[llvm] e23ab73 - [VPlan] Don't convert widen recipes to VP intrinsics in EVL transform (#127180)
via llvm-commits
llvm-commits at lists.llvm.org
Sat Feb 22 03:38:14 PST 2025
Author: Luke Lau
Date: 2025-02-22T19:38:11+08:00
New Revision: e23ab73335c857d1a4c6e695cb25a5cffb1329c6
URL: https://github.com/llvm/llvm-project/commit/e23ab73335c857d1a4c6e695cb25a5cffb1329c6
DIFF: https://github.com/llvm/llvm-project/commit/e23ab73335c857d1a4c6e695cb25a5cffb1329c6.diff
LOG: [VPlan] Don't convert widen recipes to VP intrinsics in EVL transform (#127180)
This is a copy of #126177, since it was automatically and permanently
closed because I messed up the source branch on my remote
This patch proposes to avoid converting widening recipes to VP
intrinsics during the EVL transform.
IIUC we initially did this to avoid `vl` toggles on RISC-V. However we
now have the RISCVVLOptimizer pass which mostly makes this redundant.
Emitting regular IR instead of VP intrinsics allows more generic
optimisations, both in the middle end and DAGCombiner, and we generally
have better patterns in the RISC-V backend for non-VP nodes. Sticking to
regular IR instructions is likely a lot less work than reimplementing
all of these optimisations for VP intrinsics, and on SPEC CPU 2017 we get
noticeably better code generation.
Added:
llvm/test/CodeGen/RISCV/rvv/vl-opt-evl-tail-folding.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-div.ll
Modified:
llvm/lib/Transforms/Vectorize/VPlan.h
llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
llvm/lib/Transforms/Vectorize/VPlanPatternMatch.h
llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
llvm/lib/Transforms/Vectorize/VPlanValue.h
llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp
llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll
llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-call-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-intermediate-store.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-known-no-overflow.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction.ll
llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-cast-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll
llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll
llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
index 8089cfd1ce802..d86914f0fb026 100644
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -523,7 +523,6 @@ class VPSingleDefRecipe : public VPRecipeBase, public VPValue {
case VPRecipeBase::VPWidenGEPSC:
case VPRecipeBase::VPWidenIntrinsicSC:
case VPRecipeBase::VPWidenSC:
- case VPRecipeBase::VPWidenEVLSC:
case VPRecipeBase::VPWidenSelectSC:
case VPRecipeBase::VPBlendSC:
case VPRecipeBase::VPPredInstPHISC:
@@ -710,7 +709,6 @@ class VPRecipeWithIRFlags : public VPSingleDefRecipe {
static inline bool classof(const VPRecipeBase *R) {
return R->getVPDefID() == VPRecipeBase::VPInstructionSC ||
R->getVPDefID() == VPRecipeBase::VPWidenSC ||
- R->getVPDefID() == VPRecipeBase::VPWidenEVLSC ||
R->getVPDefID() == VPRecipeBase::VPWidenGEPSC ||
R->getVPDefID() == VPRecipeBase::VPWidenCastSC ||
R->getVPDefID() == VPRecipeBase::VPWidenIntrinsicSC ||
@@ -1113,8 +1111,7 @@ class VPWidenRecipe : public VPRecipeWithIRFlags {
}
static inline bool classof(const VPRecipeBase *R) {
- return R->getVPDefID() == VPRecipeBase::VPWidenSC ||
- R->getVPDefID() == VPRecipeBase::VPWidenEVLSC;
+ return R->getVPDefID() == VPRecipeBase::VPWidenSC;
}
static inline bool classof(const VPUser *U) {
@@ -1139,54 +1136,6 @@ class VPWidenRecipe : public VPRecipeWithIRFlags {
#endif
};
-/// A recipe for widening operations with vector-predication intrinsics with
-/// explicit vector length (EVL).
-class VPWidenEVLRecipe : public VPWidenRecipe {
- using VPRecipeWithIRFlags::transferFlags;
-
-public:
- template <typename IterT>
- VPWidenEVLRecipe(Instruction &I, iterator_range<IterT> Operands, VPValue &EVL)
- : VPWidenRecipe(VPDef::VPWidenEVLSC, I, Operands) {
- addOperand(&EVL);
- }
- VPWidenEVLRecipe(VPWidenRecipe &W, VPValue &EVL)
- : VPWidenEVLRecipe(*W.getUnderlyingInstr(), W.operands(), EVL) {
- transferFlags(W);
- }
-
- ~VPWidenEVLRecipe() override = default;
-
- VPWidenRecipe *clone() override final {
- llvm_unreachable("VPWidenEVLRecipe cannot be cloned");
- return nullptr;
- }
-
- VP_CLASSOF_IMPL(VPDef::VPWidenEVLSC);
-
- VPValue *getEVL() { return getOperand(getNumOperands() - 1); }
- const VPValue *getEVL() const { return getOperand(getNumOperands() - 1); }
-
- /// Produce a vp-intrinsic using the opcode and operands of the recipe,
- /// processing EVL elements.
- void execute(VPTransformState &State) override final;
-
- /// Returns true if the recipe only uses the first lane of operand \p Op.
- bool onlyFirstLaneUsed(const VPValue *Op) const override {
- assert(is_contained(operands(), Op) &&
- "Op must be an operand of the recipe");
- // EVL in that recipe is always the last operand, thus any use before means
- // the VPValue should be vectorized.
- return getEVL() == Op;
- }
-
-#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
- /// Print the recipe.
- void print(raw_ostream &O, const Twine &Indent,
- VPSlotTracker &SlotTracker) const override final;
-#endif
-};
-
/// VPWidenCastRecipe is a recipe to create vector cast instructions.
class VPWidenCastRecipe : public VPRecipeWithIRFlags {
/// Cast instruction opcode.
diff --git a/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp b/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
index bf61251fc9133..8e5b37a35dda7 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
@@ -251,9 +251,8 @@ Type *VPTypeAnalysis::inferScalarType(const VPValue *V) {
VPPartialReductionRecipe>([this](const VPRecipeBase *R) {
return inferScalarType(R->getOperand(0));
})
- .Case<VPBlendRecipe, VPInstruction, VPWidenRecipe, VPWidenEVLRecipe,
- VPReplicateRecipe, VPWidenCallRecipe, VPWidenMemoryRecipe,
- VPWidenSelectRecipe>(
+ .Case<VPBlendRecipe, VPInstruction, VPWidenRecipe, VPReplicateRecipe,
+ VPWidenCallRecipe, VPWidenMemoryRecipe, VPWidenSelectRecipe>(
[this](const auto *R) { return inferScalarTypeForRecipe(R); })
.Case<VPWidenIntrinsicRecipe>([](const VPWidenIntrinsicRecipe *R) {
return R->getResultType();
diff --git a/llvm/lib/Transforms/Vectorize/VPlanPatternMatch.h b/llvm/lib/Transforms/Vectorize/VPlanPatternMatch.h
index ebc82c01467cf..8c11d93734667 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanPatternMatch.h
+++ b/llvm/lib/Transforms/Vectorize/VPlanPatternMatch.h
@@ -155,14 +155,6 @@ struct Recipe_match {
if ((!matchRecipeAndOpcode<RecipeTys>(R) && ...))
return false;
- if (!(std::is_same_v<VPWidenEVLRecipe, RecipeTys> || ...) &&
- isa<VPWidenEVLRecipe>(R)) {
- // Don't match VPWidenEVLRecipe if it is not explicitly part of RecipeTys.
- // Otherwise we might match it unexpectedly when trying to match
- // VPWidenRecipe, of which VPWidenEVLRecipe is a subclass of.
- return false;
- }
-
assert(R->getNumOperands() == std::tuple_size<Ops_t>::value &&
"recipe with matched opcode the expected number of operands");
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index d57a6c481748c..8a928fa71fab8 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -86,7 +86,6 @@ bool VPRecipeBase::mayWriteToMemory() const {
case VPWidenLoadSC:
case VPWidenPHISC:
case VPWidenSC:
- case VPWidenEVLSC:
case VPWidenSelectSC: {
const Instruction *I =
dyn_cast_or_null<Instruction>(getVPSingleValue()->getUnderlyingValue());
@@ -132,7 +131,6 @@ bool VPRecipeBase::mayReadFromMemory() const {
case VPWidenIntOrFpInductionSC:
case VPWidenPHISC:
case VPWidenSC:
- case VPWidenEVLSC:
case VPWidenSelectSC: {
const Instruction *I =
dyn_cast_or_null<Instruction>(getVPSingleValue()->getUnderlyingValue());
@@ -173,7 +171,6 @@ bool VPRecipeBase::mayHaveSideEffects() const {
case VPWidenPHISC:
case VPWidenPointerInductionSC:
case VPWidenSC:
- case VPWidenEVLSC:
case VPWidenSelectSC: {
const Instruction *I =
dyn_cast_or_null<Instruction>(getVPSingleValue()->getUnderlyingValue());
@@ -1602,42 +1599,6 @@ InstructionCost VPWidenRecipe::computeCost(ElementCount VF,
}
}
-void VPWidenEVLRecipe::execute(VPTransformState &State) {
- unsigned Opcode = getOpcode();
- // TODO: Support other opcodes
- if (!Instruction::isBinaryOp(Opcode) && !Instruction::isUnaryOp(Opcode))
- llvm_unreachable("Unsupported opcode in VPWidenEVLRecipe::execute");
-
- State.setDebugLocFrom(getDebugLoc());
-
- assert(State.get(getOperand(0))->getType()->isVectorTy() &&
- "VPWidenEVLRecipe should not be used for scalars");
-
- VPValue *EVL = getEVL();
- Value *EVLArg = State.get(EVL, /*NeedsScalar=*/true);
- IRBuilderBase &BuilderIR = State.Builder;
- VectorBuilder Builder(BuilderIR);
- Value *Mask = BuilderIR.CreateVectorSplat(State.VF, BuilderIR.getTrue());
-
- SmallVector<Value *, 4> Ops;
- for (unsigned I = 0, E = getNumOperands() - 1; I < E; ++I) {
- VPValue *VPOp = getOperand(I);
- Ops.push_back(State.get(VPOp));
- }
-
- Builder.setMask(Mask).setEVL(EVLArg);
- Value *VPInst =
- Builder.createVectorInstruction(Opcode, Ops[0]->getType(), Ops, "vp.op");
- // Currently vp-intrinsics only accept FMF flags.
- // TODO: Enable other flags when support is added.
- if (isa<FPMathOperator>(VPInst))
- setFlags(cast<Instruction>(VPInst));
-
- State.set(this, VPInst);
- State.addMetadata(VPInst,
- dyn_cast_or_null<Instruction>(getUnderlyingValue()));
-}
-
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
void VPWidenRecipe::print(raw_ostream &O, const Twine &Indent,
VPSlotTracker &SlotTracker) const {
@@ -1647,15 +1608,6 @@ void VPWidenRecipe::print(raw_ostream &O, const Twine &Indent,
printFlags(O);
printOperands(O, SlotTracker);
}
-
-void VPWidenEVLRecipe::print(raw_ostream &O, const Twine &Indent,
- VPSlotTracker &SlotTracker) const {
- O << Indent << "WIDEN ";
- printAsOperand(O, SlotTracker);
- O << " = vp." << Instruction::getOpcodeName(getOpcode());
- printFlags(O);
- printOperands(O, SlotTracker);
-}
#endif
void VPWidenCastRecipe::execute(VPTransformState &State) {
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 6c917e4eef655..ce81b2e147df8 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1662,40 +1662,10 @@ static VPRecipeBase *createEVLRecipe(VPValue *HeaderMask,
VPValue *NewMask = GetNewMask(S->getMask());
return new VPWidenStoreEVLRecipe(*S, EVL, NewMask);
})
- .Case<VPWidenRecipe>([&](VPWidenRecipe *W) -> VPRecipeBase * {
- unsigned Opcode = W->getOpcode();
- if (!Instruction::isBinaryOp(Opcode) && !Instruction::isUnaryOp(Opcode))
- return nullptr;
- return new VPWidenEVLRecipe(*W, EVL);
- })
.Case<VPReductionRecipe>([&](VPReductionRecipe *Red) {
VPValue *NewMask = GetNewMask(Red->getCondOp());
return new VPReductionEVLRecipe(*Red, EVL, NewMask);
})
- .Case<VPWidenIntrinsicRecipe, VPWidenCastRecipe>(
- [&](auto *CR) -> VPRecipeBase * {
- Intrinsic::ID VPID;
- if (auto *CallR = dyn_cast<VPWidenIntrinsicRecipe>(CR)) {
- VPID =
- VPIntrinsic::getForIntrinsic(CallR->getVectorIntrinsicID());
- } else {
- auto *CastR = cast<VPWidenCastRecipe>(CR);
- VPID = VPIntrinsic::getForOpcode(CastR->getOpcode());
- }
-
- // Not all intrinsics have a corresponding VP intrinsic.
- if (VPID == Intrinsic::not_intrinsic)
- return nullptr;
- assert(VPIntrinsic::getMaskParamPos(VPID) &&
- VPIntrinsic::getVectorLengthParamPos(VPID) &&
- "Expected VP intrinsic to have mask and EVL");
-
- SmallVector<VPValue *> Ops(CR->operands());
- Ops.push_back(&AllOneMask);
- Ops.push_back(&EVL);
- return new VPWidenIntrinsicRecipe(
- VPID, Ops, TypeInfo.inferScalarType(CR), CR->getDebugLoc());
- })
.Case<VPWidenSelectRecipe>([&](VPWidenSelectRecipe *Sel) {
SmallVector<VPValue *> Ops(Sel->operands());
Ops.push_back(&EVL);
diff --git a/llvm/lib/Transforms/Vectorize/VPlanValue.h b/llvm/lib/Transforms/Vectorize/VPlanValue.h
index aabc4ab571e7a..a058b2a121d59 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanValue.h
+++ b/llvm/lib/Transforms/Vectorize/VPlanValue.h
@@ -351,7 +351,6 @@ class VPDef {
VPWidenStoreEVLSC,
VPWidenStoreSC,
VPWidenSC,
- VPWidenEVLSC,
VPWidenSelectSC,
VPBlendSC,
VPHistogramSC,
diff --git a/llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp b/llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp
index 96156de444f88..a4b309d6dcd9f 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp
@@ -145,10 +145,6 @@ bool VPlanVerifier::verifyEVLRecipe(const VPInstruction &EVL) const {
[&](const VPRecipeBase *S) { return VerifyEVLUse(*S, 2); })
.Case<VPWidenLoadEVLRecipe, VPReverseVectorPointerRecipe>(
[&](const VPRecipeBase *R) { return VerifyEVLUse(*R, 1); })
- .Case<VPWidenEVLRecipe>([&](const VPWidenEVLRecipe *W) {
- return VerifyEVLUse(*W,
- Instruction::isUnaryOp(W->getOpcode()) ? 1 : 2);
- })
.Case<VPScalarCastRecipe>(
[&](const VPScalarCastRecipe *S) { return VerifyEVLUse(*S, 0); })
.Case<VPInstruction>([&](const VPInstruction *I) {
diff --git a/llvm/test/CodeGen/RISCV/rvv/vl-opt-evl-tail-folding.ll b/llvm/test/CodeGen/RISCV/rvv/vl-opt-evl-tail-folding.ll
new file mode 100644
index 0000000000000..48f93c8323cfd
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vl-opt-evl-tail-folding.ll
@@ -0,0 +1,59 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=riscv64 -mattr=+v -verify-machineinstrs | FileCheck %s
+
+; Check that EVL tail folded loops from the loop vectorizer are able to have the
+; vl of non-VP instructions reduced.
+define void @evl_tail_folded(ptr %p, ptr %q) {
+; CHECK-LABEL: evl_tail_folded:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a2, 0
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: srli a3, a3, 2
+; CHECK-NEXT: addi a4, a3, 1023
+; CHECK-NEXT: neg a5, a3
+; CHECK-NEXT: and a4, a4, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: .LBB0_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: sub a6, a5, a2
+; CHECK-NEXT: slli a7, a2, 3
+; CHECK-NEXT: vsetvli a6, a6, e64, m2, ta, ma
+; CHECK-NEXT: add t0, a0, a7
+; CHECK-NEXT: vle64.v v8, (t0)
+; CHECK-NEXT: sub a4, a4, a3
+; CHECK-NEXT: add a7, a1, a7
+; CHECK-NEXT: vadd.vi v8, v8, 1
+; CHECK-NEXT: vse64.v v8, (a7)
+; CHECK-NEXT: add a2, a2, a6
+; CHECK-NEXT: bnez a4, .LBB0_1
+; CHECK-NEXT: # %bb.2: # %exit
+; CHECK-NEXT: ret
+entry:
+ %0 = tail call i64 @llvm.vscale.i64()
+ %1 = shl i64 %0, 1
+ %n.rnd.up = add i64 %1, 1023
+ %n.mod.vf = urem i64 %n.rnd.up, %1
+ %n.vec = sub i64 %n.rnd.up, %n.mod.vf
+ %2 = tail call i64 @llvm.vscale.i64()
+ %3 = shl i64 %2, 1
+ br label %vector.body
+
+vector.body:
+ %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+ %evl.based.iv = phi i64 [ 0, %entry ], [ %index.evl.next, %vector.body ]
+ %avl = sub i64 1024, %evl.based.iv
+ %4 = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %avl, i32 2, i1 true)
+ %5 = getelementptr i64, ptr %p, i64 %evl.based.iv
+ %vp.op.load = tail call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr %5, <vscale x 2 x i1> splat (i1 true), i32 %4)
+ %6 = add <vscale x 2 x i64> %vp.op.load, splat (i64 1)
+ %7 = getelementptr i64, ptr %q, i64 %evl.based.iv
+ tail call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> %6, ptr %7, <vscale x 2 x i1> splat (i1 true), i32 %4)
+ %8 = zext i32 %4 to i64
+ %index.evl.next = add i64 %evl.based.iv, %8
+ %index.next = add i64 %index, %3
+ %9 = icmp eq i64 %index.next, %n.vec
+ br i1 %9, label %exit, label %vector.body
+
+exit:
+ ret void
+}
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll
index 14818199072c2..b96a44a546a14 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll
@@ -143,8 +143,8 @@ define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
; IF-EVL-OUTLOOP-NEXT: [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP6]]
; IF-EVL-OUTLOOP-NEXT: [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[TMP7]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i16> @llvm.vp.load.nxv4i16.p0(ptr align 2 [[TMP8]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
-; IF-EVL-OUTLOOP-NEXT: [[TMP9:%.*]] = call <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i16(<vscale x 4 x i16> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
-; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i32> [[TMP9]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-OUTLOOP-NEXT: [[TMP9:%.*]] = sext <vscale x 4 x i16> [[VP_OP_LOAD]] to <vscale x 4 x i32>
+; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[VEC_PHI]], [[TMP9]]
; IF-EVL-OUTLOOP-NEXT: [[TMP10]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP4]]
@@ -200,7 +200,7 @@ define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
; IF-EVL-INLOOP-NEXT: [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP7]]
; IF-EVL-INLOOP-NEXT: [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[TMP8]], i32 0
; IF-EVL-INLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0(ptr align 2 [[TMP9]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-INLOOP-NEXT: [[TMP14:%.*]] = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i16(<vscale x 8 x i16> [[VP_OP_LOAD]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-INLOOP-NEXT: [[TMP14:%.*]] = sext <vscale x 8 x i16> [[VP_OP_LOAD]] to <vscale x 8 x i32>
; IF-EVL-INLOOP-NEXT: [[TMP10:%.*]] = call i32 @llvm.vp.reduce.add.nxv8i32(i32 0, <vscale x 8 x i32> [[TMP14]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT: [[TMP11]] = add i32 [[TMP10]], [[VEC_PHI]]
; IF-EVL-INLOOP-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP6]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
index 68b36f23de4b0..ba7158eb02d90 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
@@ -27,10 +27,10 @@ define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr %src) {
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i8, ptr [[TMP5]], i32 0
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 1 x i8> @llvm.vp.load.nxv1i8.p0(ptr align 1 [[TMP6]], <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 1 x i16> @llvm.vp.zext.nxv1i16.nxv1i8(<vscale x 1 x i8> [[VP_OP_LOAD]], <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 1 x i16> @llvm.vp.mul.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> [[TMP7]], <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT: [[VP_OP1:%.*]] = call <vscale x 1 x i16> @llvm.vp.lshr.nxv1i16(<vscale x 1 x i16> [[VP_OP]], <vscale x 1 x i16> trunc (<vscale x 1 x i32> splat (i32 1) to <vscale x 1 x i16>), <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT: [[TMP8:%.*]] = call <vscale x 1 x i8> @llvm.vp.trunc.nxv1i8.nxv1i16(<vscale x 1 x i16> [[VP_OP1]], <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
+; CHECK-NEXT: [[TMP7:%.*]] = zext <vscale x 1 x i8> [[VP_OP_LOAD]] to <vscale x 1 x i16>
+; CHECK-NEXT: [[TMP12:%.*]] = mul <vscale x 1 x i16> zeroinitializer, [[TMP7]]
+; CHECK-NEXT: [[VP_OP1:%.*]] = lshr <vscale x 1 x i16> [[TMP12]], trunc (<vscale x 1 x i32> splat (i32 1) to <vscale x 1 x i16>)
+; CHECK-NEXT: [[TMP8:%.*]] = trunc <vscale x 1 x i16> [[VP_OP1]] to <vscale x 1 x i8>
; CHECK-NEXT: call void @llvm.vp.scatter.nxv1i8.nxv1p0(<vscale x 1 x i8> [[TMP8]], <vscale x 1 x ptr> align 1 zeroinitializer, <vscale x 1 x i1> splat (i1 true), i32 [[TMP3]])
; CHECK-NEXT: [[TMP9:%.*]] = zext i32 [[TMP3]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP9]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll b/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
index 7de51bc3a8a68..c95414db18bef 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
@@ -44,15 +44,15 @@ define void @type_info_cache_clobber(ptr %dstv, ptr %src, i64 %wide.trip.count)
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i8, ptr [[TMP13]], i32 0
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr align 1 [[TMP14]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META0:![0-9]+]]
-; CHECK-NEXT: [[TMP15:%.*]] = call <vscale x 8 x i32> @llvm.vp.zext.nxv8i32.nxv8i8(<vscale x 8 x i8> [[VP_OP_LOAD]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 8 x i32> @llvm.vp.mul.nxv8i32(<vscale x 8 x i32> [[TMP15]], <vscale x 8 x i32> zeroinitializer, <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
-; CHECK-NEXT: [[VP_OP2:%.*]] = call <vscale x 8 x i32> @llvm.vp.ashr.nxv8i32(<vscale x 8 x i32> [[TMP15]], <vscale x 8 x i32> zeroinitializer, <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
-; CHECK-NEXT: [[VP_OP3:%.*]] = call <vscale x 8 x i32> @llvm.vp.or.nxv8i32(<vscale x 8 x i32> [[VP_OP2]], <vscale x 8 x i32> zeroinitializer, <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
+; CHECK-NEXT: [[TMP15:%.*]] = zext <vscale x 8 x i8> [[VP_OP_LOAD]] to <vscale x 8 x i32>
+; CHECK-NEXT: [[VP_OP:%.*]] = mul <vscale x 8 x i32> [[TMP15]], zeroinitializer
+; CHECK-NEXT: [[TMP23:%.*]] = ashr <vscale x 8 x i32> [[TMP15]], zeroinitializer
+; CHECK-NEXT: [[VP_OP3:%.*]] = or <vscale x 8 x i32> [[TMP23]], zeroinitializer
; CHECK-NEXT: [[TMP16:%.*]] = icmp ult <vscale x 8 x i32> [[TMP15]], zeroinitializer
; CHECK-NEXT: [[TMP17:%.*]] = call <vscale x 8 x i32> @llvm.vp.select.nxv8i32(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i32> [[VP_OP3]], <vscale x 8 x i32> zeroinitializer, i32 [[TMP11]])
-; CHECK-NEXT: [[TMP18:%.*]] = call <vscale x 8 x i8> @llvm.vp.trunc.nxv8i8.nxv8i32(<vscale x 8 x i32> [[TMP17]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
-; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> [[TMP18]], <vscale x 8 x ptr> align 1 [[BROADCAST_SPLAT]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
-; CHECK-NEXT: [[TMP19:%.*]] = call <vscale x 8 x i16> @llvm.vp.trunc.nxv8i16.nxv8i32(<vscale x 8 x i32> [[VP_OP]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
+; CHECK-NEXT: [[TMP24:%.*]] = trunc <vscale x 8 x i32> [[TMP17]] to <vscale x 8 x i8>
+; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> [[TMP24]], <vscale x 8 x ptr> align 1 [[BROADCAST_SPLAT]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
+; CHECK-NEXT: [[TMP19:%.*]] = trunc <vscale x 8 x i32> [[VP_OP]] to <vscale x 8 x i16>
; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> [[TMP19]], <vscale x 8 x ptr> align 2 zeroinitializer, <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
; CHECK-NEXT: [[TMP20:%.*]] = zext i32 [[TMP11]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP20]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll
index 13286a3394126..e7181f7f30c77 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll
@@ -42,7 +42,7 @@ define void @test_and(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.and.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = and <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -136,7 +136,7 @@ define void @test_or(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.or.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = or <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -230,7 +230,7 @@ define void @test_xor(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.xor.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = xor <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -324,7 +324,7 @@ define void @test_shl(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.shl.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = shl <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -418,7 +418,7 @@ define void @test_lshr(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.lshr.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = lshr <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -512,7 +512,7 @@ define void @test_ashr(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.ashr.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = ashr <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -606,7 +606,7 @@ define void @test_add(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = add <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -700,7 +700,7 @@ define void @test_sub(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.sub.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 1), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = sub <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -794,7 +794,7 @@ define void @test_mul(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.mul.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 3), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = mul <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 3)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -888,7 +888,7 @@ define void @test_sdiv(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.sdiv.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 3), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = sdiv <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 3)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -982,7 +982,7 @@ define void @test_udiv(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.udiv.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 3), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = udiv <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 3)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -1076,7 +1076,7 @@ define void @test_srem(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.srem.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 3), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = srem <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 3)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -1170,7 +1170,7 @@ define void @test_urem(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP14]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 16 x i8> @llvm.vp.urem.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i8> splat (i8 3), <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = urem <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 3)
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[B]], i64 [[TMP12]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i8, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[VP_OP]], ptr align 1 [[TMP17]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP11]])
@@ -1267,7 +1267,7 @@ define void @test_fadd(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> splat (float 3.000000e+00), <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fadd fast <vscale x 4 x float> [[VP_OP_LOAD]], splat (float 3.000000e+00)
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[VP_OP]], ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
@@ -1362,7 +1362,7 @@ define void @test_fsub(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fsub.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> splat (float 3.000000e+00), <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fsub fast <vscale x 4 x float> [[VP_OP_LOAD]], splat (float 3.000000e+00)
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[VP_OP]], ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
@@ -1457,7 +1457,7 @@ define void @test_fmul(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fmul.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> splat (float 3.000000e+00), <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fmul fast <vscale x 4 x float> [[VP_OP_LOAD]], splat (float 3.000000e+00)
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[VP_OP]], ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
@@ -1552,7 +1552,7 @@ define void @test_fdiv(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> splat (float 3.000000e+00), <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fdiv fast <vscale x 4 x float> [[VP_OP_LOAD]], splat (float 3.000000e+00)
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[VP_OP]], ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
@@ -1700,7 +1700,7 @@ define void @test_fneg(ptr nocapture %a, ptr nocapture readonly %b) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fneg.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fneg fast <vscale x 4 x float> [[VP_OP_LOAD]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[VP_OP]], ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-call-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-call-intrinsics.ll
index 28ba5efb53c2a..f19e581d1c028 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-call-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-call-intrinsics.ll
@@ -55,7 +55,7 @@ define void @vp_smax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD5:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP29]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -63,7 +63,7 @@ define void @vp_smax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP18]], [[EVL_BASED_IV]]
; IF-EVL-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP8]]
; IF-EVL-NEXT: [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; IF-EVL-NEXT: br i1 [[TMP19]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]]
+; IF-EVL-NEXT: br i1 [[TMP19]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL: [[MIDDLE_BLOCK]]:
; IF-EVL-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; IF-EVL: [[SCALAR_PH]]:
@@ -80,7 +80,7 @@ define void @vp_smax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: store i32 [[DOT]], ptr [[GEP11]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -170,7 +170,7 @@ define void @vp_smin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD5:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP29]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -195,7 +195,7 @@ define void @vp_smin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: store i32 [[DOT]], ptr [[GEP11]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -285,7 +285,7 @@ define void @vp_umax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD5:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP29]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -310,7 +310,7 @@ define void @vp_umax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: store i32 [[DOT]], ptr [[GEP11]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -400,7 +400,7 @@ define void @vp_umin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD5:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP29:%.*]] = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD5]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP29]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -425,7 +425,7 @@ define void @vp_umin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: store i32 [[DOT]], ptr [[GEP11]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -507,7 +507,7 @@ define void @vp_ctlz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP24:%.*]] = call <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true, <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP24:%.*]] = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true)
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP24]], ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -530,7 +530,7 @@ define void @vp_ctlz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: store i32 [[TMP19]], ptr [[GEP3]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -607,7 +607,7 @@ define void @vp_cttz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP14]]
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[TMP15]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP16]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP13]])
-; IF-EVL-NEXT: [[TMP17:%.*]] = call <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true, <vscale x 4 x i1> splat (i1 true), i32 [[TMP13]])
+; IF-EVL-NEXT: [[TMP17:%.*]] = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true)
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP14]]
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[TMP18]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP17]], ptr align 4 [[TMP19]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP13]])
@@ -630,7 +630,7 @@ define void @vp_cttz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: store i32 [[TMP23]], ptr [[GEP3]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP13:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -708,9 +708,9 @@ define void @vp_lrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, ptr [[TMP11]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP13:%.*]] = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP14:%.*]] = call <vscale x 4 x i64> @llvm.vp.lrint.nxv4i64.nxv4f64(<vscale x 4 x double> [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP15:%.*]] = call <vscale x 4 x i32> @llvm.vp.trunc.nxv4i32.nxv4i64(<vscale x 4 x i64> [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP27:%.*]] = fpext <vscale x 4 x float> [[VP_OP_LOAD]] to <vscale x 4 x double>
+; IF-EVL-NEXT: [[TMP28:%.*]] = call <vscale x 4 x i64> @llvm.lrint.nxv4i64.nxv4f64(<vscale x 4 x double> [[TMP27]])
+; IF-EVL-NEXT: [[TMP15:%.*]] = trunc <vscale x 4 x i64> [[TMP28]] to <vscale x 4 x i32>
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP15]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -735,7 +735,7 @@ define void @vp_lrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: store i32 [[CONV3]], ptr [[GEP5]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP15:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -817,9 +817,9 @@ define void @vp_llrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, ptr [[TMP11]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP13:%.*]] = call <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP14:%.*]] = call <vscale x 4 x i64> @llvm.vp.llrint.nxv4i64.nxv4f64(<vscale x 4 x double> [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP15:%.*]] = call <vscale x 4 x i32> @llvm.vp.trunc.nxv4i32.nxv4i64(<vscale x 4 x i64> [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP27:%.*]] = fpext <vscale x 4 x float> [[VP_OP_LOAD]] to <vscale x 4 x double>
+; IF-EVL-NEXT: [[TMP28:%.*]] = call <vscale x 4 x i64> @llvm.llrint.nxv4i64.nxv4f64(<vscale x 4 x double> [[TMP27]])
+; IF-EVL-NEXT: [[TMP15:%.*]] = trunc <vscale x 4 x i64> [[TMP28]] to <vscale x 4 x i32>
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP15]], ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -844,7 +844,7 @@ define void @vp_llrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: store i32 [[CONV3]], ptr [[GEP5]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP17:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -926,7 +926,7 @@ define void @vp_abs(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
-; IF-EVL-NEXT: [[TMP24:%.*]] = call <vscale x 4 x i32> @llvm.vp.abs.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true, <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
+; IF-EVL-NEXT: [[TMP24:%.*]] = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], i1 true)
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP10]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP24]], ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
@@ -949,7 +949,7 @@ define void @vp_abs(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: store i32 [[COND]], ptr [[GEP9]], align 4
; IF-EVL-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
-; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]]
+; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP19:![0-9]+]]
; IF-EVL: [[EXIT]]:
; IF-EVL-NEXT: ret void
;
@@ -1054,3 +1054,25 @@ declare i32 @llvm.cttz.i32(i32, i1 immarg)
declare i64 @llvm.lrint.i64.f64(double)
declare i64 @llvm.llrint.i64.f64(double)
declare i32 @llvm.abs.i32(i32, i1 immarg)
+;.
+; IF-EVL: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; IF-EVL: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; IF-EVL: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; IF-EVL: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]]}
+; IF-EVL: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]]}
+; IF-EVL: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP7]] = distinct !{[[LOOP7]], [[META1]]}
+; IF-EVL: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP9]] = distinct !{[[LOOP9]], [[META1]]}
+; IF-EVL: [[LOOP10]] = distinct !{[[LOOP10]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP11]] = distinct !{[[LOOP11]], [[META1]]}
+; IF-EVL: [[LOOP12]] = distinct !{[[LOOP12]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP13]] = distinct !{[[LOOP13]], [[META1]]}
+; IF-EVL: [[LOOP14]] = distinct !{[[LOOP14]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP15]] = distinct !{[[LOOP15]], [[META1]]}
+; IF-EVL: [[LOOP16]] = distinct !{[[LOOP16]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP17]] = distinct !{[[LOOP17]], [[META1]]}
+; IF-EVL: [[LOOP18]] = distinct !{[[LOOP18]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP19]] = distinct !{[[LOOP19]], [[META1]]}
+;.
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
index 4557e95f1e1b6..7450c303c1045 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
@@ -47,7 +47,7 @@ define void @vp_sext(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i32> @llvm.vp.load.nxv2i32.p0(ptr align 4 [[TMP15]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META0:![0-9]+]]
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 2 x i64> @llvm.vp.sext.nxv2i64.nxv2i32(<vscale x 2 x i32> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = sext <vscale x 2 x i32> [[VP_OP_LOAD]] to <vscale x 2 x i64>
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i64, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP16]], ptr align 8 [[TMP18]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
@@ -147,7 +147,7 @@ define void @vp_zext(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i32> @llvm.vp.load.nxv2i32.p0(ptr align 4 [[TMP15]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META9:![0-9]+]]
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 2 x i64> @llvm.vp.zext.nxv2i64.nxv2i32(<vscale x 2 x i32> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = zext <vscale x 2 x i32> [[VP_OP_LOAD]] to <vscale x 2 x i64>
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i64, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP16]], ptr align 8 [[TMP18]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META12:![0-9]+]], !noalias [[META9]]
@@ -247,7 +247,7 @@ define void @vp_trunc(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i64, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP15]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META16:![0-9]+]]
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 2 x i32> @llvm.vp.trunc.nxv2i32.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = trunc <vscale x 2 x i64> [[VP_OP_LOAD]] to <vscale x 2 x i32>
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i32.p0(<vscale x 2 x i32> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META19:![0-9]+]], !noalias [[META16]]
@@ -347,7 +347,7 @@ define void @vp_fpext(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x float> @llvm.vp.load.nxv2f32.p0(ptr align 4 [[TMP15]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META23:![0-9]+]]
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 2 x double> @llvm.vp.fpext.nxv2f64.nxv2f32(<vscale x 2 x float> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = fpext <vscale x 2 x float> [[VP_OP_LOAD]] to <vscale x 2 x double>
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds double, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds double, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2f64.p0(<vscale x 2 x double> [[TMP16]], ptr align 8 [[TMP18]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META26:![0-9]+]], !noalias [[META23]]
@@ -447,7 +447,7 @@ define void @vp_fptrunc(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds double, ptr [[B]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds double, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x double> @llvm.vp.load.nxv2f64.p0(ptr align 8 [[TMP15]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META30:![0-9]+]]
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 2 x float> @llvm.vp.fptrunc.nxv2f32.nxv2f64(<vscale x 2 x double> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = fptrunc <vscale x 2 x double> [[VP_OP_LOAD]] to <vscale x 2 x float>
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2f32.p0(<vscale x 2 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META33:![0-9]+]], !noalias [[META30]]
@@ -547,7 +547,7 @@ define void @vp_sitofp(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
-; IF-EVL-NEXT: [[TMP18:%.*]] = call <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
+; IF-EVL-NEXT: [[TMP18:%.*]] = sitofp <vscale x 4 x i32> [[VP_OP_LOAD]] to <vscale x 4 x float>
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr inbounds float, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP18]], ptr align 4 [[TMP20]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
@@ -647,7 +647,7 @@ define void @vp_uitofp(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
-; IF-EVL-NEXT: [[TMP18:%.*]] = call <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
+; IF-EVL-NEXT: [[TMP18:%.*]] = uitofp <vscale x 4 x i32> [[VP_OP_LOAD]] to <vscale x 4 x float>
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr inbounds float, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP18]], ptr align 4 [[TMP20]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
@@ -747,7 +747,7 @@ define void @vp_fptosi(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
-; IF-EVL-NEXT: [[TMP18:%.*]] = call <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
+; IF-EVL-NEXT: [[TMP18:%.*]] = fptosi <vscale x 4 x float> [[VP_OP_LOAD]] to <vscale x 4 x i32>
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP18]], ptr align 4 [[TMP20]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
@@ -847,7 +847,7 @@ define void @vp_fptoui(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
-; IF-EVL-NEXT: [[TMP18:%.*]] = call <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
+; IF-EVL-NEXT: [[TMP18:%.*]] = fptoui <vscale x 4 x float> [[VP_OP_LOAD]] to <vscale x 4 x i32>
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr inbounds i32, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP18]], ptr align 4 [[TMP20]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP14]])
@@ -947,7 +947,7 @@ define void @vp_inttoptr(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i64, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP17]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP14]])
-; IF-EVL-NEXT: [[TMP18:%.*]] = call <vscale x 2 x ptr> @llvm.vp.inttoptr.nxv2p0.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP14]])
+; IF-EVL-NEXT: [[TMP18:%.*]] = inttoptr <vscale x 2 x i64> [[VP_OP_LOAD]] to <vscale x 2 x ptr>
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds ptr, ptr [[A]], i64 [[TMP15]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr inbounds ptr, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv2p0.p0(<vscale x 2 x ptr> [[TMP18]], ptr align 8 [[TMP20]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP14]])
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll
index 78059955b2da5..fefbdb473e2ab 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll
@@ -53,7 +53,7 @@ define i32 @cond_add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP18:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], splat (i32 3)
; IF-EVL-OUTLOOP-NEXT: [[TMP19:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP18]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer, i32 [[TMP11]])
-; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[TMP19]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[TMP19]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT: [[TMP20]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP22:%.*]] = zext i32 [[TMP11]] to i64
; IF-EVL-OUTLOOP-NEXT: [[INDEX_EVL_NEXT1]] = add i64 [[TMP22]], [[EVL_BASED_IV1]]
@@ -302,7 +302,7 @@ define i32 @cond_add_pred(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP18:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], splat (i32 3)
-; IF-EVL-OUTLOOP-NEXT: [[TMP19:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
+; IF-EVL-OUTLOOP-NEXT: [[TMP19:%.*]] = add <vscale x 4 x i32> [[VEC_PHI]], [[VP_OP_LOAD]]
; IF-EVL-OUTLOOP-NEXT: [[TMP20:%.*]] = xor <vscale x 4 x i1> [[TMP18]], splat (i1 true)
; IF-EVL-OUTLOOP-NEXT: [[TMP21:%.*]] = select <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i1> [[TMP20]], <vscale x 4 x i1> zeroinitializer
; IF-EVL-OUTLOOP-NEXT: [[PREDPHI1:%.*]] = select <vscale x 4 x i1> [[TMP21]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i32> [[TMP19]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-div.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-div.ll
new file mode 100644
index 0000000000000..0bfab2da51fa7
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-div.ll
@@ -0,0 +1,407 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=loop-vectorize \
+; RUN: -force-tail-folding-style=data-with-evl \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s --check-prefix=IF-EVL
+
+; RUN: opt -passes=loop-vectorize \
+; RUN: -force-tail-folding-style=none \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s --check-prefix=NO-VP
+
+define void @test_sdiv(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
+; IF-EVL-LABEL: define void @test_sdiv(
+; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0:[0-9]+]] {
+; IF-EVL-NEXT: [[LOOP_PREHEADER:.*]]:
+; IF-EVL-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL: [[VECTOR_PH]]:
+; IF-EVL-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT: [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
+; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT: br label %[[VECTOR_BODY:.*]]
+; IF-EVL: [[VECTOR_BODY]]:
+; IF-EVL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; IF-EVL-NEXT: [[TMP6:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT: [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = sdiv <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
+; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
+; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
+; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; IF-EVL: [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL: [[SCALAR_PH]]:
+; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; IF-EVL-NEXT: br label %[[LOOP:.*]]
+; IF-EVL: [[LOOP]]:
+; IF-EVL-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; IF-EVL-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
+; IF-EVL-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
+; IF-EVL-NEXT: [[TMP18:%.*]] = sdiv i64 [[TMP16]], [[TMP17]]
+; IF-EVL-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; IF-EVL-NEXT: store i64 [[TMP18]], ptr [[C_GEP]], align 8
+; IF-EVL-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; IF-EVL-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; IF-EVL: [[EXIT]]:
+; IF-EVL-NEXT: ret void
+;
+; NO-VP-LABEL: define void @test_sdiv(
+; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0:[0-9]+]] {
+; NO-VP-NEXT: [[LOOP_PREHEADER:.*]]:
+; NO-VP-NEXT: br label %[[LOOP:.*]]
+; NO-VP: [[LOOP]]:
+; NO-VP-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; NO-VP-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
+; NO-VP-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
+; NO-VP-NEXT: [[TMP2:%.*]] = sdiv i64 [[TMP0]], [[TMP1]]
+; NO-VP-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; NO-VP-NEXT: store i64 [[TMP2]], ptr [[C_GEP]], align 8
+; NO-VP-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; NO-VP-NEXT: br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
+; NO-VP: [[EXIT]]:
+; NO-VP-NEXT: ret void
+;
+loop.preheader:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
+ %a.gep = getelementptr i64, ptr %a, i64 %iv
+ %0 = load i64, ptr %a.gep
+ %b.gep = getelementptr i64, ptr %b, i64 %iv
+ %1 = load i64, ptr %b.gep
+ %2 = sdiv i64 %0, %1
+ %c.gep = getelementptr i64, ptr %c, i64 %iv
+ store i64 %2, ptr %c.gep
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, 1024
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret void
+}
+
+
+define void @test_udiv(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
+; IF-EVL-LABEL: define void @test_udiv(
+; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; IF-EVL-NEXT: [[LOOP_PREHEADER:.*]]:
+; IF-EVL-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL: [[VECTOR_PH]]:
+; IF-EVL-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT: [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
+; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT: br label %[[VECTOR_BODY:.*]]
+; IF-EVL: [[VECTOR_BODY]]:
+; IF-EVL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; IF-EVL-NEXT: [[TMP6:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT: [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = udiv <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
+; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
+; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
+; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; IF-EVL: [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL: [[SCALAR_PH]]:
+; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; IF-EVL-NEXT: br label %[[LOOP:.*]]
+; IF-EVL: [[LOOP]]:
+; IF-EVL-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; IF-EVL-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
+; IF-EVL-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
+; IF-EVL-NEXT: [[TMP18:%.*]] = udiv i64 [[TMP16]], [[TMP17]]
+; IF-EVL-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; IF-EVL-NEXT: store i64 [[TMP18]], ptr [[C_GEP]], align 8
+; IF-EVL-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; IF-EVL-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
+; IF-EVL: [[EXIT]]:
+; IF-EVL-NEXT: ret void
+;
+; NO-VP-LABEL: define void @test_udiv(
+; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; NO-VP-NEXT: [[LOOP_PREHEADER:.*]]:
+; NO-VP-NEXT: br label %[[LOOP:.*]]
+; NO-VP: [[LOOP]]:
+; NO-VP-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; NO-VP-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
+; NO-VP-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
+; NO-VP-NEXT: [[TMP2:%.*]] = udiv i64 [[TMP0]], [[TMP1]]
+; NO-VP-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; NO-VP-NEXT: store i64 [[TMP2]], ptr [[C_GEP]], align 8
+; NO-VP-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; NO-VP-NEXT: br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
+; NO-VP: [[EXIT]]:
+; NO-VP-NEXT: ret void
+;
+loop.preheader:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
+ %a.gep = getelementptr i64, ptr %a, i64 %iv
+ %0 = load i64, ptr %a.gep
+ %b.gep = getelementptr i64, ptr %b, i64 %iv
+ %1 = load i64, ptr %b.gep
+ %2 = udiv i64 %0, %1
+ %c.gep = getelementptr i64, ptr %c, i64 %iv
+ store i64 %2, ptr %c.gep
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, 1024
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret void
+}
+
+define void @test_srem(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
+; IF-EVL-LABEL: define void @test_srem(
+; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; IF-EVL-NEXT: [[LOOP_PREHEADER:.*]]:
+; IF-EVL-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL: [[VECTOR_PH]]:
+; IF-EVL-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT: [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
+; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT: br label %[[VECTOR_BODY:.*]]
+; IF-EVL: [[VECTOR_BODY]]:
+; IF-EVL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; IF-EVL-NEXT: [[TMP6:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT: [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = srem <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
+; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
+; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
+; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; IF-EVL: [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL: [[SCALAR_PH]]:
+; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; IF-EVL-NEXT: br label %[[LOOP:.*]]
+; IF-EVL: [[LOOP]]:
+; IF-EVL-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; IF-EVL-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
+; IF-EVL-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
+; IF-EVL-NEXT: [[TMP18:%.*]] = srem i64 [[TMP16]], [[TMP17]]
+; IF-EVL-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; IF-EVL-NEXT: store i64 [[TMP18]], ptr [[C_GEP]], align 8
+; IF-EVL-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; IF-EVL-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; IF-EVL: [[EXIT]]:
+; IF-EVL-NEXT: ret void
+;
+; NO-VP-LABEL: define void @test_srem(
+; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; NO-VP-NEXT: [[LOOP_PREHEADER:.*]]:
+; NO-VP-NEXT: br label %[[LOOP:.*]]
+; NO-VP: [[LOOP]]:
+; NO-VP-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; NO-VP-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
+; NO-VP-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
+; NO-VP-NEXT: [[TMP2:%.*]] = srem i64 [[TMP0]], [[TMP1]]
+; NO-VP-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; NO-VP-NEXT: store i64 [[TMP2]], ptr [[C_GEP]], align 8
+; NO-VP-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; NO-VP-NEXT: br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
+; NO-VP: [[EXIT]]:
+; NO-VP-NEXT: ret void
+;
+loop.preheader:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
+ %a.gep = getelementptr i64, ptr %a, i64 %iv
+ %0 = load i64, ptr %a.gep
+ %b.gep = getelementptr i64, ptr %b, i64 %iv
+ %1 = load i64, ptr %b.gep
+ %2 = srem i64 %0, %1
+ %c.gep = getelementptr i64, ptr %c, i64 %iv
+ store i64 %2, ptr %c.gep
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, 1024
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret void
+}
+
+define void @test_urem(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
+; IF-EVL-LABEL: define void @test_urem(
+; IF-EVL-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; IF-EVL-NEXT: [[LOOP_PREHEADER:.*]]:
+; IF-EVL-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL: [[VECTOR_PH]]:
+; IF-EVL-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT: [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i64 1024, [[TMP2]]
+; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT: br label %[[VECTOR_BODY:.*]]
+; IF-EVL: [[VECTOR_BODY]]:
+; IF-EVL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT: [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; IF-EVL-NEXT: [[TMP6:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT: [[TMP7:%.*]] = getelementptr i64, ptr [[A]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP9:%.*]] = getelementptr i64, ptr [[B]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP10:%.*]] = getelementptr i64, ptr [[TMP9]], i32 0
+; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[VP_OP_LOAD1]], <vscale x 2 x i64> splat (i64 1), i32 [[TMP5]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = urem <vscale x 2 x i64> [[VP_OP_LOAD]], [[TMP11]]
+; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[C]], i64 [[TMP6]]
+; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr i64, ptr [[TMP12]], i32 0
+; IF-EVL-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; IF-EVL-NEXT: [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
+; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT: br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; IF-EVL: [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL: [[SCALAR_PH]]:
+; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; IF-EVL-NEXT: br label %[[LOOP:.*]]
+; IF-EVL: [[LOOP]]:
+; IF-EVL-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; IF-EVL-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP16:%.*]] = load i64, ptr [[A_GEP]], align 8
+; IF-EVL-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; IF-EVL-NEXT: [[TMP17:%.*]] = load i64, ptr [[B_GEP]], align 8
+; IF-EVL-NEXT: [[TMP18:%.*]] = urem i64 [[TMP16]], [[TMP17]]
+; IF-EVL-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; IF-EVL-NEXT: store i64 [[TMP18]], ptr [[C_GEP]], align 8
+; IF-EVL-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; IF-EVL-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; IF-EVL: [[EXIT]]:
+; IF-EVL-NEXT: ret void
+;
+; NO-VP-LABEL: define void @test_urem(
+; NO-VP-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; NO-VP-NEXT: [[LOOP_PREHEADER:.*]]:
+; NO-VP-NEXT: br label %[[LOOP:.*]]
+; NO-VP: [[LOOP]]:
+; NO-VP-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ 0, %[[LOOP_PREHEADER]] ]
+; NO-VP-NEXT: [[A_GEP:%.*]] = getelementptr i64, ptr [[A]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP0:%.*]] = load i64, ptr [[A_GEP]], align 8
+; NO-VP-NEXT: [[B_GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[IV]]
+; NO-VP-NEXT: [[TMP1:%.*]] = load i64, ptr [[B_GEP]], align 8
+; NO-VP-NEXT: [[TMP2:%.*]] = urem i64 [[TMP0]], [[TMP1]]
+; NO-VP-NEXT: [[C_GEP:%.*]] = getelementptr i64, ptr [[C]], i64 [[IV]]
+; NO-VP-NEXT: store i64 [[TMP2]], ptr [[C_GEP]], align 8
+; NO-VP-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT: [[DONE:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
+; NO-VP-NEXT: br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
+; NO-VP: [[EXIT]]:
+; NO-VP-NEXT: ret void
+;
+loop.preheader:
+ br label %loop
+
+loop:
+ %iv = phi i64 [ %iv.next, %loop ], [ 0, %loop.preheader ]
+ %a.gep = getelementptr i64, ptr %a, i64 %iv
+ %0 = load i64, ptr %a.gep
+ %b.gep = getelementptr i64, ptr %b, i64 %iv
+ %1 = load i64, ptr %b.gep
+ %2 = urem i64 %0, %1
+ %c.gep = getelementptr i64, ptr %c, i64 %iv
+ store i64 %2, ptr %c.gep
+ %iv.next = add i64 %iv, 1
+ %done = icmp eq i64 %iv.next, 1024
+ br i1 %done, label %exit, label %loop
+
+exit:
+ ret void
+}
+;.
+; IF-EVL: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; IF-EVL: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; IF-EVL: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; IF-EVL: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+; IF-EVL: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
+; IF-EVL: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]}
+; IF-EVL: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
+; IF-EVL: [[LOOP9]] = distinct !{[[LOOP9]], [[META2]], [[META1]]}
+;.
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-intermediate-store.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-intermediate-store.ll
index 733c05fd9259c..69988e03b2657 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-intermediate-store.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-intermediate-store.ll
@@ -59,7 +59,7 @@ define void @reduction_intermediate_store(ptr %a, i64 %n, i32 %start, ptr %addr)
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP13]]
; IF-EVL-OUTLOOP-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[TMP17]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]]), !alias.scope [[META0:![0-9]+]]
-; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT: [[TMP19]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP12]])
; IF-EVL-OUTLOOP-NEXT: [[TMP21:%.*]] = zext i32 [[TMP12]] to i64
; IF-EVL-OUTLOOP-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP21]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-known-no-overflow.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-known-no-overflow.ll
index dc74f44688fdf..b4ef2c800f5bd 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-known-no-overflow.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-known-no-overflow.ll
@@ -39,7 +39,7 @@ define void @trip_count_max_1024(ptr %p, i64 %tc) vscale_range(2, 1024) {
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[TMP11]], i32 0
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP12]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i64> splat (i64 1), <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
+; CHECK-NEXT: [[VP_OP:%.*]] = add <vscale x 2 x i64> [[VP_OP_LOAD]], splat (i64 1)
; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP12]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
; CHECK-NEXT: [[TMP13:%.*]] = zext i32 [[TMP9]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP13]], [[EVL_BASED_IV]]
@@ -115,7 +115,7 @@ define void @overflow_at_0(ptr %p, i64 %tc) vscale_range(2, 1024) {
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i64, ptr [[TMP11]], i32 0
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP12]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i64> splat (i64 1), <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
+; CHECK-NEXT: [[VP_OP:%.*]] = add <vscale x 2 x i64> [[VP_OP_LOAD]], splat (i64 1)
; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP12]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
; CHECK-NEXT: [[TMP13:%.*]] = zext i32 [[TMP9]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP13]], [[EVL_BASED_IV]]
@@ -187,7 +187,7 @@ define void @no_overflow_at_0(ptr %p, i64 %tc) vscale_range(2, 1024) {
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
-; CHECK-NEXT: [[VP_OP:%.*]] = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> [[VP_OP_LOAD]], <vscale x 2 x i64> splat (i64 1), <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; CHECK-NEXT: [[VP_OP:%.*]] = add <vscale x 2 x i64> [[VP_OP_LOAD]], splat (i64 1)
; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP]], ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT: [[TMP9:%.*]] = zext i32 [[TMP5]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP9]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll
index ab58bb07702c1..4452f3860274d 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll
@@ -50,7 +50,7 @@ define void @masked_loadstore(ptr noalias %a, ptr noalias %b, i64 %n) {
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr i32, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP20:%.*]] = getelementptr i32, ptr [[TMP19]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD3:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP20]], <vscale x 4 x i1> [[TMP18]], i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VP_OP_LOAD3]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[VP_OP_LOAD]], [[VP_OP_LOAD3]]
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[VP_OP]], ptr align 4 [[TMP20]], <vscale x 4 x i1> [[TMP18]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP21:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP21]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction.ll
index b81805d473002..ed44fe33999ad 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-reduction.ll
@@ -38,7 +38,7 @@ define i32 @add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT: [[TMP14]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP15:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP15]], [[EVL_BASED_IV]]
@@ -271,7 +271,7 @@ define i32 @or(ptr %a, i64 %n, i32 %start) {
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.or.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = or <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT: [[TMP14]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP15:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP15]], [[EVL_BASED_IV]]
@@ -391,7 +391,7 @@ define i32 @and(ptr %a, i64 %n, i32 %start) {
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = and <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT: [[TMP14]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP15:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP15]], [[EVL_BASED_IV]]
@@ -511,7 +511,7 @@ define i32 @xor(ptr %a, i64 %n, i32 %start) {
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.xor.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = xor <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT: [[TMP14]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP15:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP15]], [[EVL_BASED_IV]]
@@ -1139,7 +1139,7 @@ define float @fadd(ptr %a, i64 %n, float %start) {
; IF-EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP13:%.*]] = getelementptr inbounds float, ptr [[TMP12]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call reassoc <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = fadd reassoc <vscale x 4 x float> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT: [[TMP14]] = call <vscale x 4 x float> @llvm.vp.merge.nxv4f32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> [[VP_OP]], <vscale x 4 x float> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP15:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP15]], [[EVL_BASED_IV]]
@@ -1857,7 +1857,7 @@ define float @fmuladd(ptr %a, ptr %b, i64 %n, float %start) {
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 [[TMP11]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
-; IF-EVL-NEXT: [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fmuladd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> [[VP_OP_LOAD1]], <vscale x 4 x float> [[VEC_PHI]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP10]])
+; IF-EVL-NEXT: [[TMP16:%.*]] = call reassoc <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> [[VP_OP_LOAD1]], <vscale x 4 x float> [[VEC_PHI]])
; IF-EVL-NEXT: [[TMP17]] = call <vscale x 4 x float> @llvm.vp.merge.nxv4f32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> [[TMP16]], <vscale x 4 x float> [[VEC_PHI]], i32 [[TMP10]])
; IF-EVL-NEXT: [[TMP18:%.*]] = zext i32 [[TMP10]] to i64
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP18]], [[EVL_BASED_IV]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll
index 55a84733191fd..9069c6bf7a1a0 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-vp-intrinsics.ll
@@ -39,7 +39,7 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD1:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
-; IF-EVL-NEXT: [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VP_OP_LOAD1]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
+; IF-EVL-NEXT: [[VP_OP:%.*]] = add nsw <vscale x 4 x i32> [[VP_OP_LOAD1]], [[VP_OP_LOAD]]
; IF-EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP13]]
; IF-EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, ptr [[TMP18]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[VP_OP]], ptr align 4 [[TMP19]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll
index 81a2675dc6583..a213608857728 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll
@@ -30,10 +30,10 @@ define void @vp_smax(ptr %a, ptr %b, ptr %c, i64 %N) {
; 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-INTRINSIC vp<[[SMAX:%.+]]> = call llvm.vp.smax(ir<[[LD1]]>, ir<[[LD2]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[SMAX:%.+]]> = call llvm.smax(ir<[[LD1]]>, ir<[[LD2]]>)
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, vp<[[SMAX]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[SMAX]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -86,10 +86,10 @@ define void @vp_smin(ptr %a, ptr %b, ptr %c, i64 %N) {
; 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-INTRINSIC vp<[[SMIN:%.+]]> = call llvm.vp.smin(ir<[[LD1]]>, ir<[[LD2]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[SMIN:%.+]]> = call llvm.smin(ir<[[LD1]]>, ir<[[LD2]]>)
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, vp<[[SMIN]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[SMIN]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -142,10 +142,10 @@ define void @vp_umax(ptr %a, ptr %b, ptr %c, i64 %N) {
; 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-INTRINSIC vp<[[UMAX:%.+]]> = call llvm.vp.umax(ir<[[LD1]]>, ir<[[LD2]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[UMAX:%.+]]> = call llvm.umax(ir<[[LD1]]>, ir<[[LD2]]>)
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, vp<[[UMAX]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[UMAX]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -198,10 +198,10 @@ define void @vp_umin(ptr %a, ptr %b, ptr %c, i64 %N) {
; 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-INTRINSIC vp<[[UMIN:%.+]]> = call llvm.vp.umin(ir<[[LD1]]>, ir<[[LD2]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[UMIN:%.+]]> = call llvm.umin(ir<[[LD1]]>, ir<[[LD2]]>)
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, vp<[[UMIN]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[UMIN]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -251,10 +251,10 @@ define void @vp_ctlz(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[CTLZ:%.+]]> = call llvm.vp.ctlz(ir<[[LD1]]>, ir<true>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[CTLZ:%.+]]> = call llvm.ctlz(ir<[[LD1]]>, ir<true>)
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[CTLZ]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[CTLZ]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -302,10 +302,10 @@ define void @vp_cttz(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[CTTZ:%.+]]> = call llvm.vp.cttz(ir<[[LD1]]>, ir<true>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[CTTZ:%.+]]> = call llvm.cttz(ir<[[LD1]]>, ir<true>)
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[CTTZ]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[CTTZ]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -353,12 +353,12 @@ define void @vp_lrint(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPEXT:%.+]]> = call llvm.vp.fpext(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
-; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[LRINT:%.+]]> = call llvm.vp.lrint(vp<[[FPEXT]]>, ir<true>, vp<[[EVL]]>)
-; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[TRUNC:%.+]]> = call llvm.vp.trunc(vp<[[LRINT]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPEXT:%.+]]> = fpext ir<[[LD1]]> to double
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[LRINT:%.+]]> = call llvm.lrint(ir<[[FPEXT]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[TRUNC:%.+]]> = trunc ir<[[LRINT]]> to i32
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[TRUNC]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[TRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -408,12 +408,12 @@ define void @vp_llrint(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPEXT:%.+]]> = call llvm.vp.fpext(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
-; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[LLRINT:%.+]]> = call llvm.vp.llrint(vp<[[FPEXT]]>, ir<true>, vp<[[EVL]]>)
-; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[TRUNC:%.+]]> = call llvm.vp.trunc(vp<[[LLRINT]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPEXT:%.+]]> = fpext ir<[[LD1]]> to double
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[LLRINT:%.+]]> = call llvm.llrint(ir<[[FPEXT]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[TRUNC:%.+]]> = trunc ir<[[LLRINT]]> to i32
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[TRUNC]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[TRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -463,10 +463,10 @@ define void @vp_abs(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[ABS:%.+]]> = call llvm.vp.abs(ir<[[LD1]]>, ir<true>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-INTRINSIC ir<[[ABS:%.+]]> = call llvm.abs(ir<[[LD1]]>, ir<true>)
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[ABS]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ABS]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-cast-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-cast-intrinsics.ll
index 40cf02c4663fe..b8f20aa670b5c 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-cast-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-cast-intrinsics.ll
@@ -26,10 +26,10 @@ define void @vp_sext(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[SEXT:%.+]]> = call llvm.vp.sext(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[SEXT:%.+]]> = sext ir<[[LD1]]> to i64
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[SEXT]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[SEXT]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -79,10 +79,10 @@ define void @vp_zext(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[ZEXT:%.+]]> = call llvm.vp.zext(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[ZEXT:%.+]]> = zext ir<[[LD1]]> to i64
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[ZEXT]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ZEXT]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -130,10 +130,10 @@ define void @vp_trunc(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[TRUNC:%.+]]> = call llvm.vp.trunc(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[TRUNC:%.+]]> = trunc ir<[[LD1]]> to i16
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[TRUNC]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[TRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -181,10 +181,10 @@ define void @vp_fpext(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPEXT:%.+]]> = call llvm.vp.fpext(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPEXT:%.+]]> = fpext ir<[[LD1]]> to double
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[FPEXT]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[FPEXT]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -232,10 +232,10 @@ define void @vp_fptrunc(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPTRUNC:%.+]]> = call llvm.vp.fptrunc(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPTRUNC:%.+]]> = fptrunc ir<[[LD1]]> to float
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[FPTRUNC]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[FPTRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -283,10 +283,10 @@ define void @vp_sitofp(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[SITOFP:%.+]]> = call llvm.vp.sitofp(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[SITOFP:%.+]]> = sitofp ir<[[LD1]]> to float
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[SITOFP]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[SITOFP]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -334,10 +334,10 @@ define void @vp_uitofp(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[UITOFP:%.+]]> = call llvm.vp.uitofp(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[UITOFP:%.+]]> = uitofp ir<[[LD1]]> to float
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[UITOFP]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[UITOFP]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -385,10 +385,10 @@ define void @vp_fptosi(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPTOSI:%.+]]> = call llvm.vp.fptosi(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPTOSI:%.+]]> = fptosi ir<[[LD1]]> to i32
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[FPTOSI]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[FPTOSI]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -436,10 +436,10 @@ define void @vp_fptoui(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[FPTOUI:%.+]]> = call llvm.vp.fptoui(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[FPTOUI:%.+]]> = fptoui ir<[[LD1]]> to i32
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[FPTOUI]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[FPTOUI]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
@@ -487,10 +487,10 @@ define void @vp_inttoptr(ptr %a, ptr %b, i64 %N) {
; 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: WIDEN-INTRINSIC vp<[[INTTOPTR:%.+]]> = call llvm.vp.inttoptr(ir<[[LD1]]>, ir<true>, vp<[[EVL]]>)
+; IF-EVL-NEXT: WIDEN-CAST ir<[[INTTOPTR:%.+]]> = inttoptr ir<[[LD1]]> to ptr
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
-; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, vp<[[INTTOPTR]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[INTTOPTR]]>, vp<[[EVL]]>
; IF-EVL-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll
index 0daf15d04af35..3594b3f047363 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll
@@ -49,7 +49,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]>
; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]>
-; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = vp.add ir<[[LD1]]>, ir<[[RDX_PHI]]>, vp<[[EVL]]>
+; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]>
; IF-EVL-OUTLOOP-NEXT: WIDEN-INTRINSIC vp<[[RDX_SELECT]]> = call llvm.vp.merge(ir<true>, ir<[[ADD]]>, ir<[[RDX_PHI]]>, vp<[[EVL]]>)
; IF-EVL-OUTLOOP-NEXT: SCALAR-CAST vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-OUTLOOP-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll
index e64ea387d4582..4cef3f029e20f 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll
@@ -35,7 +35,7 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
; 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<[[ADD:%.+]]> = vp.add nsw ir<[[LD2]]>, ir<[[LD1]]>, vp<[[EVL]]>
+; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]>
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[ADD]]>, vp<[[EVL]]>
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll
index 90de5b6bfd1d3..67be80393d829 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-select-intrinsics.ll
@@ -44,9 +44,9 @@
; 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 ir<[[SUB:%.+]]> = sub ir<0>, ir<[[LD2]]>
; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[SELECT:%.+]]> = call llvm.vp.select(ir<[[CMP]]>, ir<[[LD2]]>, ir<[[SUB]]>, vp<[[EVL]]>)
- ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = vp.add vp<[[SELECT]]>, ir<[[LD1]]>, vp<[[EVL]]>
+ ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add vp<[[SELECT]]>, ir<[[LD1]]>
; 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]]>
More information about the llvm-commits
mailing list