HercuLeS高级合成工具中的源和ir级优化

N. Kavvadias, K. Masselos
{"title":"HercuLeS高级合成工具中的源和ir级优化","authors":"N. Kavvadias, K. Masselos","doi":"10.1504/IJIRD.2015.071089","DOIUrl":null,"url":null,"abstract":"HercuLeS is an extensible high-level synthesis environment for automatically mapping algorithms to hardware. It overcomes limitations of known work: insufficient representations, maintenance difficulties, necessity of code templates, lack of usage paradigms and vendor-dependence. Aspects that are highlighted include automatic IP integration and especially source- and intermediate-level optimising transformations. In this context, we present transformational patterns for loop and if-conversion optimisations. Further, we focus on constant multiplication and division by proposing a suitable scheme for their straightforward and decoupled utilisation in user applications. It is shown that loop optimisations provide benefits of up to 32% in cycle performance, while if-conversion delivers an average improvement of 6.5%. By applying arithmetic optimisations, a 3.3-5.9× speedup over sequential implementations is achieved. It is also shown that HercuLeS is highly competitive to state-of-the-art commercial tools.","PeriodicalId":260303,"journal":{"name":"International Journal of Innovation and Regional Development","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Source and IR-level optimisations in the HercuLeS high-level synthesis tool\",\"authors\":\"N. Kavvadias, K. Masselos\",\"doi\":\"10.1504/IJIRD.2015.071089\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"HercuLeS is an extensible high-level synthesis environment for automatically mapping algorithms to hardware. It overcomes limitations of known work: insufficient representations, maintenance difficulties, necessity of code templates, lack of usage paradigms and vendor-dependence. Aspects that are highlighted include automatic IP integration and especially source- and intermediate-level optimising transformations. In this context, we present transformational patterns for loop and if-conversion optimisations. Further, we focus on constant multiplication and division by proposing a suitable scheme for their straightforward and decoupled utilisation in user applications. It is shown that loop optimisations provide benefits of up to 32% in cycle performance, while if-conversion delivers an average improvement of 6.5%. By applying arithmetic optimisations, a 3.3-5.9× speedup over sequential implementations is achieved. It is also shown that HercuLeS is highly competitive to state-of-the-art commercial tools.\",\"PeriodicalId\":260303,\"journal\":{\"name\":\"International Journal of Innovation and Regional Development\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Innovation and Regional Development\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1504/IJIRD.2015.071089\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Innovation and Regional Development","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/IJIRD.2015.071089","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

HercuLeS是一个可扩展的高级综合环境,用于自动将算法映射到硬件。它克服了已知工作的局限性:不充分的表示、维护困难、代码模板的必要性、缺乏使用范例和对供应商的依赖性。重点强调的方面包括自动IP集成,特别是源和中间层的优化转换。在这种情况下,我们提出了循环和if转换优化的转换模式。此外,我们通过提出适合的方案来关注常数乘法和除法,以便在用户应用程序中直接解耦利用它们。结果表明,循环优化在循环性能方面提供了高达32%的好处,而if转换提供了6.5%的平均改进。通过应用算法优化,实现了比顺序实现3.3-5.9倍的加速。这也表明,与最先进的商业工具相比,HercuLeS具有很强的竞争力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Source and IR-level optimisations in the HercuLeS high-level synthesis tool
HercuLeS is an extensible high-level synthesis environment for automatically mapping algorithms to hardware. It overcomes limitations of known work: insufficient representations, maintenance difficulties, necessity of code templates, lack of usage paradigms and vendor-dependence. Aspects that are highlighted include automatic IP integration and especially source- and intermediate-level optimising transformations. In this context, we present transformational patterns for loop and if-conversion optimisations. Further, we focus on constant multiplication and division by proposing a suitable scheme for their straightforward and decoupled utilisation in user applications. It is shown that loop optimisations provide benefits of up to 32% in cycle performance, while if-conversion delivers an average improvement of 6.5%. By applying arithmetic optimisations, a 3.3-5.9× speedup over sequential implementations is achieved. It is also shown that HercuLeS is highly competitive to state-of-the-art commercial tools.
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
期刊最新文献
Social capital, regional development and innovation in Greece: an interregional analysis Investigation of regional development in Brazil: a patento-scientometric approach Innovative regional development through triple helix collaboration: a comparative case study of strategic structures and implementation Characterisation and assessment of the technological innovation network of the Valparaíso Region in Chile Social entrepreneurship and charismatic leadership: Master Cheng Yen and Tzu Chi Foundation
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1