Regionbased Hierarchical Operation Partitioning for Multicluster 基于区域的层次划的多集群作业.ppt

下载文档 降价啦

2
0
约5.72千字
约 27页
2018-06-19 发布于福建
举报
版权申诉
保障服务

Regionbased Hierarchical Operation Partitioning for Multicluster 基于区域的层次划的多集群作业.ppt

1、本文档共27页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

Regionbased Hierarchical Operation Partitioning for Multicluster 基于区域的层次划的多集群作业

Region-based Hierarchical Operation Partitioningfor Multicluster Processors Michael Chu, Kevin Fan, Scott Mahlke Advanced Computer Architecture Lab University of Michigan * Clustered Architectures Increasing width from 4 to 8 increases total delay 29% [Palacharla ‘98] Clustered Approach: Decentralized architecture Communication through interconnection network Used in Alpha 21264, TI C6x, Analog Tigersharc and others. Basics of Multicluster Compilation Objectives: Balance workload per cluster Minimize critical intercluster communication Problem #1: Local vs Global Scope Problem #2: Scheduler-centric Cluster assignment during scheduling adds complexity Detailed resource model/reservation tables is slow Forces local decisions Our Approach Opposite approach to conventional clustering Global view Graph partitioning strategy [Aletà ‘01, ‘02] Identify tightly coupled operations - treat uniformly Non scheduler-centric mindset Prescheduling technique Doesn’t complicate scheduler Enable global view of code Estimate-based approach [Lapinskii ‘01] Region-based Hierarchical Operation Partitioning (RHOP) Code is considered region at a time Weight calculation creates guides for good partitions Partitioning clusters based on given weights Node Weights Create a metric to determine resource usage Edge Weights Slack distribution allocates slack to certain edges Edge slack = lstartdest - latencyedge - estartsrc First come, first serve method used RHOP - Partitioning Phase Modified Multilevel-KL algorithm [Kernighan ‘69] Multilevel graph partitioning consists of two stages Coarsening stage Refinement stage Cluster Refinement 3 questions to answer: Which cluster should operations move from? How good is the current partition? How profitable is it to move X from cluster A to B? Where Should Operations Move From? How Good is this Partition? How Good is This Proposed Move? Experimental Evaluation Trimaran toolset: a retargetable VLIW compiler Evaluated DSP kernels and SPECint2