Remove restriction on indvar phis, erase PHI if unused, fix mangled comment

Author: lukel97

llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp

@@ -120,18 +120,16 @@ bool RISCVCodeGenPrepare::visitAnd(BinaryOperator &BO) {
 // vectorize any scalar phis that feed into a fadd reduction:
 //
 // loop:
-// %phi = phi <float> [ ..., %entry ], [ %acc, %loop]
-// %acc = call float @llvm.vector.reduce.fadd.nxv4f32(float %phi, <vscale x 2 x
-// float> %vec)
+// %phi = phi <float> [ ..., %entry ], [ %acc, %loop ]
+// %acc = call float @llvm.vector.reduce.fadd.nxv4f32(float %phi, <vscale x 2 x float> %vec)
 //
 // ->
 //
 // loop:
-// %phi = phi <vscale x 2 x float> [ ..., %entry ], [ %acc.vec, %loop]
+// %phi = phi <vscale x 2 x float> [ ..., %entry ], [ %acc.vec, %loop ]
 // %phi.scalar = extractelement <vscale x 2 x float> %phi, i64 0
-// %acc = call float @llvm.vector.reduce.fadd.nxv4f32(float %x, <vscale x 2 x
-// float> %vec) %acc.vec = insertelement <vscale x 2 x float> poison, float
-// %acc.next, i64 0
+// %acc = call float @llvm.vector.reduce.fadd.nxv4f32(float %x, <vscale x 2 x float> %vec)
+// %acc.vec = insertelement <vscale x 2 x float> poison, float %acc.next, i64 0
 //
 // Which eliminates the scalar -> vector -> scalar crossing during instruction
 // selection.
@@ -140,7 +138,7 @@ bool RISCVCodeGenPrepare::visitIntrinsicInst(IntrinsicInst &I) {
     return false;
 
   auto *PHI = dyn_cast<PHINode>(I.getOperand(0));
-  if (!PHI || !llvm::is_contained(PHI->incoming_values(), &I))
+  if (!PHI)
     return false;
 
   Type *VecTy = I.getOperand(1)->getType();
@@ -157,6 +155,9 @@ bool RISCVCodeGenPrepare::visitIntrinsicInst(IntrinsicInst &I) {
   Builder.SetInsertPoint(&I);
   I.setOperand(0, Builder.CreateExtractElement(VecPHI, (uint64_t)0));
 
+  if (PHI->hasNUses(0))
+    PHI->eraseFromParent();
+
   return true;
 }
 

llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare.ll

@@ -26,11 +26,10 @@ define float @reduce_fadd(ptr nocapture noundef readonly %f, i32 noundef signext
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP5:%.*]] = phi <vscale x 4 x float> [ insertelement (<vscale x 4 x float> poison, float 0.000000e+00, i64 0), [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, ptr [[F]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <vscale x 4 x float> [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP8]] = tail call float @llvm.vector.reduce.fadd.nxv4f32(float [[TMP7]], <vscale x 4 x float> [[WIDE_LOAD]])
+; CHECK-NEXT:    [[TMP8:%.*]] = tail call float @llvm.vector.reduce.fadd.nxv4f32(float [[TMP7]], <vscale x 4 x float> [[WIDE_LOAD]])
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    [[TMP10]] = insertelement <vscale x 4 x float> poison, float [[TMP8]], i64 0