Emulating Write-Allocate on a No-Write-Allocate Cache
Abstract:
A cache write-miss policy of write-allocate leads to better performance for many programs than a policy of no-write-allocate. I show a compiling technique to emulate a write-allocate policy even on a no-writeallocate machine, if that machine has nonblocking cache read misses (e.g. DEC Alpha 21064). The trick is to pre-fetch garbage before the write, so that the cache line will be allocated and the write will hit the cache. Measurements show a factor-of-1.2 improvement in execution time. Jouppi [5] analyzed cache write-miss policies.
Citations
| 134 | Cache write policies and performance – Jouppi - 1991 |
| 41 | Memory subsystem performance of programs using copying garbage collection – Diwan, Tarditi, et al. - 1994 |
| 20 | Cache memory design considerations to support languages with dynamic heap allocation – Peng, Sohi - 1989 |
| 7 | Data cache and storage control units – Hardell, Hicks, et al. - 1990 |

