[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)
commit1184c27fa586f8fe713921150146d433aae969ff
treebfc773ec0b1d96166f66f9b50e283336763bd307
parent034badb312bedfee9e81a933ad3ef7f0a1d8853d
[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

llvm-svn: 374910
llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
llvm/lib/Target/AMDGPU/SIInstrInfo.h
llvm/lib/Target/AMDGPU/SIInstructions.td
llvm/test/CodeGen/AMDGPU/dpp_combine.mir
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll