commit | ce29f37ca00de9c5689191a9fa3fda07ce2871d4 | [log] [tgz] |
---|---|---|
author | sewardj <sewardj@a5019735-40e9-0310-863c-91ae7b9d1cf9> | Wed Oct 19 11:23:07 2005 +0000 |
committer | sewardj <sewardj@a5019735-40e9-0310-863c-91ae7b9d1cf9> | Wed Oct 19 11:23:07 2005 +0000 |
tree | 680f801dd0ec7305a6ce5afe9ea03745632bb283 | |
parent | 34f042e4f6c094a7c4a1b4c32e71ff156cff3074 [diff] |
Halve the size of the fast tt lookup cache. This improves ppc32 performance quite a bit, since the cache is emptied quite often on ppc32, and a smaller cache is less intrusive in the real machine's L2 cache. On x86 the change doesn't seem to have much effect. git-svn-id: svn://svn.valgrind.org/valgrind/trunk@4947 a5019735-40e9-0310-863c-91ae7b9d1cf9