diff options
| author | Shuxin Yang <shuxin.llvm@gmail.com> | 2013-09-19 21:13:46 +0000 |
|---|---|---|
| committer | Shuxin Yang <shuxin.llvm@gmail.com> | 2013-09-19 21:13:46 +0000 |
| commit | b1ccfb3a548e122e282cd62c534c4d47f5310bf6 (patch) | |
| tree | 39cebad965612ce61b118f5ad31abbd08026a31b /include/llvm/Support/Dwarf.h | |
| parent | bf22298093d7069fbf3a3149d26fbcb4ad453ceb (diff) | |
| download | llvm-b1ccfb3a548e122e282cd62c534c4d47f5310bf6.tar.gz llvm-b1ccfb3a548e122e282cd62c534c4d47f5310bf6.tar.bz2 llvm-b1ccfb3a548e122e282cd62c534c4d47f5310bf6.tar.xz | |
[Fast-math] Disable "(C1/X)*C2 => (C1*C2)/X" if C1/X has multiple uses.
If "C1/X" were having multiple uses, the only benefit of this
transformation is to potentially shorten critical path. But it is at the
cost of instroducing additional div.
The additional div may or may not incur cost depending on how div is
implemented. If it is implemented using Newton–Raphson iteration, it dosen't
seem to incur any cost (FIXME). However, if the div blocks the entire
pipeline, that sounds to be pretty expensive. Let CodeGen to take care
this transformation.
This patch sees 6% on a benchmark.
rdar://15032743
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191037 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'include/llvm/Support/Dwarf.h')
0 files changed, 0 insertions, 0 deletions