]> granicus.if.org Git - llvm/commit
[AMDGPU] Support mov dpp with 64 bit operands
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Tue, 15 Oct 2019 16:41:15 +0000 (16:41 +0000)
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Tue, 15 Oct 2019 16:41:15 +0000 (16:41 +0000)
commite7c9c5bebdaa6dbf81ea02ca9ebac6763641d1cb
tree2d46aba59aea55f79f52a938715dcc3fa9f74d7b
parent325a4c24567b0a12b7e800fcff0cec9a97a0176a
[AMDGPU] Support mov dpp with 64 bit operands

We define mov/update dpp intrinsics as overloaded but do not
support i64, which is a practically useful type. Fix the
selection and lowering.

Differential Revision: https://reviews.llvm.org/D68673

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@374910 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/GCNDPPCombine.cpp
lib/Target/AMDGPU/SIInstrInfo.cpp
lib/Target/AMDGPU/SIInstrInfo.h
lib/Target/AMDGPU/SIInstructions.td
test/CodeGen/AMDGPU/dpp_combine.mir
test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll