Evaluation of Compiler-Controlled Updating to Reduce Coherence-Miss Penalties in Shared-Memory Multiprocessors

Author： Skeppstedt J. Dahlgren F. Stenström P.

ISSN： 0743-7315

Source： Journal of Parallel and Distributed Computing, Vol.56, Iss.2, 1999-02, pp. : 122-143

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

We consider in this paper the effectiveness of a new approach called compiler-controlled updating to reduce coherence-miss penalties in shared-memory multiprocessors. A key part of the method is a compiler algorithm that identifies the last store instruction to a memory block in a flow graph using classic dataflow analysis techniques. Such stores are marked and replaced by update instructions that at run time make the memory copy clean. Whereas this static method shortens the read-miss latency for actively shared blocks, it can cause useless traffic for shared blocks that are effectively private. We therefore complement the static analysis with a dynamic simple heuristic in the cache coherence protocol aiming at classifying blocks as private or shared at run time. We evaluate the performance effects of compiler-controlled updating using six scientific parallel applications compiled by an optimizing compiler that incorporates our static analysis and then running them on a detailed CC-NUMA architectural simulation model. We have found that the compiler algorithm can convert between 83 and 100% of the dirty misses into clean misses. By adding the private/shared heuristic, the update traffic of private memory blocks can be practically eliminated. Overall, the static analysis in combination with the dynamic heuristic is shown to reduce the execution time by as much as 32%. Copyright 1999 Academic Press.

Related content

A Compiler-Directed Approach to Network Latency Reduction for Distributed Shared Memory Multiprocessors

By Ray S. Jiang H. Yang Q.

Journal of Parallel and Distributed Computing, Vol. 38, Iss. 2, 1996-11 ,pp. : 267-276 (10)

Academic Press

Access to resources Recommend Favorite

Scalable barrier synchronisation for large-scale shared-memory multiprocessors

By Fang Zhen Zhang Lixin Carter John B. Parker Mike

International Journal of High Performance Computing and Networking, Vol. 1, Iss. 1-2, 2005-08 ,pp. : 33-42 (10)

Inderscience Publishers

Access to resources Recommend Favorite

Comparing Processor Allocation Strategies in Multiprogrammed Shared-Memory Multiprocessors

By Yue K.K. Lilja D.J.

Journal of Parallel and Distributed Computing, Vol. 49, Iss. 2, 1998-03 ,pp. : 245-258 (14)

Academic Press

Access to resources Recommend Favorite

The Performance Implications of Locality Information Usage in Shared-Memory Multiprocessors

By Bellosa F. Steckermeier M.

Journal of Parallel and Distributed Computing, Vol. 37, Iss. 1, 1996-08 ,pp. : 113-121 (9)

Academic Press

Access to resources Recommend Favorite

An evaluation of hardware-based and compiler-controlled optimizations of snooping cache protocols

By Dahlgren F. Skeppstedt J. Stenstrom P.

Future Generation Computer Systems, Vol. 13, Iss. 6, 1998-05 ,pp. : 469-487 (19)

Elsevier

Access to resources Recommend Favorite