[LV][EVL] Adrress the comments

rebase and update testcase

Author: LiqinWeng

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -1078,10 +1078,7 @@ void VPWidenSelectRecipe::execute(VPTransformState &State) {
 
 void VPWidenSelectEVLRecipe::execute(VPTransformState &State) {
   State.setDebugLocFrom(getDebugLoc());
-  assert(State.UF == 1 && "Expected only UF == 1 when vectorizing with "
-                          "explicit vector length.");
-
-  Value *EVLArg = State.get(getEVL(), 0, /*NeedsScalar=*/true);
+  Value *EVLArg = State.get(getEVL(), /*NeedsScalar=*/true);
   IRBuilderBase &BuilderIR = State.Builder;
   VectorBuilder Builder(BuilderIR);
   Builder.setEVL(EVLArg);
@@ -1090,11 +1087,10 @@ void VPWidenSelectEVLRecipe::execute(VPTransformState &State) {
   // We have to take the 'vectorized' value and pick the first lane.
   // Instcombine will make this a no-op.
   auto *InvarCond =
-      isInvariantCond() ? State.get(getCond(), VPIteration(0, 0)) : nullptr;
+      isInvariantCond() ? State.get(getCond(), VPLane(0)) : nullptr;
 
   Value *Cond = InvarCond ? InvarCond : State.get(getCond(), 0);
-  if (!isa<VectorType>(Cond->getType()))
-    Cond = BuilderIR.CreateVectorSplat(State.VF, Cond, "splat.cond");
+  assert(isa<VectorType>(Cond->getType()) && "CondType must be vector Type.");
 
   Value *Op0 = State.get(getOperand(1), 0);
   Value *Op1 = State.get(getOperand(2), 0);

llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll

@@ -5,83 +5,44 @@
 ; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
 ; RUN: -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-max=128 -disable-output < %s 2>&1 | FileCheck --check-prefix=IF-EVL %s
 
-; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize \
-; RUN: -force-tail-folding-style=none \
-; RUN: -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
-; RUN: -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-max=128 -disable-output < %s 2>&1 | FileCheck --check-prefix=NO-VP %s
-
 define void @vp_select(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
 ; IF-EVL: VPlan 'Final VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' {
-; IF-EVL-NEXT: Live-in vp<%0> = VF * UF
-; IF-EVL-NEXT: Live-in vp<%1> = vector-trip-count
+; IF-EVL-NEXT: Live-in vp<[[VFUF:%[0-9]+]]> = VF * UF
+; IF-EVL-NEXT: Live-in vp<[[VTC:%[0-9]+]]> = vector-trip-count
 ; IF-EVL-NEXT: Live-in ir<%N> = original trip-count
 
 ; IF-EVL: vector.ph:
 ; IF-EVL-NEXT: Successor(s): vector loop
 
 ; IF-EVL: <x1> vector loop: {
 ; IF-EVL-NEXT:   vector.body:
-; IF-EVL-NEXT:     EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%12>
-; IF-EVL-NEXT:     EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<%4> = phi ir<0>, vp<%11>
-; IF-EVL-NEXT:     EMIT vp<%5> = EXPLICIT-VECTOR-LENGTH vp<%4>, ir<%N>
-; IF-EVL-NEXT:     vp<%6> = SCALAR-STEPS vp<%4>, ir<1>
-; IF-EVL-NEXT:     CLONE ir<%arrayidx> = getelementptr inbounds ir<%b>, vp<%6>
-; IF-EVL-NEXT:     vp<%7> = vector-pointer ir<%arrayidx>
-; IF-EVL-NEXT:     WIDEN ir<%0> = vp.load vp<%7>, vp<%5>
-; IF-EVL-NEXT:     CLONE ir<%arrayidx3> = getelementptr inbounds ir<%c>, vp<%6>
-; IF-EVL-NEXT:     vp<%8> = vector-pointer ir<%arrayidx3>
-; IF-EVL-NEXT:     WIDEN ir<%1> = vp.load vp<%8>, vp<%5>
-; IF-EVL-NEXT:     WIDEN ir<%cmp4> = icmp sgt ir<%0>, ir<%1>
-; IF-EVL-NEXT:     WIDEN ir<%2> = vp.sub ir<0>, ir<%1>, vp<%5>
-; IF-EVL-NEXT:     WIDEN-SELECT ir<%cond.p> = vp.select ir<%cmp4>, ir<%1>, ir<%2>, vp<%5>
-; IF-EVL-NEXT:     WIDEN ir<%cond> = vp.add ir<%cond.p>, ir<%0>, vp<%5>
-; IF-EVL-NEXT:     CLONE ir<%arrayidx15> = getelementptr inbounds ir<%a>, vp<%6>
-; IF-EVL-NEXT:     vp<%9> = vector-pointer ir<%arrayidx15>
-; IF-EVL-NEXT:     WIDEN vp.store vp<%9>, ir<%cond>, vp<%5>
-; IF-EVL-NEXT:     SCALAR-CAST vp<%10> = zext vp<%5> to i64
-; IF-EVL-NEXT:     EMIT vp<%11> = add vp<%10>, vp<%4>
-; IF-EVL-NEXT:     EMIT vp<%12> = add vp<%3>, vp<%0>
-; IF-EVL-NEXT:     EMIT branch-on-count vp<%12>, vp<%1>
+; IF-EVL-NEXT:     EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION
+; IF-EVL-NEXT:     EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<[[EVL_PHI:%[0-9]+]]>  = phi ir<0>, vp<[[IV_NEX:%[0-9]+]]>
+; IF-EVL-NEXT:     EMIT vp<[[AVL:%.+]]> = sub ir<%N>, vp<[[EVL_PHI]]>
+; IF-EVL-NEXT:     EMIT vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]>
+; IF-EVL-NEXT:     vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>
+; IF-EVL-NEXT:     CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]>
+; IF-EVL-NEXT:     vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]>
+; IF-EVL-NEXT:     WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]>
+; IF-EVL-NEXT:     CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]>
+; IF-EVL-NEXT:     vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
+; IF-EVL-NEXT:     WIDEN ir<[[LD2:%.+]]> = vp.load vp<[[PTR2]]>, vp<[[EVL]]>
+; IF-EVL-NEXT:     WIDEN ir<[[CMP:%.+]]> = icmp sgt ir<[[LD1]]>, ir<[[LD2]]>
+; IF-EVL-NEXT:     WIDEN ir<[[SUB:%.+]]> = vp.sub ir<0>, ir<[[LD2]]>, vp<[[EVL]]>
+; IF-EVL-NEXT:     WIDEN-SELECT ir<[[SELECT:%.+]]> = vp.select ir<[[CMP]]>, ir<%1>, ir<%2>, vp<[[EVL]]>
+; IF-EVL-NEXT:     WIDEN ir<[[ADD:%.+]]> = vp.add ir<[[SELECT]]>, ir<[[LD1]]>, vp<[[EVL]]>
+; IF-EVL-NEXT:     CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
+; IF-EVL-NEXT:     vp<[[PTR3:%.+]]> = vector-pointer ir<[[GEP3]]>
+; IF-EVL-NEXT:     WIDEN vp.store vp<[[PTR3]]>, ir<[[ADD]]>, vp<[[EVL]]>
+; IF-EVL-NEXT:     SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
+; IF-EVL-NEXT:     EMIT vp<[[IV_NEX]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
+; IF-EVL-NEXT:     EMIT vp<[[IV_NEXT_EXIT:%[0-9]+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
+; IF-EVL-NEXT:     EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>,  vp<[[VTC]]>
 ; IF-EVL-NEXT:   No successors
 ; IF-EVL-NEXT: }
 
-; NO-VP: VPlan 'Final VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF>=1' {
-; NO-VP-NEXT: Live-in vp<%0> = VF * UF
-; NO-VP-NEXT: Live-in vp<%1> = vector-trip-count
-; NO-VP-NEXT: Live-in ir<%N> = original trip-count
-
-; NO-VP: vector.ph:
-; NO-VP-NEXT: Successor(s): vector loop
-
-; NO-VP: <x1> vector loop: {
-; NO-VP-NEXT:   vector.body:
-; NO-VP-NEXT:     EMIT vp<%2> = CANONICAL-INDUCTION ir<0>, vp<%7>
-; NO-VP-NEXT:     vp<%3> = SCALAR-STEPS vp<%2>, ir<1>
-; NO-VP-NEXT:     CLONE ir<%arrayidx> = getelementptr inbounds ir<%b>, vp<%3>
-; NO-VP-NEXT:     vp<%4> = vector-pointer ir<%arrayidx>
-; NO-VP-NEXT:     WIDEN ir<%0> = load vp<%4>
-; NO-VP-NEXT:     CLONE ir<%arrayidx3> = getelementptr inbounds ir<%c>, vp<%3>
-; NO-VP-NEXT:     vp<%5> = vector-pointer ir<%arrayidx3>
-; NO-VP-NEXT:     WIDEN ir<%1> = load vp<%5>
-; NO-VP-NEXT:     WIDEN ir<%cmp4> = icmp sgt ir<%0>, ir<%1>
-; NO-VP-NEXT:     WIDEN ir<%2> = sub ir<0>, ir<%1>
-; NO-VP-NEXT:     WIDEN-SELECT ir<%cond.p> = select ir<%cmp4>, ir<%1>, ir<%2>
-; NO-VP-NEXT:     WIDEN ir<%cond> = add ir<%cond.p>, ir<%0>
-; NO-VP-NEXT:     CLONE ir<%arrayidx15> = getelementptr inbounds ir<%a>, vp<%3>
-; NO-VP-NEXT:     vp<%6> = vector-pointer ir<%arrayidx15>
-; NO-VP-NEXT:     WIDEN store vp<%6>, ir<%cond>
-; NO-VP-NEXT:     EMIT vp<%7> = add nuw vp<%2>, vp<%0>
-; NO-VP-NEXT:     EMIT branch-on-count vp<%7>, vp<%1>
-; NO-VP-NEXT:   No successors
-; NO-VP-NEXT: }
-
-
 entry:
-  %cmp30 = icmp sgt i64 %N, 0
-  br i1 %cmp30, label %for.body, label %for.cond.cleanup
-
-for.cond.cleanup:
-  ret void
+  br label %for.body
 
 for.body:
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
@@ -97,5 +58,8 @@ for.body:
   store i32 %cond, ptr %arrayidx15, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond.not = icmp eq i64 %indvars.iv.next, %N
-  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+  br i1 %exitcond.not, label %exit, label %for.body
+
+exit:
+  ret void
 }