This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 5ccd8badb18 [llvm-objdump] Removed archive-headers-disas test new a46b1e54f3f [CostModel][X86] Add UDIV/UREM by pow2 costs new e5d3d151346 AMDGPU/GlobalISel: Implement custom kernel arg lowering new 5ad067fad46 AMDGPU: Don't use spir_kernel in a test new 30ba76520af Fix asserts in AMDGCN fmed3 folding by handling more cases of NaN
The 4 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "adds" were already present in the repository and have only been added to this reference.
Summary of changes: lib/Target/AMDGPU/AMDGPUCallLowering.cpp | 48 +- lib/Target/AMDGPU/AMDGPUCallLowering.h | 5 +- lib/Target/AMDGPU/AMDGPUCallingConv.td | 15 - lib/Target/AMDGPU/AMDGPUISelLowering.cpp | 4 +- lib/Target/X86/X86TargetTransformInfo.cpp | 44 +- lib/Transforms/InstCombine/InstCombineCalls.cpp | 25 +- test/Analysis/CostModel/X86/div.ll | 361 ++++++---- test/Analysis/CostModel/X86/rem.ll | 234 +++++-- .../GlobalISel/irtranslator-amdgpu_kernel.ll | 723 +++++++++++++++++++++ test/CodeGen/AMDGPU/coalescer_distribute.ll | 5 +- test/CodeGen/AMDGPU/kernel-args.ll | 86 ++- .../InstCombine/AMDGPU/amdgcn-intrinsics.ll | 48 +- 12 files changed, 1344 insertions(+), 254 deletions(-) create mode 100644 test/CodeGen/AMDGPU/GlobalISel/irtranslator-amdgpu_kernel.ll