[PATCH] D127143: [AMDGPU] gfx11 EXECZ and VCCZ are no longer allowed to be used as

[Jay Foad via Phabricator via llvm-commits]

foad accepted this revision.
foad added a comment.

LGTM modulo nits.



================
Comment at: llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp:4502
+    return true;
+  for (auto& Operand: Operands) {
+    if (!Operand->isReg())
----------------
Nit: `&` goes after the space. Doesn't clang-format fix this?


================
Comment at: llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp:5619-5620
     return isGFX9Plus();
+  case AMDGPU::SRC_POPS_EXITING_WAVE_ID:
+    return isGFX9Plus() && !isGFX11Plus();
   case AMDGPU::TBA:
----------------
I would do this as a separate commit, but consider it pre-approved.


================
Comment at: llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp:5643
     // No flat_scr on SI.
-    // On GFX10 flat scratch is not a valid register operand and can only be
+    // On GFX10Plus flat scratch is not a valid register operand and can only be
     // accessed with s_setreg/s_getreg.
----------------
I would do this plus the other comment tweak on line 5609 as a separate commit, no review required.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D127143/new/

https://reviews.llvm.org/D127143