DMCA
Understanding the Backward Slices of Performance Degrading Instructions (2000)
Cached
Download Links
| Venue: | in Proceedings of the 27th Annual International Symposium on Computer Architecture |
| Citations: | 85 - 3 self |
BibTeX
@INPROCEEDINGS{Zilles00understandingthe,
author = {Craig B. Zilles and Gurindar S. Sohi},
title = {Understanding the Backward Slices of Performance Degrading Instructions},
booktitle = {in Proceedings of the 27th Annual International Symposium on Computer Architecture},
year = {2000},
pages = {172--181}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
For many applications, branch mispredictions and cache misses limit a processor's performance to a level well below its peak instruction throughput. A small fraction of static instructions, whose behavior cannot be anticipated using current branch predictors and caches, contribute a large fraction of such performance degrading events. This paper analyzes the dynamic instruction stream leading up to these performance degrading instructions to identify the operations necessary to execute them early. The backward slice (the subset of the program that relates to the instruction) of these performance degrading instructions, if small compared to the whole dynamic instruction stream, can be pre-executed to hide the instruction's latency. To overcome conservative dependence assumptions that result in large slices, speculation can be used, resulting in speculative slices. This paper provides an initial characterization of the backward slices of L2 data cache misses and branch mispredictions, and shows the effectiveness of techniques, including memory dependence prediction and control independence, for reducing the size of these slices. Through the use of these techniques, many slices can be reduced to less than one tenth of the full dynamic instruction stream when considering the 512 instructions before the performance degrading instruction. 1
Keyphrases
backward slice performance degrading instruction branch mispredictions conservative dependence assumption full dynamic instruction stream control independence l2 data cache miss small fraction memory dependence prediction many application large fraction behavior cannot whole dynamic instruction stream static instruction large slice current branch predictor many slice peak instruction throughput initial characterization cache miss dynamic instruction stream speculative slice
