Accession Number:

ADA202001

Title:

Micro-Optimization of Floating-Point Operations

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE MICROSYSTEMS RESEARCH CENTER

Personal Author(s):

Report Date:

1988-08-01

Pagination or Media Count:

15.0

Abstract:

This paper describes micro-optimization, a technique for reducing the operation count and time required to perform floating-point calculations. Micro optimization involves breaking floating-point operations into their constituent micro-operations and optimizing the resulting code. Exposing micro-operations to the compiler creates many opportunities for optimization. Redundant normalization operations can be eliminated or combined. Also, scheduling micro- operations separately results allows dependent operations to be partially overlapped. A prototype expression compiler has been written to evaluate a number of micro-optimizations. On a set of benchmark expressions operation count is reduced by 33 and execution time is reduced by 40.

Subject Categories:

  • Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE