This is an automated email from the git hooks/post-receive script.

unknown user pushed a change to branch master in repository llvm.

from 50b4952 Clear the PendingTypeTests vector after moving from it. new 15a4f4e AMDGPU: Update isFPImmLegal for f16 new 0bb2ef4 AMDGPU: Implement f16 fcanonicalize new 4bb9991 AMDGPU: Custom lower f16 fdiv new a8dff18 AMDGPU: Allow rcp and rsq usage with f16

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/AMDGPUCodeGenPrepare.cpp | 1 - lib/Target/AMDGPU/AMDGPUISelLowering.cpp | 3 +- lib/Target/AMDGPU/AMDGPUInstructions.td | 1 + lib/Target/AMDGPU/SIISelLowering.cpp | 36 ++++- lib/Target/AMDGPU/SIISelLowering.h | 1 + lib/Target/AMDGPU/SIInstructions.td | 5 + test/CodeGen/AMDGPU/fcanonicalize.f16.ll | 172 ++++++++++++++++++++++ test/CodeGen/AMDGPU/fdiv.f16.ll | 224 ++++++++++++++++++++++++++--- 8 files changed, 416 insertions(+), 27 deletions(-) create mode 100644 test/CodeGen/AMDGPU/fcanonicalize.f16.ll