Chapter 14

Optimizing Cache Usage

Abstract

This chapter covers the fundamentals of processor caches and how temporal and spatial data locality affect performance. Section 14.1 covers the organization of the cache. Section 14.2 demonstrates how to dynamically determine the topology. Section 14.3 covers both hardware and software prefetching. Section 14.4 covers techniques for improving cache utilization.

Keywords

Cache

Ways

Associative cache

PAT

MTRR

Cache line

Cacheline

Streaming instructions

Prefetch

LLC

L1

L2

L3

AOS

SOA

Array of structs

Struct of arrays

Get Power and Performance now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.