Generating cache hints for improved program efficiency
Journal of Systems Architecture: the EUROMICRO Journal
The challenges of massive on-chip concurrency
ACSAC'05 Proceedings of the 10th Asia-Pacific conference on Advances in Computer Systems Architecture
Hi-index | 0.00 |
Recent studies on program execution behavior revealthat a large amount of execution time is spent in small frequentlyexecuted regions of code. Whereas adaptive cachemanagement systems focus on allocating cache resourcesbased on execution access patterns, this paper presents amethod of using compiler analysis to manage critical processorresources. With the addition of new architecturetechniques to direct the utilization of instruction and datacache resources, the compiler can guard the most active regionsof program execution from cache contention issues.The effect is that the overall performance of programs canbe improved by either selectively granting each dynamic regiona priority level for using cache and memory resourcesor providing active regions with dedicated cache structures.