projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8fbb88f) | patch
[AMDGPU] Use custom inserter for gfx10 VOP2b
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Mon, 17 Jun 2019 22:37:37 +0000 (22:37 +0000)
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Mon, 17 Jun 2019 22:37:37 +0000 (22:37 +0000)
commit121956108f274f15a24ecc6df729e9cba8d2bb37
tree77d53b85c869770e8902f1a08787cfffd4dcaa36tree | snapshot
parent8fbb88fbff5e0fef1418650f2d3f716598344d97commit | diff
[AMDGPU] Use custom inserter for gfx10 VOP2b

This is part of the approved D63204 pending parent revision.
This small change is in fact a part of the VOP2b legalization which
does not technically belong to wave32 support, so extracted
separately.

llvm-svn: 363625
llvm/lib/Target/AMDGPU/VOP2Instructions.td diff | blob | history
Domain: System / Toolchain;