Gianmarco Accordi, Davide Gadioli, Gianluca Palermo, Luigi Crisci, Lorenzo Carpentieri, Biagio Cosenza, A. Beccari
{"title":"Unlocking performance portability on LUMI-G supercomputer: A virtual screening case study","authors":"Gianmarco Accordi, Davide Gadioli, Gianluca Palermo, Luigi Crisci, Lorenzo Carpentieri, Biagio Cosenza, A. Beccari","doi":"10.1145/3648115.3648125","DOIUrl":"https://doi.org/10.1145/3648115.3648125","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"9 3","pages":"9:1-9:4"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SYCLomatic: SYCL Adoption for Everyone - Moving from CUDA to SYCL Gets Progressively Easier: Advanced Migration Considerations","authors":"Robert Mueller-Albrecht","doi":"10.1145/3648115.3648124","DOIUrl":"https://doi.org/10.1145/3648115.3648124","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"81 5‐6","pages":"22:1-22:2"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140731777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Acceleration of Quantum Transport Simulations with OpenCL","authors":"Yosang Jeong, Hoon Ryu","doi":"10.1145/3648115.3648127","DOIUrl":"https://doi.org/10.1145/3648115.3648127","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"100 1","pages":"20:1"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140728545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"AdaptiveCpp Stdpar: C++ Standard Parallelism Integrated Into a SYCL Compiler","authors":"Aksel Alpay, Vincent Heuveline","doi":"10.1145/3648115.3648117","DOIUrl":"https://doi.org/10.1145/3648115.3648117","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"57 11","pages":"5:1-5:12"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luigi Crisci, Lorenzo Carpentieri, Peter Thoman, Aksel Alpay, Vincent Heuveline, Biagio Cosenza
Today, the SYCL standard represents the most advanced programming model for heterogeneous computing, delivering both productivity, portability, and performance in pure C++17. SYCL 2020, in particular, represents a major enhancement that pushes the boundaries of heterogeneous programming by introducing a number of new features. As the new features are implemented by existing compilers, it becomes critical to assess the maturity of the implementation through accurate and specific benchmarking. This paper presents SYCL-Bench 2020, an extended benchmark suite specifically designed to evaluate six key features of SYCL 2020: unified shared memory, reduction kernel, specialization constants, group algorithms, in-order queue, and atomics. We experimentally evaluate SYCL-Bench 2020 on GPUs from the three major vendors, i.e., AMD, Intel, and NVIDIA, and on two different SYCL implementations AdaptiveCPP and oneAPI DPC++.
{"title":"SYCL-Bench 2020: Benchmarking SYCL 2020 on AMD, Intel, and NVIDIA GPUs","authors":"Luigi Crisci, Lorenzo Carpentieri, Peter Thoman, Aksel Alpay, Vincent Heuveline, Biagio Cosenza","doi":"10.1145/3648115.3648120","DOIUrl":"https://doi.org/10.1145/3648115.3648120","url":null,"abstract":"Today, the SYCL standard represents the most advanced programming model for heterogeneous computing, delivering both productivity, portability, and performance in pure C++17. SYCL 2020, in particular, represents a major enhancement that pushes the boundaries of heterogeneous programming by introducing a number of new features. As the new features are implemented by existing compilers, it becomes critical to assess the maturity of the implementation through accurate and specific benchmarking. This paper presents SYCL-Bench 2020, an extended benchmark suite specifically designed to evaluate six key features of SYCL 2020: unified shared memory, reduction kernel, specialization constants, group algorithms, in-order queue, and atomics. We experimentally evaluate SYCL-Bench 2020 on GPUs from the three major vendors, i.e., AMD, Intel, and NVIDIA, and on two different SYCL implementations AdaptiveCPP and oneAPI DPC++.","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"278 5","pages":"1:1-1:12"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of SYCL's Different Data Parallel Kernels","authors":"Marcel Breyer, Alexander Van Craen, Dirk Pflüger","doi":"10.1145/3648115.3648130","DOIUrl":"https://doi.org/10.1145/3648115.3648130","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"172 S381","pages":"10:1-10:4"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brian Homerding, Arturo Vargas, Thomas Scogland, Robert Chen, Mike Davis, Rich Hornung
{"title":"Enabling RAJA on Intel GPUs with SYCL","authors":"Brian Homerding, Arturo Vargas, Thomas Scogland, Robert Chen, Mike Davis, Rich Hornung","doi":"10.1145/3648115.3648131","DOIUrl":"https://doi.org/10.1145/3648115.3648131","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"232 1","pages":"7:1-7:10"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nathan S. Nichols, J. T. Childers, T. Burch, Laurence Field
{"title":"Improving Performance Portability of the Procedurally Generated High Energy Physics Event Generator MadGraph Using SYCL","authors":"Nathan S. Nichols, J. T. Childers, T. Burch, Laurence Field","doi":"10.1145/3648115.3648116","DOIUrl":"https://doi.org/10.1145/3648115.3648116","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"36 4","pages":"8:1-8:8"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140728198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Migrating CUDA to SYCL: A HEP Case Study with ROOT RDataFrame","authors":"Jolly Chen, Monica Dessole, A. Varbanescu","doi":"10.1145/3648115.3648122","DOIUrl":"https://doi.org/10.1145/3648115.3648122","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"254 1","pages":"11:1-11:2"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ziran Zhang, Zhiming Wang, Chenwei Sun, Andy Huang
{"title":"Smoothing the Migration from CUDA to SYCL: SYCLomatic Utility Features","authors":"Ziran Zhang, Zhiming Wang, Chenwei Sun, Andy Huang","doi":"10.1145/3648115.3648132","DOIUrl":"https://doi.org/10.1145/3648115.3648132","url":null,"abstract":"","PeriodicalId":73497,"journal":{"name":"International Workshop on OpenCL","volume":"201 S600","pages":"14:1-14:2"},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：