[llvm] [AMDGPU] CodeGen for GFX12 VIMAGE and VSAMPLE instructions (PR #75488)

Jay Foad via llvm-commits llvm-commits at lists.llvm.org
Fri Jan 19 05:45:35 PST 2024


================
@@ -845,7 +845,9 @@ class AMDGPUImageDimIntrinsic<AMDGPUDimProfile P_,
       !if(P_.IsSample, [llvm_v4i32_ty,           // samp(SGPR)
                         llvm_i1_ty], []),        // unorm(imm)
       [llvm_i32_ty,                              // texfailctrl(imm; bit 0 = tfe, bit 1 = lwe)
-       llvm_i32_ty]),                            // cachepolicy(imm; bit 0 = glc, bit 1 = slc, bit 2 = dlc)
+       llvm_i32_ty]),                            // cachepolicy(imm; bit 0 = glc, bit 1 = slc, bit 2 = dlc;
+                                                 //   gfx12+ imm: bits [0-2] = th, bits [3-4] = scope)
+                                                 // TODO-GFX12: Update all other cachepolicy descriptions.
----------------
jayfoad wrote:

@mbrkusanin can you address the TODO please?

https://github.com/llvm/llvm-project/pull/75488


More information about the llvm-commits mailing list