Ruobing Han, Jun Chen, Bhanu Garg, Xule Zhou, John Lu, Jeffrey Young, Jaewoong Sim, Hyesoon Kim
{"title":"CuPBoP:让 CUDA 成为可移植语言","authors":"Ruobing Han, Jun Chen, Bhanu Garg, Xule Zhou, John Lu, Jeffrey Young, Jaewoong Sim, Hyesoon Kim","doi":"10.1145/3659949","DOIUrl":null,"url":null,"abstract":"CUDA is designed specifically for NVIDIA GPUs and is not compatible with non-NVIDIA devices. Enabling CUDA execution on alternative backends could greatly benefit the hardware community by fostering a more diverse software ecosystem.\n To address the need for portability, our objective is to develop a framework that meets key requirements, such as extensive coverage, comprehensive end-to-end support, superior performance, and hardware scalability. Existing solutions that translate CUDA source code into other high-level languages, however, fall short of these goals.\n In contrast to these source-to-source approaches, we present a novel framework, CuPBoP, which treats CUDA as a portable language in its own right. Compared to two commercial source-to-source solutions, CuPBoP offers a broader coverage and superior performance for the CUDA-to-CPU migration. Additionally, we evaluate the performance of CuPBoP against manually optimized CPU programs, highlighting the differences between CPU programs derived from CUDA and those that are manually optimized.\n Furthermore, we demonstrate the hardware scalability of CuPBoP by showcasing its successful migration of CUDA to AMD GPUs.\n To promote further research in this field, we have released CuPBoP as an open-source resource.","PeriodicalId":50944,"journal":{"name":"ACM Transactions on Design Automation of Electronic Systems","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CuPBoP: Making CUDA a Portable Language\",\"authors\":\"Ruobing Han, Jun Chen, Bhanu Garg, Xule Zhou, John Lu, Jeffrey Young, Jaewoong Sim, Hyesoon Kim\",\"doi\":\"10.1145/3659949\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"CUDA is designed specifically for NVIDIA GPUs and is not compatible with non-NVIDIA devices. Enabling CUDA execution on alternative backends could greatly benefit the hardware community by fostering a more diverse software ecosystem.\\n To address the need for portability, our objective is to develop a framework that meets key requirements, such as extensive coverage, comprehensive end-to-end support, superior performance, and hardware scalability. Existing solutions that translate CUDA source code into other high-level languages, however, fall short of these goals.\\n In contrast to these source-to-source approaches, we present a novel framework, CuPBoP, which treats CUDA as a portable language in its own right. Compared to two commercial source-to-source solutions, CuPBoP offers a broader coverage and superior performance for the CUDA-to-CPU migration. Additionally, we evaluate the performance of CuPBoP against manually optimized CPU programs, highlighting the differences between CPU programs derived from CUDA and those that are manually optimized.\\n Furthermore, we demonstrate the hardware scalability of CuPBoP by showcasing its successful migration of CUDA to AMD GPUs.\\n To promote further research in this field, we have released CuPBoP as an open-source resource.\",\"PeriodicalId\":50944,\"journal\":{\"name\":\"ACM Transactions on Design Automation of Electronic Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-04-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Transactions on Design Automation of Electronic Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1145/3659949\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Design Automation of Electronic Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3659949","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0
摘要
CUDA 专为英伟达™(NVIDIA®)GPU 设计,与非英伟达™(NVIDIA®)设备不兼容。在其他后端上执行 CUDA 可以促进软件生态系统的多样化,从而使硬件社区受益匪浅。为了满足可移植性的需求,我们的目标是开发一个能满足关键要求的框架,如广泛的覆盖范围、全面的端到端支持、卓越的性能和硬件可扩展性。然而,现有的将 CUDA 源代码翻译成其他高级语言的解决方案无法实现这些目标。与这些源代码到源代码的方法不同,我们提出了一个新颖的框架 CuPBoP,它将 CUDA 本身视为一种可移植语言。与两种商业源代码到源代码解决方案相比,CuPBoP 为 CUDA 到 CPU 的迁移提供了更广泛的覆盖范围和更优越的性能。此外,我们还评估了 CuPBoP 与经过人工优化的 CPU 程序的性能,强调了从 CUDA 派生的 CPU 程序与经过人工优化的 CPU 程序之间的差异。此外,我们还展示了 CuPBoP 的硬件可扩展性,成功地将 CUDA 移植到 AMD GPU。为促进该领域的进一步研究,我们已将 CuPBoP 作为开源资源发布。
CUDA is designed specifically for NVIDIA GPUs and is not compatible with non-NVIDIA devices. Enabling CUDA execution on alternative backends could greatly benefit the hardware community by fostering a more diverse software ecosystem.
To address the need for portability, our objective is to develop a framework that meets key requirements, such as extensive coverage, comprehensive end-to-end support, superior performance, and hardware scalability. Existing solutions that translate CUDA source code into other high-level languages, however, fall short of these goals.
In contrast to these source-to-source approaches, we present a novel framework, CuPBoP, which treats CUDA as a portable language in its own right. Compared to two commercial source-to-source solutions, CuPBoP offers a broader coverage and superior performance for the CUDA-to-CPU migration. Additionally, we evaluate the performance of CuPBoP against manually optimized CPU programs, highlighting the differences between CPU programs derived from CUDA and those that are manually optimized.
Furthermore, we demonstrate the hardware scalability of CuPBoP by showcasing its successful migration of CUDA to AMD GPUs.
To promote further research in this field, we have released CuPBoP as an open-source resource.
期刊介绍:
TODAES is a premier ACM journal in design and automation of electronic systems. It publishes innovative work documenting significant research and development advances on the specification, design, analysis, simulation, testing, and evaluation of electronic systems, emphasizing a computer science/engineering orientation. Both theoretical analysis and practical solutions are welcome.