701","author":"Zeiler D.","year":"2012","unstructured":"Matthew\u00a0 D. Zeiler . 2012 . ADADELTA: An Adaptive Learning Rate Method. arXiv abs\/1212.5701 (2012). Matthew\u00a0D. Zeiler. 2012. ADADELTA: An Adaptive Learning Rate Method. arXiv abs\/1212.5701 (2012)."}],"event":{"name":"IWOCL '23: International Workshop on OpenCL","location":"Cambridge United Kingdom","acronym":"IWOCL '23"},"container-title":["International Workshop on OpenCL"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585341.3585372","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:56Z","timestamp":1750178276000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585341.3585372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,18]]},"references-count":33,"alternative-id":["10.1145\/3585341.3585372","10.1145\/3585341"],"URL":"https:\/\/doi.org\/10.1145\/3585341.3585372","relation":{},"subject":[],"published":{"date-parts":[[2023,4,18]]},"assertion":[{"value":"2023-04-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}