projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 07ddb9d) | patch
[AMDGPU] V_CVT_F32_UBYTE{0,1,2,3} are full rate instructions
authorCarl Ritson <carl.ritson@amd.com>
Fri, 8 Mar 2019 09:03:11 +0000 (09:03 +0000)
committerCarl Ritson <carl.ritson@amd.com>
Fri, 8 Mar 2019 09:03:11 +0000 (09:03 +0000)
commit1a98dc184044768dd672c54b3b9557a05dd082f1
tree9913f5ffc732c591a2066e520e3a1cde09ef7308tree | snapshot
parent07ddb9d91ff6f05cdbf4639961c6e248c74a61d4commit | diff
[AMDGPU] V_CVT_F32_UBYTE{0,1,2,3} are full rate instructions

Summary: Fix a bug in the scheduling model where V_CVT_F32_UBYTE{0,1,2,3} are incorrectly marked as quarter rate instructions.

Reviewers: arsenm, rampitec

Reviewed By: rampitec

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59091

llvm-svn: 355671
llvm/lib/Target/AMDGPU/VOP1Instructions.td diff | blob | history
llvm/test/CodeGen/AMDGPU/cvt_f32_ubyte.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/udivrem24.ll diff | blob | history
Domain: System / Toolchain;