Kernel Optimizations and Prefetch with the Spike Executable Optimizer (2001)
| Venue: | In Proceedings of the 4th Workshop on Feedback-Directed and Dynamic Optimization (FDDO-4 |
| Citations: | 10 - 0 self |
BibTeX
@INPROCEEDINGS{Flower01kerneloptimizations,
author = {Richard Flower and Chi-Keung Luk and Robert Muth and Harish Patil and John Shakshober and Robert Cohn and P. Geoffrey Lowney},
title = {Kernel Optimizations and Prefetch with the Spike Executable Optimizer},
booktitle = {In Proceedings of the 4th Workshop on Feedback-Directed and Dynamic Optimization (FDDO-4},
year = {2001}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Spike is an executable optimizer that uses profile information to place application code for improved fetch efficiency and reduced cache footprint. This placement reduces the number of cache misses and the latencies they add to program execution time. This paper presents extensions of Spike to take advantage of three additional performance opportunities: 1) optimization of the Unix kernel code, 2) prefetching to reduce latencies of long latency loads, and 3) prefetching for loads with predictable strides that are not detected at compile-time.
