[PATCH] D72931: AMDGPU: Add a16 feature to gfx10

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: nhaehnle, rampitec.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

It seems like this was accidentally dropped.

      

No test since the selected a16 images still fail the verifier.


https://reviews.llvm.org/D72931

Files:
  llvm/lib/Target/AMDGPU/AMDGPU.td


Index: llvm/lib/Target/AMDGPU/AMDGPU.td
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPU.td
+++ llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -848,6 +848,7 @@
     [FeatureGFX10,
      FeatureLDSBankCount32,
      FeatureDLInsts,
+     FeatureR128A16,
      FeatureNSAEncoding,
      FeatureWavefrontSize32,
      FeatureScalarStores,
@@ -866,6 +867,7 @@
      FeatureDot2Insts,
      FeatureDot5Insts,
      FeatureDot6Insts,
+     FeatureR128A16,
      FeatureNSAEncoding,
      FeatureWavefrontSize32,
      FeatureScalarStores,
@@ -883,6 +885,7 @@
      FeatureDot2Insts,
      FeatureDot5Insts,
      FeatureDot6Insts,
+     FeatureR128A16,
      FeatureNSAEncoding,
      FeatureWavefrontSize32,
      FeatureScalarStores,


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D72931.238794.patch
Type: text/x-patch
Size: 772 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200117/00ef900c/attachment.bin>