2021 IEEE International Symposium on Workload Characterization (IISWC)最新文献

筛选

英文中文

Copernicus: Characterizing the Performance Implications of Compression Formats Used in Sparse Workloads 哥白尼:描述稀疏工作负载中使用的压缩格式的性能含义

2021 IEEE International Symposium on Workload Characterization (IISWC) Pub Date : 2020-11-22 DOI: 10.1109/IISWC53511.2021.00012

Bahar Asgari, Ramyad Hadidi, Joshua Dierberger, Charlotte Steinichen, Hyesoon Kim

{"title":"Copernicus: Characterizing the Performance Implications of Compression Formats Used in Sparse Workloads","authors":"Bahar Asgari, Ramyad Hadidi, Joshua Dierberger, Charlotte Steinichen, Hyesoon Kim","doi":"10.1109/IISWC53511.2021.00012","DOIUrl":"https://doi.org/10.1109/IISWC53511.2021.00012","url":null,"abstract":"Sparse matrices are the key ingredients of several application domains, from scientific computing to machine learning. The primary challenge with sparse matrices has been efficiently storing and transferring data, for which many sparse formats have been proposed to significantly eliminate zero entries. Such formats, essentially designed to optimize memory footprint, may not be as successful in performing faster processing. In other words, although they allow faster data transfer and improve memory bandwidth utilization - the classic challenge of sparse problems - their decompression mechanism can potentially create a computation bottleneck. Not only is this challenge not resolved, but also it becomes more serious with the advent of domain-specific architectures (DSAs), as they intend to more aggressively improve performance. The performance implications of using various formats along with DSAs, however, has not been extensively studied by prior work. To fill this gap of knowledge, we characterize the impact of using seven frequently used compression formats on performance, based on a DSA for sparse matrix-vector multiplication (SpMV), implemented on an FPGA using high-level synthesis (HLS) tools, a growing and popular method for developing DSAs. Seeking a fair comparison, we tailor and well-optimize the HLS implementation of decompression for each format. We explore metrics, including decompression overhead, latency, balance ratio, throughput, memory bandwidth utilization, resource utilization, and power consumption, on a variety of real-world and synthetic sparse workloads.","PeriodicalId":203713,"journal":{"name":"2021 IEEE International Symposium on Workload Characterization (IISWC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117060606","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}

引用次数: 9

首页上一页