[PATCH] D46754: [AMDGPU] Add intrinsics for 16 bit interpolation

[Tim Corringham via Phabricator via llvm-commits]

timcorringham created this revision.
Herald added subscribers: llvm-commits, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl, arsenm.

Added the intrinsics llvm.amdgcn.interp.p1.f16() and
llvm.amdgcn.interp.p2.f16() and related LIT test.

The p1 intrinsic generates code appropriate for both 16 and 32
bank LDS.


Repository:
  rL LLVM

https://reviews.llvm.org/D46754

Files:
  include/llvm/IR/IntrinsicsAMDGPU.td
  lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  lib/Target/AMDGPU/AMDGPUISelLowering.h
  lib/Target/AMDGPU/AMDGPUInstrInfo.td
  lib/Target/AMDGPU/AMDGPUSearchableTables.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/VOP3Instructions.td
  test/CodeGen/AMDGPU/llvm.amdgcn.interp.f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D46754.146317.patch
Type: text/x-patch
Size: 12735 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180511/68c14295/attachment.bin>