Approaching a smart sharing of resources in SMT processors

DMCA

Approaching a smart sharing of resources in SMT processors (2004)

Cached

Download Links

by Francisco J. Cazorla , Enrique Fern , Alex Ramirez , Mateo Valero

Venue:	In Proc. WCED
Citations:	1 - 1 self

BibTeX

@INPROCEEDINGS{Cazorla04approachinga,
    author = {Francisco J. Cazorla and Enrique Fern and Alex Ramirez and Mateo Valero},
    title = {Approaching a smart sharing of resources in SMT processors},
    booktitle = {In Proc. WCED},
    year = {2004}
}

OpenURL

Abstract

SMT processors increase performance by executing instructions from several threads simultaneously. These threads use the processor’s resources better by sharing them, but, at the same time, threads are competing for these resources. The way critical resources are distributed among threads determines the final throughput and also the performance of each individual thread. Currently, the processor instruction fetch policy decides each cycle which threads enter the processor to compete for resources. However, these fetch policies only use indirect indicators of how resource allocation is carried out. This may cause resource monopolization by a single thread, or wasted resources when no thread can use them. Both situations can harm the processor performance and occur, for example, after an L2 cache miss. This paper is a first step toward dynamic resource allocation for SMT processors. We show that being conscious about resource demand and directly controlling resource assignment significantly im-proves performance of SMTs. We introduce for the first time the concept of resource allocation policy in order to provide such a control. Our results show that our resource allocation policy outperforms the best published fetch policies for throughput and fairness, like FLUSH, by 7 % on average. In addition, our resource allocation policy does not need to squash instructions from the pipeline, like FLUSH, in order to get this performance improvement. As a result, it reduces dynamic power consumption and hardware complexity. 1

Keyphrases

smt processor resource allocation policy smart sharing resource assignment processor instruction fetch policy indirect indicator hardware complexity performance improvement processor resource resource allocation resource monopolization resource demand l2 cache miss fetch policy several thread im-proves performance dynamic power consumption way critical resource final throughput first step first time individual thread processor performance single thread dynamic resource allocation

DMCA