[𝘀𝗽𝗿] changes introduced through rebase

Created using spr 1.3.6-beta.1

[skip ci]

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

@@ -1150,6 +1150,7 @@ class VPseudoUnaryNoMaskGPROut :
 class VPseudoUnaryMaskGPROut :
       Pseudo<(outs GPR:$rd),
              (ins VR:$rs1, VMaskOp:$vm, AVL:$vl, sew:$sew), []>,
+      RISCVMaskedPseudo<MaskIdx=1>,
       RISCVVPseudo {
   let mayLoad = 0;
   let mayStore = 0;

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -2527,7 +2527,7 @@ RISCVTTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
     Options.LoadSizes = {8, 4, 2, 1};
   else
     Options.LoadSizes = {4, 2, 1};
-  if (IsZeroCmp && ST->hasVInstructions()) {
+  if (IsZeroCmp && ST->hasVInstructions() && ST->enableUnalignedVectorMem()) {
     unsigned RealMinVLen = ST->getRealMinVLen();
     // Support Fractional LMULs if the lengths are larger than XLen.
     // TODO: Support non-power-of-2 types.

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