commit | 8d84d5b62cdf2a772d51338136c7022a6e1ff931 | [log] [tgz] |
---|---|---|
author | Evan Cheng <evan.cheng@apple.com> | Mon Mar 24 06:37:48 2008 +0000 |
committer | Evan Cheng <evan.cheng@apple.com> | Mon Mar 24 06:37:48 2008 +0000 |
tree | 4ad44203af29e98cb7c89ddd60b731e582e9fd4a | |
parent | 16b412c6e278d84bcf71b1bf07a7d3c24e81a49e [diff] |
Increasing the inline limit from (overly conservative) 200 to 300. Given each BB costs 20 and each instruction costs 5, 200 means a 4 BB function + 24 instructions (actually less because caller's size also contributes to it). Furthermore, double the limit when more than 10% of the callee instructions are vector instructions. Multimedia kernels tend to love inlining. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48725 91177308-0d34-0410-b5e6-96231b3b80d8