Kernel Optimizations and Prefetch with the Spike Executable Optimizer
Richard Flower, Chi-Keung Luk, Robert Muth, Harish Patil, John Shakshober, Robert S. Cohn, P. Geoffrey Lowney, Shrewsbury · 2001
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.