通过绕过SPIR-V,简化提前SYCL CPU设备实现

Wenju He, Yilong Guo, Xinmin Tian, Hideki Saito, Wenwan Xing, Feng Zou, Chunyang Dai, Maosu Zhao, Haonan Yang
{"title":"通过绕过SPIR-V,简化提前SYCL CPU设备实现","authors":"Wenju He, Yilong Guo, Xinmin Tian, Hideki Saito, Wenwan Xing, Feng Zou, Chunyang Dai, Maosu Zhao, Haonan Yang","doi":"10.1145/3585341.3585381","DOIUrl":null,"url":null,"abstract":"Here we present the design and implementation of our LLVM-based Ahead-Of-Time (AOT) SYCL CPU device without using SPIR-V, known as non-SPIRV CPU device. Our design of non-SPIRV CPU device is intended to highlight a general SYCL CPU implementation that aims for both debuggability and performance. Contributions: • Streamline compiler optimization pipeline by integrating kernel optimizations and transformations into LLVM C++ pipeline. • Eliminate SPIR-V IR generation during the CPU device code compilation and leverage LLVM IR from compiler front-end directly to reduce compilation overhead and preserve IR information including debug info, among LLVM passes.","PeriodicalId":360830,"journal":{"name":"Proceedings of the 2023 International Workshop on OpenCL","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Streamline Ahead-of-Time SYCL CPU Device Implementation through Bypassing SPIR-V\",\"authors\":\"Wenju He, Yilong Guo, Xinmin Tian, Hideki Saito, Wenwan Xing, Feng Zou, Chunyang Dai, Maosu Zhao, Haonan Yang\",\"doi\":\"10.1145/3585341.3585381\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Here we present the design and implementation of our LLVM-based Ahead-Of-Time (AOT) SYCL CPU device without using SPIR-V, known as non-SPIRV CPU device. Our design of non-SPIRV CPU device is intended to highlight a general SYCL CPU implementation that aims for both debuggability and performance. Contributions: • Streamline compiler optimization pipeline by integrating kernel optimizations and transformations into LLVM C++ pipeline. • Eliminate SPIR-V IR generation during the CPU device code compilation and leverage LLVM IR from compiler front-end directly to reduce compilation overhead and preserve IR information including debug info, among LLVM passes.\",\"PeriodicalId\":360830,\"journal\":{\"name\":\"Proceedings of the 2023 International Workshop on OpenCL\",\"volume\":\"24 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2023 International Workshop on OpenCL\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3585341.3585381\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2023 International Workshop on OpenCL","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3585341.3585381","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在这里,我们介绍了不使用spirv的基于llvm的提前(AOT) SYCL CPU设备的设计和实现,称为非spirv CPU设备。我们设计的非spirv CPU设备旨在突出一个通用的SYCL CPU实现,其目标是可调试性和性能。•通过将内核优化和转换集成到LLVM c++管道中,简化编译器优化管道。•在CPU设备代码编译期间消除SPIR-V IR生成,并直接从编译器前端利用LLVM IR,以减少编译开销,并在LLVM传递中保留包括调试信息在内的IR信息。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Streamline Ahead-of-Time SYCL CPU Device Implementation through Bypassing SPIR-V
Here we present the design and implementation of our LLVM-based Ahead-Of-Time (AOT) SYCL CPU device without using SPIR-V, known as non-SPIRV CPU device. Our design of non-SPIRV CPU device is intended to highlight a general SYCL CPU implementation that aims for both debuggability and performance. Contributions: • Streamline compiler optimization pipeline by integrating kernel optimizations and transformations into LLVM C++ pipeline. • Eliminate SPIR-V IR generation during the CPU device code compilation and leverage LLVM IR from compiler front-end directly to reduce compilation overhead and preserve IR information including debug info, among LLVM passes.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信