[llvm] [AMDGPU][MC] Restrict op_sel in VOP3P dot instructions (PR #100485)

Jun Wang via llvm-commits llvm-commits at lists.llvm.org
Fri Nov 8 15:17:33 PST 2024


================
@@ -4588,28 +4588,40 @@ bool AMDGPUAsmParser::validateOpSel(const MCInst &Inst) {
 
   uint64_t TSFlags = MII.get(Opc).TSFlags;
 
-  if (isGFX940() && (TSFlags & SIInstrFlags::IsDOT)) {
-    int OpSelIdx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::op_sel);
-    if (OpSelIdx != -1) {
-      if (Inst.getOperand(OpSelIdx).getImm() != 0)
-        return false;
+  if (TSFlags & SIInstrFlags::IsDOT) {
+    // For all DOT instructions on GFX940, or VOP3P DOT instructions on all
+    // targets, i.e. v_dot2_*(except on pre-GFX940), v_dot4_* and v_dot8_*,
----------------
jwanggit86 wrote:

Ok, I'll look into this.

https://github.com/llvm/llvm-project/pull/100485


More information about the llvm-commits mailing list