[llvm] [TTI][RISCV] Deduplicate type-based VP costing (PR #115983)

[Luke Lau via llvm-commits]

https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/115983

>From ef0adc704e8a19b71566d3c8465d498226bd4d47 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Wed, 13 Nov 2024 11:15:47 +0800
Subject: [PATCH 1/2] [TTI][RISCV] Deduplicate type-based VP costing

We have a lot of code in RISCVTTIImpl::getIntrinsicInstrCost for vp intrinsics, which just forward the cost to the underlying non-vp cost function.

However I just also noticed that there is generic code in BasicTTIImpl's getIntrinsicInstrCost that does the same thing, added in #67178. The only difference is that BasicTTIImpl doesn't yet handle it for type-based costing. There doesn't seem to be any reason that it can't since it's just inspecting the argument types.

This shuffles the VP costing up to handle both regular and type-based costing, and begins to deduplicate the VP specific costing in RISCVTTIImpl by moving them into BasicTTIImpl.h.

It's not NFC since it picks up a couple of VP nodes that had slipped through the cracks. Future PRs can begin to move more of the code from RISCVTTIImpl to BasicTTIImpl.
---
 llvm/include/llvm/CodeGen/BasicTTIImpl.h      | 123 +++++++++---------
 .../Target/RISCV/RISCVTargetTransformInfo.cpp |  43 ------
 .../Analysis/CostModel/RISCV/vp-intrinsics.ll |  32 ++---
 3 files changed, 77 insertions(+), 121 deletions(-)

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 36df9ee2e7d94c..c2e48284c68acb 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1574,6 +1574,67 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     if (Intrinsic::isTargetIntrinsic(IID))
       return TargetTransformInfo::TCC_Basic;
 
+    // VP Intrinsics should have the same cost as their non-vp counterpart.
+    // TODO: Adjust the cost to make the vp intrinsic cheaper than its non-vp
+    // counterpart when the vector length argument is smaller than the maximum
+    // vector length.
+    // TODO: Support other kinds of VPIntrinsics
+    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
+      std::optional<unsigned> FOp =
+          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
+      if (FOp) {
+        if (ICA.getID() == Intrinsic::vp_load) {
+          Align Alignment;
+          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
+            Alignment = VPI->getPointerAlignment().valueOrOne();
+          unsigned AS = 0;
+          if (ICA.getArgTypes().size() > 1)
+            if (auto *PtrTy = dyn_cast<PointerType>(ICA.getArgTypes()[0]))
+              AS = PtrTy->getAddressSpace();
+          return thisT()->getMemoryOpCost(*FOp, ICA.getReturnType(), Alignment,
+                                          AS, CostKind);
+        }
+        if (ICA.getID() == Intrinsic::vp_store) {
+          Align Alignment;
+          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
+            Alignment = VPI->getPointerAlignment().valueOrOne();
+          unsigned AS = 0;
+          if (ICA.getArgTypes().size() >= 2)
+            if (auto *PtrTy = dyn_cast<PointerType>(ICA.getArgTypes()[1]))
+              AS = PtrTy->getAddressSpace();
+          return thisT()->getMemoryOpCost(*FOp, ICA.getArgTypes()[0], Alignment,
+                                          AS, CostKind);
+        }
+        if (VPBinOpIntrinsic::isVPBinOp(ICA.getID())) {
+          return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
+                                                 CostKind);
+        }
+      }
+
+      std::optional<Intrinsic::ID> FID =
+          VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());
+      if (FID) {
+        // Non-vp version will have same arg types except mask and vector
+        // length.
+        assert(ICA.getArgTypes().size() >= 2 &&
+               "Expected VPIntrinsic to have Mask and Vector Length args and "
+               "types");
+        ArrayRef<Type *> NewTys = ArrayRef(ICA.getArgTypes()).drop_back(2);
+
+        // VPReduction intrinsics have a start value argument that their non-vp
+        // counterparts do not have, except for the fadd and fmul non-vp
+        // counterpart.
+        if (VPReductionIntrinsic::isVPReduction(ICA.getID()) &&
+            *FID != Intrinsic::vector_reduce_fadd &&
+            *FID != Intrinsic::vector_reduce_fmul)
+          NewTys = NewTys.drop_front();
+
+        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewTys,
+                                       ICA.getFlags());
+        return thisT()->getIntrinsicInstrCost(NewICA, CostKind);
+      }
+    }
+
     if (ICA.isTypeBasedOnly())
       return getTypeBasedIntrinsicInstrCost(ICA, CostKind);
 
@@ -1834,68 +1895,6 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
     }
     }
 
-    // VP Intrinsics should have the same cost as their non-vp counterpart.
-    // TODO: Adjust the cost to make the vp intrinsic cheaper than its non-vp
-    // counterpart when the vector length argument is smaller than the maximum
-    // vector length.
-    // TODO: Support other kinds of VPIntrinsics
-    if (VPIntrinsic::isVPIntrinsic(ICA.getID())) {
-      std::optional<unsigned> FOp =
-          VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
-      if (FOp) {
-        if (ICA.getID() == Intrinsic::vp_load) {
-          Align Alignment;
-          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
-            Alignment = VPI->getPointerAlignment().valueOrOne();
-          unsigned AS = 0;
-          if (ICA.getArgs().size() > 1)
-            if (auto *PtrTy =
-                    dyn_cast<PointerType>(ICA.getArgs()[0]->getType()))
-              AS = PtrTy->getAddressSpace();
-          return thisT()->getMemoryOpCost(*FOp, ICA.getReturnType(), Alignment,
-                                          AS, CostKind);
-        }
-        if (ICA.getID() == Intrinsic::vp_store) {
-          Align Alignment;
-          if (auto *VPI = dyn_cast_or_null<VPIntrinsic>(ICA.getInst()))
-            Alignment = VPI->getPointerAlignment().valueOrOne();
-          unsigned AS = 0;
-          if (ICA.getArgs().size() >= 2)
-            if (auto *PtrTy =
-                    dyn_cast<PointerType>(ICA.getArgs()[1]->getType()))
-              AS = PtrTy->getAddressSpace();
-          return thisT()->getMemoryOpCost(*FOp, Args[0]->getType(), Alignment,
-                                          AS, CostKind);
-        }
-        if (VPBinOpIntrinsic::isVPBinOp(ICA.getID())) {
-          return thisT()->getArithmeticInstrCost(*FOp, ICA.getReturnType(),
-                                                 CostKind);
-        }
-      }
-
-      std::optional<Intrinsic::ID> FID =
-          VPIntrinsic::getFunctionalIntrinsicIDForVP(ICA.getID());
-      if (FID) {
-        // Non-vp version will have same Args/Tys except mask and vector length.
-        assert(ICA.getArgs().size() >= 2 && ICA.getArgTypes().size() >= 2 &&
-               "Expected VPIntrinsic to have Mask and Vector Length args and "
-               "types");
-        ArrayRef<Type *> NewTys = ArrayRef(ICA.getArgTypes()).drop_back(2);
-
-        // VPReduction intrinsics have a start value argument that their non-vp
-        // counterparts do not have, except for the fadd and fmul non-vp
-        // counterpart.
-        if (VPReductionIntrinsic::isVPReduction(ICA.getID()) &&
-            *FID != Intrinsic::vector_reduce_fadd &&
-            *FID != Intrinsic::vector_reduce_fmul)
-          NewTys = NewTys.drop_front();
-
-        IntrinsicCostAttributes NewICA(*FID, ICA.getReturnType(), NewTys,
-                                       ICA.getFlags());
-        return thisT()->getIntrinsicInstrCost(NewICA, CostKind);
-      }
-    }
-
     // Assume that we need to scalarize this intrinsic.)
     // Compute the scalarization overhead based on Args for a vector
     // intrinsic.
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 5d21bb611df4e4..8d40c410e4b4a5 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1104,32 +1104,6 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return Cost * LT.first;
     break;
   }
-  // vp integer arithmetic ops.
-  case Intrinsic::vp_add:
-  case Intrinsic::vp_and:
-  case Intrinsic::vp_ashr:
-  case Intrinsic::vp_lshr:
-  case Intrinsic::vp_mul:
-  case Intrinsic::vp_or:
-  case Intrinsic::vp_sdiv:
-  case Intrinsic::vp_shl:
-  case Intrinsic::vp_srem:
-  case Intrinsic::vp_sub:
-  case Intrinsic::vp_udiv:
-  case Intrinsic::vp_urem:
-  case Intrinsic::vp_xor:
-  // vp float arithmetic ops.
-  case Intrinsic::vp_fadd:
-  case Intrinsic::vp_fsub:
-  case Intrinsic::vp_fmul:
-  case Intrinsic::vp_fdiv:
-  case Intrinsic::vp_frem: {
-    std::optional<unsigned> FOp =
-        VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
-    assert(FOp.has_value());
-    return getArithmeticInstrCost(*FOp, ICA.getReturnType(), CostKind);
-    break;
-  }
   // vp int cast ops.
   case Intrinsic::vp_trunc:
   case Intrinsic::vp_zext:
@@ -1163,23 +1137,6 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     return getCmpSelInstrCost(*FOp, ICA.getArgTypes()[0], ICA.getReturnType(),
                               UI->getPredicate(), CostKind);
   }
-  // vp load/store
-  case Intrinsic::vp_load:
-  case Intrinsic::vp_store: {
-    if (!ICA.getInst())
-      break;
-    Intrinsic::ID IID = ICA.getID();
-    std::optional<unsigned> FOp = VPIntrinsic::getFunctionalOpcodeForVP(IID);
-    assert(FOp.has_value());
-    auto *UI = cast<VPIntrinsic>(ICA.getInst());
-    if (ICA.getID() == Intrinsic::vp_load)
-      return getMemoryOpCost(
-          *FOp, ICA.getReturnType(), UI->getPointerAlignment(),
-          UI->getOperand(0)->getType()->getPointerAddressSpace(), CostKind);
-    return getMemoryOpCost(
-        *FOp, ICA.getArgTypes()[0], UI->getPointerAlignment(),
-        UI->getOperand(1)->getType()->getPointerAddressSpace(), CostKind);
-  }
   case Intrinsic::vp_select: {
     Intrinsic::ID IID = ICA.getID();
     std::optional<unsigned> FOp = VPIntrinsic::getFunctionalOpcodeForVP(IID);
diff --git a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
index f5c54b93914688..4be2529c929221 100644
--- a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
@@ -1172,37 +1172,37 @@ define void @abs() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'abs'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 141 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;

>From 763388652cf5e688d840db3dad34e1e8ea8c17f2 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Wed, 13 Nov 2024 14:25:23 +0800
Subject: [PATCH 2/2] Update test

---
 .../Analysis/CostModel/RISCV/vp-intrinsics.ll | 256 +++++++++---------
 .../RISCV/vpintrin-scalarization.ll           | 100 +++----
 2 files changed, 160 insertions(+), 196 deletions(-)

diff --git a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
index 4be2529c929221..169c0cc710c7c9 100644
--- a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
@@ -747,38 +747,38 @@ define void @smax() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'smax'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t0 = call <2 x i8> @llvm.vp.smax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t2 = call <4 x i8> @llvm.vp.smax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t4 = call <8 x i8> @llvm.vp.smax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %t6 = call <16 x i8> @llvm.vp.smax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t8 = call <2 x i16> @llvm.vp.smax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t10 = call <4 x i16> @llvm.vp.smax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t12 = call <8 x i16> @llvm.vp.smax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t14 = call <16 x i16> @llvm.vp.smax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t16 = call <2 x i32> @llvm.vp.smax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t18 = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t20 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t22 = call <16 x i32> @llvm.vp.smax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t24 = call <2 x i64> @llvm.vp.smax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %t26 = call <4 x i64> @llvm.vp.smax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t28 = call <8 x i64> @llvm.vp.smax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t30 = call <16 x i64> @llvm.vp.smax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.smax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.smax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.smax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.smax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.smax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.smax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.smax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.smax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.smax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.smax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.smax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.smax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.smax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.smax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.smax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.smax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -854,38 +854,38 @@ define void @smin() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'smin'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t0 = call <2 x i8> @llvm.vp.smin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t2 = call <4 x i8> @llvm.vp.smin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t4 = call <8 x i8> @llvm.vp.smin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %t6 = call <16 x i8> @llvm.vp.smin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t8 = call <2 x i16> @llvm.vp.smin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t10 = call <4 x i16> @llvm.vp.smin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t12 = call <8 x i16> @llvm.vp.smin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t14 = call <16 x i16> @llvm.vp.smin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t16 = call <2 x i32> @llvm.vp.smin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t18 = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t20 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t22 = call <16 x i32> @llvm.vp.smin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t24 = call <2 x i64> @llvm.vp.smin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %t26 = call <4 x i64> @llvm.vp.smin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t28 = call <8 x i64> @llvm.vp.smin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t30 = call <16 x i64> @llvm.vp.smin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.smin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.smin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.smin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.smin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.smin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.smin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.smin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.smin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.smin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.smin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.smin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.smin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.smin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.smin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.smin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.smin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.smin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -960,38 +960,38 @@ define void @umax() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'umax'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t0 = call <2 x i8> @llvm.vp.umax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t2 = call <4 x i8> @llvm.vp.umax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t4 = call <8 x i8> @llvm.vp.umax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %t6 = call <16 x i8> @llvm.vp.umax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t8 = call <2 x i16> @llvm.vp.umax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t10 = call <4 x i16> @llvm.vp.umax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t12 = call <8 x i16> @llvm.vp.umax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t14 = call <16 x i16> @llvm.vp.umax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t16 = call <2 x i32> @llvm.vp.umax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t18 = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t20 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t22 = call <16 x i32> @llvm.vp.umax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t24 = call <2 x i64> @llvm.vp.umax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %t26 = call <4 x i64> @llvm.vp.umax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t28 = call <8 x i64> @llvm.vp.umax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t30 = call <16 x i64> @llvm.vp.umax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.umax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.umax.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.umax.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.umax.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.umax.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.umax.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.umax.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.umax.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.umax.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.umax.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.umax.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.umax.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.umax.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.umax.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.umax.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umax.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.umax.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -1066,38 +1066,38 @@ define void @umin() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPEBASED-LABEL: 'umin'
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t0 = call <2 x i8> @llvm.vp.umin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t2 = call <4 x i8> @llvm.vp.umin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t4 = call <8 x i8> @llvm.vp.umin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %t6 = call <16 x i8> @llvm.vp.umin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t8 = call <2 x i16> @llvm.vp.umin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t10 = call <4 x i16> @llvm.vp.umin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %t12 = call <8 x i16> @llvm.vp.umin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t14 = call <16 x i16> @llvm.vp.umin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t16 = call <2 x i32> @llvm.vp.umin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %t18 = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t20 = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t22 = call <16 x i32> @llvm.vp.umin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %t24 = call <2 x i64> @llvm.vp.umin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %t26 = call <4 x i64> @llvm.vp.umin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %t28 = call <8 x i64> @llvm.vp.umin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 172 for instruction: %t30 = call <16 x i64> @llvm.vp.umin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.umin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.umin.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.umin.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.umin.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.umin.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.umin.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.umin.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.umin.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.umin.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.umin.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.umin.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.umin.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.umin.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.umin.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.umin.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.umin.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.umin.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
diff --git a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
index 28d6b59e2b7f02..058aaea46fd090 100644
--- a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
+++ b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
@@ -973,23 +973,14 @@ define <vscale x 1 x i64> @xor_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @smin_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @smin_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = call i64 @llvm.smin.i64(i64 [[Y:%.*]], i64 42)
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @smin_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @smin_nxv1i64_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1016,23 +1007,14 @@ define <vscale x 1 x i64> @smin_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
 }
 
 define <vscale x 1 x i64> @smax_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @smax_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = call i64 @llvm.smax.i64(i64 [[Y:%.*]], i64 42)
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @smax_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @smax_nxv1i64_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.smax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1059,23 +1041,14 @@ define <vscale x 1 x i64> @smax_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
 }
 
 define <vscale x 1 x i64> @umin_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @umin_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = call i64 @llvm.umin.i64(i64 [[Y:%.*]], i64 42)
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @umin_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @umin_nxv1i64_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umin.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1087,23 +1060,14 @@ define <vscale x 1 x i64> @umin_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 }
 
 define <vscale x 1 x i64> @umax_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @umax_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = call i64 @llvm.umax.i64(i64 [[Y:%.*]], i64 42)
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @umax_nxv1i64_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+; ALL-LABEL: @umax_nxv1i64_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.umax.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer