projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 7ab54fc) | patch
AMDGPU: Implement {{s|u}}int_to_fp i64 -> f32
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 11 Jan 2016 22:01:48 +0000 (22:01 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 11 Jan 2016 22:01:48 +0000 (22:01 +0000)
commit6e3a667705ac8f405e91cc378a299548834c11aa
tree7edcd0daad734f3461ff9006641b8ae6b1d2b6e8tree | snapshot
parent7ab54fc926fd2ef4b7826957b3f6b9bf1963f01ccommit | diff
AMDGPU: Implement {{s|u}}int_to_fp i64 -> f32

The old lowering for uint_to_fp failed opencl conformance.
It might be OK for fast math mode, but I'm not sure.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@257393 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/AMDGPUISelLowering.cpp diff | blob | history
lib/Target/AMDGPU/AMDGPUISelLowering.h diff | blob | history
test/CodeGen/AMDGPU/sint_to_fp.i64.ll [new file with mode: 0644] blob
test/CodeGen/AMDGPU/uint_to_fp.i64.ll [new file with mode: 0644] blob
test/CodeGen/AMDGPU/uint_to_fp.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors