diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2016-07-06 19:15:54 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2016-07-06 19:15:54 +0000 |
| commit | 04b3496d9b35405f367b893b3cd64210dcb5b4fa (patch) | |
| tree | 23cf094444cedb4f923bf92d8d361b6c1777abdc /llvm/lib/Transforms | |
| parent | cc464d560c4fafbb9aaebe27e85eef02a61801b9 (diff) | |
| download | bcm5719-llvm-04b3496d9b35405f367b893b3cd64210dcb5b4fa.tar.gz bcm5719-llvm-04b3496d9b35405f367b893b3cd64210dcb5b4fa.zip | |
[x86] fix cost of SINT_TO_FP for i32 --> float (PR21356, PR28434)
This is "cvtdq2ps" which does not appear to be particularly slow on any CPU
according to Agner's tables. Choosing "5" as a cost here as suggested in:
https://llvm.org/bugs/show_bug.cgi?id=21356
...but it seems very conservative given that the instruction is fully pipelined,
and I think these costs are supposed to model throughput.
Note that related costs are also most likely too high, but this fixes PR21356
and partly fixes PR28434.
llvm-svn: 274658
Diffstat (limited to 'llvm/lib/Transforms')
0 files changed, 0 insertions, 0 deletions
