Performance Optimization - Part II

4/13/99


Click here to start


Table of Contents

Performance Optimization - Part II

Compiler and Hand Tuning

SN0 Degrees of Latency

Principles of Good Cache Use

Use Stride One Access

Array Padding

TLB Thrashing

TLB Thrashing (cont.)

Blocking, or Strip Mining

Loop Optimizations

Loop Fusion

Loop Fusion (cont.)

Loop Fission

Other Loop Optimizations

Arithmetic Optimizations

Author: Shirley Browne

Email: browne@cs.utk.edu