projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4bfd303) | patch
AMDGPU/SI: Fix bitcast between v2f32 and f64
authorTom Stellard <thomas.stellard@amd.com>
Tue, 15 Dec 2015 17:11:17 +0000 (17:11 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Tue, 15 Dec 2015 17:11:17 +0000 (17:11 +0000)
commitad31d10fabf065f3a64afdff8bc9203167df984b
tree411ca132ef2492bbf0cc9333995741123a464ba1tree | snapshot
parent4bfd3034414d477377a955b3ed52237ec91bdd45commit | diff
AMDGPU/SI: Fix bitcast between v2f32 and f64

The radeonsi fp64 support can hit these now that some redundant bitcasts
are folded.

Patch by: Michel Dänzer

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255657 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/SIInstructions.td diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors