AMDGPU/SDAG: Improve {extract,insert}_subvector lowering for 16-bit vectors
authorNicolai Hähnle <nicolai.haehnle@amd.com>
Wed, 3 May 2023 20:29:48 +0000 (22:29 +0200)
committerNicolai Hähnle <nicolai.haehnle@amd.com>
Fri, 5 May 2023 08:55:18 +0000 (10:55 +0200)
commitef13308b2666be876f5a93c68c449d9fece48ac0
tree3afd9be504a9e51b9c2b393ab071fb097df2fffa
parent96e09fef3cd8cf1f8f18d6cc70ba7bb6d8dcc4c3
AMDGPU/SDAG: Improve {extract,insert}_subvector lowering for 16-bit vectors

v2:
- simplify the escape to TableGen patterns

Differential Revision: https://reviews.llvm.org/D149841
llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
llvm/test/CodeGen/AMDGPU/extract-subvector-16bit.ll
llvm/test/CodeGen/AMDGPU/scalar_to_vector.v8i16.ll