[llvm] AMDGPU: update GFX11 wmma hazards (PR #76143)

[Piotr Sobczak via llvm-commits]

================
@@ -1728,25 +1728,6 @@ bool GCNHazardRecognizer::fixWMMAHazards(MachineInstr *MI) {
       return true;
     }
 
-    // Src2 of the current wmma instruction overlaps with the dest of the
-    // previous wmma.
-    const MachineOperand *Src2 =
-        TII->getNamedOperand(*MI, AMDGPU::OpName::src2);
-    const Register CurSrc2Reg = Src2->isReg() ? Src2->getReg() : Register();
-
-    if (CurSrc2Reg != AMDGPU::NoRegister &&
-        TRI->regsOverlap(PrevDstReg, CurSrc2Reg)) {
-
-      const MachineOperand *Src2Mods =
-          TII->getNamedOperand(*MI, AMDGPU::OpName::src2_modifiers);
-      const bool NoSrc2Mods =
-          (Src2Mods->getImm() & (SISrcMods::NEG | SISrcMods::NEG_HI)) == 0;
-      // Exception: there is no hazard if the wmma instructions are of the same
-      // type and there is no input modifier on src2 of the current instruction.
-      return !(NoSrc2Mods && (TII->pseudoToMCOpcode(I.getOpcode()) ==
-                              TII->pseudoToMCOpcode(MI->getOpcode())));
-    }
-
----------------
piotrAMD wrote:

That was coded according to the spec, but the behavior/spec have recently been clarified: inserting V_NOP in these cases won't help correctness and performance at all.

https://github.com/llvm/llvm-project/pull/76143