projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 01f1273) | patch
AMDGPU: Remove wrapper only call limitation
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Wed, 6 Jan 2021 19:04:19 +0000 (14:04 -0500)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Tue, 12 Jan 2021 22:12:49 +0000 (17:12 -0500)
commit3d397091591fca4aa16153bba22f031218bee47d
treebdec606af45dd4a3b4813a1727b53d1ae297b442tree | snapshot
parent01f1273fe2f0c246f17162de24a8b6e11bad23a8commit | diff
AMDGPU: Remove wrapper only call limitation

This seems to only have overridden cold handling, which we probably
shouldn't do. As far as I can tell the wrapper library functions are
still inlined as appropriate.
llvm/lib/Target/AMDGPU/AMDGPUInline.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll diff | blob | history
Domain: System / Toolchain;