Luis G. León-Vega, Niccolò Tosato, Stefano Cozzini
{"title":"全面分析带 GPU 的多插槽系统的过程能耗","authors":"Luis G. León-Vega, Niccolò Tosato, Stefano Cozzini","doi":"arxiv-2409.04941","DOIUrl":null,"url":null,"abstract":"Robustly estimating energy consumption in High-Performance Computing (HPC) is\nessential for assessing the energy footprint of modern workloads, particularly\nin fields such as Artificial Intelligence (AI) research, development, and\ndeployment. The extensive use of supercomputers for AI training has heightened\nconcerns about energy consumption and carbon emissions. Existing energy\nestimation tools often assume exclusive use of computing nodes, a premise that\nbecomes problematic with the advent of supercomputers integrating\nmicroservices, as seen in initiatives like Acceleration as a Service (XaaS) and\ncloud computing. This work investigates the impact of executed instructions on overall power\nconsumption, providing insights into the comprehensive behaviour of HPC\nsystems. We introduce two novel mathematical models to estimate a process's\nenergy consumption based on the total node energy, process usage, and a\nnormalised vector of the probability distribution of instruction types for CPU\nand GPU processes. Our approach enables energy accounting for specific\nprocesses without the need for isolation. Our models demonstrate high accuracy, predicting CPU power consumption with a\nmere 1.9% error. For GPU predictions, the models achieve a central relative\nerror of 9.7%, showing a clear tendency to fit the test data accurately. These\nresults pave the way for new tools to measure and account for energy\nconsumption in shared supercomputing environments.","PeriodicalId":501291,"journal":{"name":"arXiv - CS - Performance","volume":"26 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Comprehensive Analysis of Process Energy Consumption on Multi-Socket Systems with GPUs\",\"authors\":\"Luis G. León-Vega, Niccolò Tosato, Stefano Cozzini\",\"doi\":\"arxiv-2409.04941\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Robustly estimating energy consumption in High-Performance Computing (HPC) is\\nessential for assessing the energy footprint of modern workloads, particularly\\nin fields such as Artificial Intelligence (AI) research, development, and\\ndeployment. The extensive use of supercomputers for AI training has heightened\\nconcerns about energy consumption and carbon emissions. Existing energy\\nestimation tools often assume exclusive use of computing nodes, a premise that\\nbecomes problematic with the advent of supercomputers integrating\\nmicroservices, as seen in initiatives like Acceleration as a Service (XaaS) and\\ncloud computing. This work investigates the impact of executed instructions on overall power\\nconsumption, providing insights into the comprehensive behaviour of HPC\\nsystems. We introduce two novel mathematical models to estimate a process's\\nenergy consumption based on the total node energy, process usage, and a\\nnormalised vector of the probability distribution of instruction types for CPU\\nand GPU processes. Our approach enables energy accounting for specific\\nprocesses without the need for isolation. Our models demonstrate high accuracy, predicting CPU power consumption with a\\nmere 1.9% error. For GPU predictions, the models achieve a central relative\\nerror of 9.7%, showing a clear tendency to fit the test data accurately. These\\nresults pave the way for new tools to measure and account for energy\\nconsumption in shared supercomputing environments.\",\"PeriodicalId\":501291,\"journal\":{\"name\":\"arXiv - CS - Performance\",\"volume\":\"26 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Performance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.04941\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Performance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04941","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
要评估现代工作负载的能源足迹,尤其是在人工智能(AI)研究、开发和部署等领域,必须对高性能计算(HPC)的能耗进行可靠估算。超级计算机在人工智能训练中的广泛应用加剧了人们对能源消耗和碳排放的担忧。现有的能耗估算工具通常假定只使用计算节点,而随着集成了微服务的超级计算机的出现,这一前提就成了问题,这在加速即服务(XaaS)和云计算等计划中都有所体现。这项工作研究了执行指令对总体功耗的影响,为了解高性能计算系统的综合行为提供了见解。我们引入了两个新颖的数学模型,根据 CPU 和 GPU 进程的节点总能耗、进程使用率和指令类型概率分布的规范化向量来估算进程的能耗。我们的方法无需隔离就能对特定进程进行能量核算。我们的模型具有很高的准确性,对 CPU 功耗的预测误差仅为 1.9%。对于 GPU 预测,模型的中心相对误差为 9.7%,显示出准确拟合测试数据的明显趋势。这些结果为测量和计算共享超级计算环境能耗的新工具铺平了道路。
A Comprehensive Analysis of Process Energy Consumption on Multi-Socket Systems with GPUs
Robustly estimating energy consumption in High-Performance Computing (HPC) is
essential for assessing the energy footprint of modern workloads, particularly
in fields such as Artificial Intelligence (AI) research, development, and
deployment. The extensive use of supercomputers for AI training has heightened
concerns about energy consumption and carbon emissions. Existing energy
estimation tools often assume exclusive use of computing nodes, a premise that
becomes problematic with the advent of supercomputers integrating
microservices, as seen in initiatives like Acceleration as a Service (XaaS) and
cloud computing. This work investigates the impact of executed instructions on overall power
consumption, providing insights into the comprehensive behaviour of HPC
systems. We introduce two novel mathematical models to estimate a process's
energy consumption based on the total node energy, process usage, and a
normalised vector of the probability distribution of instruction types for CPU
and GPU processes. Our approach enables energy accounting for specific
processes without the need for isolation. Our models demonstrate high accuracy, predicting CPU power consumption with a
mere 1.9% error. For GPU predictions, the models achieve a central relative
error of 9.7%, showing a clear tendency to fit the test data accurately. These
results pave the way for new tools to measure and account for energy
consumption in shared supercomputing environments.