[PATCH] D23286: AMDGPU/SI: Propose to redefine image load/store intrinsics

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Mon Aug 8 20:15:05 PDT 2016


arsenm added a comment.

Why wouldn't unorm be exposed?


================
Comment at: include/llvm/IR/IntrinsicsAMDGPU.td:255
@@ -255,1 +254,3 @@
+   llvm_i1_ty,        // lwe(imm)
+   llvm_i1_ty],       // da(imm)
   []>;
----------------
da should not be exposed since it is the mangling of the coordinate type


https://reviews.llvm.org/D23286





More information about the llvm-commits mailing list