diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1107,11 +1107,24 @@
                                               TTI::TargetCostKind CostKind,
                                               TTI::OperandValueInfo OpInfo,
                                               const Instruction *I) {
+  EVT VT = TLI->getValueType(DL, Src, true);
+  // Type legalization can't handle structs
+  if (VT == MVT::Other)
+    return BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
+                                  CostKind, OpInfo, I);
   InstructionCost Cost = 0;
   if (Opcode == Instruction::Store && OpInfo.isConstant())
     Cost += getStoreImmCost(Src, OpInfo, CostKind);
-  return Cost + BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
-                                       CostKind, OpInfo, I);
+
+  std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Src);
+  if (!LT.second.isVector())
+    return Cost + BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
+                                         CostKind, OpInfo, I);
+  if (CostKind == TTI::TCK_CodeSize)
+    return Cost + BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
+                                         CostKind, OpInfo, I);
+  Cost += LT.first * getLMULCost(LT.second);
+  return Cost;
 }
 
 InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
diff --git a/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll b/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
--- a/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/masked_ldst.ll
@@ -19,7 +19,7 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = call <2 x float> @llvm.masked.load.v2f32.p0(ptr undef, i32 8, <2 x i1> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr undef, i32 8, <4 x i1> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = call <2 x double> @llvm.masked.load.v2f64.p0(ptr undef, i32 8, <2 x i1> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = call <4 x i64> @llvm.masked.load.v4i64.p0(ptr undef, i32 8, <4 x i1> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = call <4 x i64> @llvm.masked.load.v4i64.p0(ptr undef, i32 8, <4 x i1> undef, <4 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %v32f16 = call <32 x half> @llvm.masked.load.v32f16.p0(ptr undef, i32 8, <32 x i1> undef, <32 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
@@ -56,21 +56,21 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f16 = call <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x half> undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f16 = call <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x half> undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f16 = call <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0(ptr undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = call <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0(ptr undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0(ptr undef, i32 8, <vscale x 1 x i1> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0(ptr undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0(ptr undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
@@ -1,76 +1,146 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+experimental-zvfh -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=1 < %s | FileCheck %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+experimental-zvfh -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=1 < %s | FileCheck %s --check-prefix=THROUGHPUT
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+experimental-zvfh -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=1 < %s | FileCheck %s --check-prefix=SIZE
 ; Check that we don't crash querying costs when vectors are not enabled.
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64
+; RUN: opt -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output -mtriple=riscv64
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=riscv64
 
 define void @load(ptr %p) {
-; CHECK-LABEL: 'load'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = load i8, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = load <1 x i8>, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load <2 x i8>, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load <4 x i8>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = load <8 x i8>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <16 x i8>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = load <32 x i8>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = load <vscale x 1 x i8>, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <vscale x 2 x i8>, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <vscale x 4 x i8>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = load <vscale x 8 x i8>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = load <vscale x 16 x i8>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = load <vscale x 32 x i8>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load i16, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = load <1 x i16>, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = load <2 x i16>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = load <4 x i16>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <8 x i16>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <16 x i16>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <32 x i16>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = load <vscale x 1 x i16>, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = load <vscale x 2 x i16>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = load <vscale x 4 x i16>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = load <vscale x 8 x i16>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = load <vscale x 16 x i16>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = load <vscale x 32 x i16>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = load i32, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = load <1 x i32>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = load <2 x i32>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = load <4 x i32>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = load <8 x i32>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = load <16 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %33 = load <32 x i32>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = load <vscale x 1 x i32>, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = load <vscale x 2 x i32>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = load <vscale x 4 x i32>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = load <vscale x 8 x i32>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = load <vscale x 16 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %39 = load <vscale x 32 x i32>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %40 = load i64, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %41 = load <1 x i64>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %42 = load <2 x i64>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %43 = load <4 x i64>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %44 = load <8 x i64>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %45 = load <16 x i64>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %46 = load <32 x i64>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %47 = load <vscale x 1 x i64>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %48 = load <vscale x 2 x i64>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %49 = load <vscale x 4 x i64>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %50 = load <vscale x 8 x i64>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %51 = load <vscale x 16 x i64>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %52 = load <vscale x 32 x i64>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %53 = load ptr, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %54 = load <1 x ptr>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %55 = load <2 x ptr>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %56 = load <4 x ptr>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %57 = load <8 x ptr>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %58 = load <16 x ptr>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %59 = load <32 x ptr>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %60 = load <vscale x 1 x ptr>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %61 = load <vscale x 2 x ptr>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %62 = load <vscale x 4 x ptr>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %63 = load <vscale x 8 x ptr>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %64 = load <vscale x 16 x ptr>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %65 = load <vscale x 32 x ptr>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+; THROUGHPUT-LABEL: 'load'
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = load i8, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = load <1 x i8>, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load <2 x i8>, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load <4 x i8>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = load <8 x i8>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <16 x i8>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = load <32 x i8>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = load <vscale x 1 x i8>, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <vscale x 2 x i8>, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <vscale x 4 x i8>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = load <vscale x 8 x i8>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = load <vscale x 16 x i8>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = load <vscale x 32 x i8>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load i16, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = load <1 x i16>, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = load <2 x i16>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = load <4 x i16>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <8 x i16>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <16 x i16>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <32 x i16>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = load <vscale x 1 x i16>, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = load <vscale x 2 x i16>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = load <vscale x 4 x i16>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = load <vscale x 8 x i16>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %25 = load <vscale x 16 x i16>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %26 = load <vscale x 32 x i16>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = load i32, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = load <1 x i32>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = load <2 x i32>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = load <4 x i32>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = load <8 x i32>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = load <16 x i32>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %33 = load <32 x i32>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = load <vscale x 1 x i32>, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = load <vscale x 2 x i32>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %36 = load <vscale x 4 x i32>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %37 = load <vscale x 8 x i32>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %38 = load <vscale x 16 x i32>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %39 = load <vscale x 32 x i32>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %40 = load i64, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %41 = load <1 x i64>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %42 = load <2 x i64>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %43 = load <4 x i64>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %44 = load <8 x i64>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %45 = load <16 x i64>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %46 = load <32 x i64>, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %47 = load <vscale x 1 x i64>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %48 = load <vscale x 2 x i64>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %49 = load <vscale x 4 x i64>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %50 = load <vscale x 8 x i64>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %51 = load <vscale x 16 x i64>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %52 = load <vscale x 32 x i64>, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %53 = load ptr, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %54 = load <1 x ptr>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %55 = load <2 x ptr>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %56 = load <4 x ptr>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %57 = load <8 x ptr>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %58 = load <16 x ptr>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %59 = load <32 x ptr>, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %60 = load <vscale x 1 x ptr>, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %61 = load <vscale x 2 x ptr>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %62 = load <vscale x 4 x ptr>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %63 = load <vscale x 8 x ptr>, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %64 = load <vscale x 16 x ptr>, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %65 = load <vscale x 32 x ptr>, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SIZE-LABEL: 'load'
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = load i8, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = load <1 x i8>, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load <2 x i8>, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load <4 x i8>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = load <8 x i8>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <16 x i8>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = load <32 x i8>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = load <vscale x 1 x i8>, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <vscale x 2 x i8>, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <vscale x 4 x i8>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = load <vscale x 8 x i8>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = load <vscale x 16 x i8>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = load <vscale x 32 x i8>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load i16, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = load <1 x i16>, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = load <2 x i16>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = load <4 x i16>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <8 x i16>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <16 x i16>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <32 x i16>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = load <vscale x 1 x i16>, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = load <vscale x 2 x i16>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = load <vscale x 4 x i16>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = load <vscale x 8 x i16>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = load <vscale x 16 x i16>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = load <vscale x 32 x i16>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = load i32, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = load <1 x i32>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = load <2 x i32>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = load <4 x i32>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = load <8 x i32>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = load <16 x i32>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %33 = load <32 x i32>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = load <vscale x 1 x i32>, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = load <vscale x 2 x i32>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = load <vscale x 4 x i32>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = load <vscale x 8 x i32>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = load <vscale x 16 x i32>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %39 = load <vscale x 32 x i32>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %40 = load i64, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %41 = load <1 x i64>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %42 = load <2 x i64>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %43 = load <4 x i64>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %44 = load <8 x i64>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %45 = load <16 x i64>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %46 = load <32 x i64>, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %47 = load <vscale x 1 x i64>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %48 = load <vscale x 2 x i64>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %49 = load <vscale x 4 x i64>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %50 = load <vscale x 8 x i64>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %51 = load <vscale x 16 x i64>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %52 = load <vscale x 32 x i64>, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %53 = load ptr, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %54 = load <1 x ptr>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %55 = load <2 x ptr>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %56 = load <4 x ptr>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %57 = load <8 x ptr>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %58 = load <16 x ptr>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %59 = load <32 x ptr>, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %60 = load <vscale x 1 x ptr>, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %61 = load <vscale x 2 x ptr>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %62 = load <vscale x 4 x ptr>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %63 = load <vscale x 8 x ptr>, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %64 = load <vscale x 16 x ptr>, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %65 = load <vscale x 32 x ptr>, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   load i8, ptr %p
   load <1 x i8>, ptr %p
@@ -147,73 +217,141 @@
 }
 
 define void @store(ptr %p) {
-; CHECK-LABEL: 'store'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i8 undef, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i8> undef, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <32 x i8> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i8> undef, ptr %p, align 1
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i8> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 32 x i8> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 undef, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i16> undef, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i16> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i16> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i16> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i16> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <32 x i16> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i16> undef, ptr %p, align 2
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i16> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i16> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i16> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i16> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 32 x i16> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i32> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i32> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <16 x i32> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <32 x i32> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i32> undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i32> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i32> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i32> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i32> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i32> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 undef, ptr %p, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i64> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x i64> undef, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i64> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i64> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i64> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i64> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i64> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 32 x i64> undef, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store ptr undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x ptr> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x ptr> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x ptr> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x ptr> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x ptr> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x ptr> undef, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x ptr> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x ptr> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x ptr> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x ptr> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x ptr> undef, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 32 x ptr> undef, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+; THROUGHPUT-LABEL: 'store'
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i8 undef, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i8> undef, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <32 x i8> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i8> undef, ptr %p, align 1
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i8> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 32 x i8> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 undef, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i16> undef, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i16> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i16> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i16> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i16> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <32 x i16> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i16> undef, ptr %p, align 2
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i16> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i16> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 8 x i16> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 16 x i16> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 32 x i16> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i32> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i32> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <16 x i32> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <32 x i32> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i32> undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i32> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 4 x i32> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 8 x i32> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 16 x i32> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 32 x i32> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 undef, ptr %p, align 4
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i64> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x i64> undef, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i64> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 2 x i64> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 4 x i64> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 8 x i64> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x i64> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: store <vscale x 32 x i64> undef, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store ptr undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x ptr> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x ptr> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x ptr> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x ptr> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x ptr> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x ptr> undef, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x ptr> undef, ptr %p, align 8
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 2 x ptr> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 4 x ptr> undef, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 8 x ptr> undef, ptr %p, align 64
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x ptr> undef, ptr %p, align 128
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: store <vscale x 32 x ptr> undef, ptr %p, align 256
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SIZE-LABEL: 'store'
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i8 undef, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i8> undef, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <32 x i8> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i8> undef, ptr %p, align 1
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i8> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 32 x i8> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 undef, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i16> undef, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i16> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i16> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i16> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <16 x i16> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <32 x i16> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i16> undef, ptr %p, align 2
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i16> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i16> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i16> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i16> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 32 x i16> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i32> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i32> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <16 x i32> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <32 x i32> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i32> undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i32> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i32> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i32> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 16 x i32> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 32 x i32> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 undef, ptr %p, align 4
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i64> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x i64> undef, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x i64> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i64> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i64> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i64> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i64> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 32 x i64> undef, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store ptr undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x ptr> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x ptr> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x ptr> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x ptr> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x ptr> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <32 x ptr> undef, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 1 x ptr> undef, ptr %p, align 8
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x ptr> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x ptr> undef, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x ptr> undef, ptr %p, align 64
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x ptr> undef, ptr %p, align 128
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 32 x ptr> undef, ptr %p, align 256
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   store i8 undef, ptr %p
   store <1 x i8> undef, ptr %p
@@ -292,26 +430,43 @@
 ; For constants, have to account for cost of materializing the constant itself
 ; This test exercises a few interesting constant patterns at VLEN=128
 define void @store_of_constant(ptr %p) {
-; CHECK-LABEL: 'store_of_constant'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> poison, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> zeroinitializer, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> zeroinitializer, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <4 x i64> <i64 1, i64 1, i64 1, i64 1>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 4096, i32 4096, i32 4096, i32 4096>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 1, i32 2, i32 1>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 1, i32 1, i32 1>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 -2, i32 -3, i32 -4>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 4, i32 6, i32 8>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 0, i32 2, i32 1>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 256, i32 4096, i32 57, i32 1>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-
   ; poison and undef
+; THROUGHPUT-LABEL: 'store_of_constant'
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> poison, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> zeroinitializer, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> zeroinitializer, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <4 x i64> <i64 1, i64 1, i64 1, i64 1>, ptr %p, align 32
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 4096, i32 4096, i32 4096, i32 4096>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 1, i32 2, i32 1>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 1, i32 1, i32 1>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 -2, i32 -3, i32 -4>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 4, i32 6, i32 8>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 0, i32 2, i32 1>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 256, i32 4096, i32 57, i32 1>, ptr %p, align 16
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SIZE-LABEL: 'store_of_constant'
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> poison, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> zeroinitializer, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> zeroinitializer, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <4 x i64> <i64 1, i64 1, i64 1, i64 1>, ptr %p, align 32
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i32> <i32 4096, i32 4096, i32 4096, i32 4096>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 1, i32 2, i32 1>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 1, i32 1, i32 1>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 -2, i32 -3, i32 -4>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 2, i32 4, i32 6, i32 8>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 -1, i32 0, i32 2, i32 1>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <4 x i32> <i32 256, i32 4096, i32 57, i32 1>, ptr %p, align 16
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
   store <4 x i32> poison, ptr %p
   store <4 x i32> undef, ptr %p
 
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
--- a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
@@ -36,10 +36,10 @@
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -79,10 +79,10 @@
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -105,7 +105,7 @@
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::VRRC, 4 registers
 ; CHECK-NEXT:  LV: The target has 31 registers of RISCV::GPRRC register class
 ; CHECK-NEXT:  LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT:  LV: Loop cost is 23
+; CHECK-NEXT:  LV: Loop cost is 25
 ; CHECK-NEXT:  LV: IC is 2
 ; CHECK-NEXT:  LV: VF is vscale x 4
 ; CHECK-NEXT:  LV: Not Interleaving.
@@ -168,10 +168,10 @@
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -211,10 +211,10 @@
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
 ; CHECK-NEXT:  LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT:  LV: Found an estimated cost of 7 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT:  LV: Found an estimated cost of 8 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
 ; CHECK-NEXT:  LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -237,7 +237,7 @@
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::VRRC, 4 registers
 ; CHECK-NEXT:  LV: The target has 31 registers of RISCV::GPRRC register class
 ; CHECK-NEXT:  LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT:  LV: Loop cost is 23
+; CHECK-NEXT:  LV: Loop cost is 25
 ; CHECK-NEXT:  LV: IC is 2
 ; CHECK-NEXT:  LV: VF is vscale x 4
 ; CHECK-NEXT:  LV: Not Interleaving.