[PATCH] D102066: [AMDGPU] Fix codegen of image intrinsics for g16 and a16

[David Stuttard via Phabricator via llvm-commits]

dstuttard added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:4233
+  if (BaseOpcode->Gradients && !ST.hasG16() && (IsA16 != IsG16))
+    // 16 bit gradients are supported, but are tied to the A16 control
+    // so both gradients and addresses must be 16 bit
----------------
foad wrote:
> Braces around this multi-line if body please (maybe `git clang-format @^` can do this for you?).
Interestingly, git clang-format didn't do this (I usually run it before any commits).


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102066/new/

https://reviews.llvm.org/D102066