Dynamically exploiting narrow width operands to improve processor power and performance

David Brooks, Margaret Martonosi

Research output: Contribution to conferencePaper

212 Scopus citations

Abstract

In general-purpose microprocessors, recent trends have pushed towards 64-bit word widths, primarily to accommodate the large addressing needs of some programs. Many integer problems, however, rarely need the full 64-bit dynamic range these CPUs provide. In fact, another recent instruction set trend has been increased support for sub-word operations (that is, manipulating data in quantities less than the full word size). In particular, most major processor families have introduced `multimedia' instruction set extensions that operate in parallel on several sub-word quantities in the same ALU. This paper notes that across the SPECint95 benchmarks, over half of the integer operation executions require 16 bits or less. With this as motivation, our work proposes hardware mechanisms that dynamically recognize and capitalize on these `narrow-bitwidth' instances. Both optimizations require little additional hardware, and neither requires compiler support. The first, power-oriented, optimization reduces processor power consumption by using aggressive clock gating to turn off portions of integer arithmetic units that will be unnecessary for narrow bitwidth operations. This optimization results in an over 50% reduction in the integer unit's power consumption for the SPECint95 and MediaBench benchmark suites. The second optimization improves performance by merging together narrow integer operations and allowing them to share a single functional unit. Conceptually akin to a dynamic form of MMX, this optimization offers speedups of 4.3%-6.2% for SPECint95 and 8.0%-10.4% for MediaBench.

Original languageEnglish (US)
Pages13-22
Number of pages10
DOIs
StatePublished - Jan 1 1999
EventProceedings of the 1999 5th International Symposium on High-Performance Computer Architecture, HPCA - Orlando, FL, USA
Duration: Jan 9 1999Jan 13 1999

Other

OtherProceedings of the 1999 5th International Symposium on High-Performance Computer Architecture, HPCA
CityOrlando, FL, USA
Period1/9/991/13/99

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Dynamically exploiting narrow width operands to improve processor power and performance'. Together they form a unique fingerprint.

Cite this