[RISCV] Add vcpop.m/vfirst.m to RISCVMaskedPseudosTable

We seem to forget these two instructions.

Reviewers: preames, frasercrmck, lukel97, topperc

Reviewed By: lukel97

Pull Request: #115162

Author: wangpc-pp

llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp

@@ -3708,6 +3708,15 @@ static bool isImplicitDef(SDValue V) {
   return V.getMachineOpcode() == TargetOpcode::IMPLICIT_DEF;
 }
 
+static bool hasGPROut(unsigned Opc) {
+  switch (RISCV::getRVVMCOpcode(Opc)) {
+  case RISCV::VCPOP_M:
+  case RISCV::VFIRST_M:
+    return true;
+  }
+  return false;
+}
+
 // Optimize masked RVV pseudo instructions with a known all-ones mask to their
 // corresponding "unmasked" pseudo versions. The mask we're interested in will
 // take the form of a V0 physical register operand, with a glued
@@ -3737,8 +3746,9 @@ bool RISCVDAGToDAGISel::doPeepholeMaskedRVV(MachineSDNode *N) {
 #endif
 
   SmallVector<SDValue, 8> Ops;
-  // Skip the passthru operand at index 0 if !UseTUPseudo.
-  for (unsigned I = !UseTUPseudo, E = N->getNumOperands(); I != E; I++) {
+  // Skip the passthru operand at index 0 if !UseTUPseudo and no GPR out.
+  bool ShouldSkip = !UseTUPseudo && !hasGPROut(Opc);
+  for (unsigned I = ShouldSkip, E = N->getNumOperands(); I != E; I++) {
     // Skip the mask, and the Glue.
     SDValue Op = N->getOperand(I);
     if (I == MaskOpIdx || Op.getValueType() == MVT::Glue)

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

@@ -1983,6 +1983,7 @@ multiclass VPseudoVPOP_M {
       def "_M_" # mti.BX : VPseudoUnaryNoMaskGPROut,
           SchedBinary<"WriteVMPopV", "ReadVMPopV", "ReadVMPopV", mx>;
       def "_M_" # mti.BX # "_MASK" : VPseudoUnaryMaskGPROut,
+          RISCVMaskedPseudo<MaskIdx=1>,
           SchedBinary<"WriteVMPopV", "ReadVMPopV", "ReadVMPopV", mx>;
     }
   }
@@ -1995,6 +1996,7 @@ multiclass VPseudoV1ST_M {
       def "_M_" #mti.BX : VPseudoUnaryNoMaskGPROut,
           SchedBinary<"WriteVMFFSV", "ReadVMFFSV", "ReadVMFFSV", mx>;
       def "_M_" # mti.BX # "_MASK" : VPseudoUnaryMaskGPROut,
+          RISCVMaskedPseudo<MaskIdx=1>,
           SchedBinary<"WriteVMFFSV", "ReadVMFFSV", "ReadVMFFSV", mx>;
     }
   }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll

@@ -1797,11 +1797,8 @@ define float @vreduce_fminimum_v7f32(ptr %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 7, e32, m2, ta, ma
 ; CHECK-NEXT:    vle32.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetivli zero, 7, e32, m2, ta, ma
 ; CHECK-NEXT:    vmfne.vv v10, v8, v8
-; CHECK-NEXT:    vcpop.m a0, v10, v0.t
+; CHECK-NEXT:    vcpop.m a0, v10
 ; CHECK-NEXT:    beqz a0, .LBB111_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    lui a0, 523264
@@ -2558,11 +2555,8 @@ define float @vreduce_fmaximum_v7f32(ptr %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 7, e32, m2, ta, ma
 ; CHECK-NEXT:    vle32.v v8, (a0)
-; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT:    vmset.m v0
-; CHECK-NEXT:    vsetivli zero, 7, e32, m2, ta, ma
 ; CHECK-NEXT:    vmfne.vv v10, v8, v8
-; CHECK-NEXT:    vcpop.m a0, v10, v0.t
+; CHECK-NEXT:    vcpop.m a0, v10
 ; CHECK-NEXT:    beqz a0, .LBB139_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    lui a0, 523264