ConvStencil：将模板计算转换为张量核上的矩阵乘法

ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming Pub Date : 2024-02-20 DOI:10.1145/3627535.3638476

Yuetao Chen, Kun Li, Yuhao Wang, Donglin Bai, Lei Wang, Lingxiao Ma, Liang Yuan, Yunquan Zhang, Ting Cao, Mao Yang

{"title":"ConvStencil：将模板计算转换为张量核上的矩阵乘法","authors":"Yuetao Chen, Kun Li, Yuhao Wang, Donglin Bai, Lei Wang, Lingxiao Ma, Liang Yuan, Yunquan Zhang, Ting Cao, Mao Yang","doi":"10.1145/3627535.3638476","DOIUrl":null,"url":null,"abstract":"Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil 1 , a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide al-gorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2)","PeriodicalId":286119,"journal":{"name":"ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming","volume":"485 ","pages":"333-347"},"PeriodicalIF":0.0000,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores\",\"authors\":\"Yuetao Chen, Kun Li, Yuhao Wang, Donglin Bai, Lei Wang, Lingxiao Ma, Liang Yuan, Yunquan Zhang, Ting Cao, Mao Yang\",\"doi\":\"10.1145/3627535.3638476\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil 1 , a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide al-gorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2)\",\"PeriodicalId\":286119,\"journal\":{\"name\":\"ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming\",\"volume\":\"485 \",\"pages\":\"333-347\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3627535.3638476\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3627535.3638476","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

张量核心单元（TCU）越来越多地被集成到现代高性能处理器中，以提高矩阵乘法性能。然而，受限于其规格过高，它在改进模版计算等其他关键科学运算方面的潜力仍未得到开发。本文介绍的 ConvStencil 1 是一种新型模版计算系统，旨在将模版计算高效地转换为张量核上的矩阵乘法。我们首先为 ConvStencil 建立了一个性能模型，以指导 TCU 上的算法设计和优化。基于该模型，我们提出了三种技术：(1) 使用 stencil2row 方法进行内存高效布局转换；(2) 在 Tensor Cores 上进行矩阵乘法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

ConvStencil: Transform Stencil Computation to Matrix Multiplication on Tensor Cores

Tensor Core Unit (TCU) is increasingly integrated into modern high-performance processors to enhance matrix multiplication performance. However, constrained to its over-specification, its potential for improving other critical scientific operations like stencil computations remains untapped. This paper presents ConvStencil 1 , a novel stencil computing system designed to efficiently transform stencil computation to matrix multiplication on Tensor Cores. We first develop a performance model for ConvStencil to guide al-gorithm design and optimization on TCUs. Based on this model, we propose three techniques: (1) Memory-efficient Layout Transformation using the stencil2row method; (2)

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

ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming

自引率

0.00%

发文量