[llvm-branch-commits] [llvm] [AMDGPU][GlobalISel] Add COPY_SCC_VCC combine for VCC-SGPR-VGPR pattern (PR #179352)

[Petar Avramovic via llvm-branch-commits]

================
@@ -18541,6 +18541,11 @@ void SITargetLowering::computeKnownBitsForTargetInstr(
   case AMDGPU::G_AMDGPU_BUFFER_LOAD_USHORT:
     Known.Zero.setHighBits(16);
     break;
+  case AMDGPU::G_AMDGPU_COPY_SCC_VCC:
+    // G_AMDGPU_COPY_SCC_VCC converts a uniform boolean in VCC to SGPR s32,
+    // producing exactly 0 or 1.
+    Known.Zero.setHighBits(Known.getBitWidth() - 1);
+    break;
----------------
petar-avramovic wrote:

Nice, can you open another PR and merge it first, then get back to this one

https://github.com/llvm/llvm-project/pull/179352