projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9563f3b) | patch
[AMDGPU] Add SelectionDAG support for insert_subvector on v4f64
authorCarl Ritson <carl.ritson@amd.com>
Tue, 27 Jul 2021 00:36:39 +0000 (09:36 +0900)
committerCarl Ritson <carl.ritson@amd.com>
Tue, 27 Jul 2021 01:11:34 +0000 (10:11 +0900)
commitfbaa35e169474c5ad2e211fdc1ec74f8e56546ab
treed431dfd841f19d595e385f2095ddeebab1a3eb14tree | snapshot
parent9563f3b571d1dc1f40a546a86c11904b1748ff86commit | diff
[AMDGPU] Add SelectionDAG support for insert_subvector on v4f64

Enable custom insert_subvector for larger vector types.
This is necessary now that SelectionDAG can attempt v3f64 insert
to v4f64, etc.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D105385
llvm/lib/Target/AMDGPU/SIISelLowering.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/bug-v4f64-subvector.ll [new file with mode: 0644] blob
Domain: System / Toolchain;