Chapter

Transactions on High-Performance Embedded Architectures and Compilers IV

Volume 6760 of the series Lecture Notes in Computer Science pp 1-20

A High Performance Adaptive Miss Handling Architecture for Chip Multiprocessors

  • Magnus JahreAffiliated withHiPEAC European Network of Excellence, Norwegian University of Science and Technology
  • , Lasse NatvigAffiliated withHiPEAC European Network of Excellence, Norwegian University of Science and Technology

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Chip Multiprocessors (CMPs) mainly base their performance gains on exploiting thread-level parallelism. Consequently, powerful memory systems are needed to support an increasing number of concurrent threads. Conventional CMP memory systems do not account for thread interference which can result in reduced overall system performance. Therefore, conventional high bandwidth Miss Handling Architectures (MHAs) are not well suited to CMPs because they can create severe memory bus congestion. However, high miss bandwidth is desirable when sufficient bus bandwidth is available. This paper presents a novel, CMP-specific technique called the Adaptive Miss Handling Architecture (AMHA). If the memory bus is congested, AMHA improves performance by dynamically reducing the maximum allowed number of concurrent L1 cache misses of a processor core if this creates a significant speedup for the other processors. Compared to a 16-wide conventional MHA, AMHA improves performance by 12% on average for one of the workload collections used in this work.