[PATCH] D73482: [AMDGPU] Fix lowering a16 image intrinsics
Sebastian Neubauer via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 27 07:53:23 PST 2020
sebastian-ne created this revision.
sebastian-ne added reviewers: nhaehnle, rtaylor, arsenm.
Herald added subscribers: llvm-commits, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.
scalar_to_vector takes only one argument, not two.
The a16 tests now take a vector of halfs as the input instead of halfs
alone so they are packed into registers and the generated code should be
more deterministic.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D73482
Files:
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.a16.encode.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.a16.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.a16.dim.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73482.240589.patch
Type: text/x-patch
Size: 45930 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200127/62882866/attachment.bin>
More information about the llvm-commits
mailing list