[Costmodel] Add "type-based-intrinsic-cost" cli option

This patch adds a command line flag to be able to test
the type based cost-model analysis for Intrinsics.

Differential Revision: https://reviews.llvm.org/D129109

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index f524d0a..da4410f 100644 (file)
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -130,7 +130,8 @@ class IntrinsicCostAttributes {
 public:
   IntrinsicCostAttributes(
       Intrinsic::ID Id, const CallBase &CI,
-      InstructionCost ScalarCost = InstructionCost::getInvalid());
+      InstructionCost ScalarCost = InstructionCost::getInvalid(),
+      bool TypeBasedOnly = false);
 
   IntrinsicCostAttributes(
       Intrinsic::ID Id, Type *RTy, ArrayRef<Type *> Tys,

diff --git a/llvm/lib/Analysis/CostModel.cpp b/llvm/lib/Analysis/CostModel.cpp
index 52e424a..3c162f6 100644 (file)
--- a/llvm/lib/Analysis/CostModel.cpp
+++ b/llvm/lib/Analysis/CostModel.cpp
@@ -25,6 +25,7 @@
 #include "llvm/Pass.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/IR/IntrinsicInst.h"
 using namespace llvm;
 
 static cl::opt<TargetTransformInfo::TargetCostKind> CostKind(
@@ -39,6 +40,9 @@ static cl::opt<TargetTransformInfo::TargetCostKind> CostKind(
                clEnumValN(TargetTransformInfo::TCK_SizeAndLatency,
                           "size-latency", "Code size and latency")));
 
+static cl::opt<bool> TypeBasedIntrinsicCost("type-based-intrinsic-cost",
+    cl::desc("Calculate intrinsics cost based only on argument types"),
+    cl::init(false));
 
 #define CM_NAME "cost-model"
 #define DEBUG_TYPE CM_NAME
@@ -103,7 +107,16 @@ void CostModelAnalysis::print(raw_ostream &OS, const Module*) const {
 
   for (BasicBlock &B : *F) {
     for (Instruction &Inst : B) {
-      InstructionCost Cost = TTI->getInstructionCost(&Inst, CostKind);
+      InstructionCost Cost;
+      if (TypeBasedIntrinsicCost && isa<IntrinsicInst>(&Inst)) {
+        auto *II = dyn_cast<IntrinsicInst>(&Inst);
+        IntrinsicCostAttributes ICA(II->getIntrinsicID(), *II,
+                                    InstructionCost::getInvalid(), true);
+        Cost = TTI->getIntrinsicInstrCost(ICA, CostKind);
+      }
+      else {
+        Cost = TTI->getInstructionCost(&Inst, CostKind);
+      }
       if (auto CostVal = Cost.getValue())
         OS << "Cost Model: Found an estimated cost of " << *CostVal;
       else
@@ -122,7 +135,16 @@ PreservedAnalyses CostModelPrinterPass::run(Function &F,
     for (Instruction &Inst : B) {
       // TODO: Use a pass parameter instead of cl::opt CostKind to determine
       // which cost kind to print.
-      InstructionCost Cost = TTI.getInstructionCost(&Inst, CostKind);
+      InstructionCost Cost;
+      if (TypeBasedIntrinsicCost && isa<IntrinsicInst>(&Inst)) {
+        auto *II = dyn_cast<IntrinsicInst>(&Inst);
+        IntrinsicCostAttributes ICA(II->getIntrinsicID(), *II,
+                                    InstructionCost::getInvalid(), true);
+        Cost = TTI.getIntrinsicInstrCost(ICA, CostKind);
+      }
+      else {
+        Cost = TTI.getInstructionCost(&Inst, CostKind);
+      }
       if (auto CostVal = Cost.getValue())
         OS << "Cost Model: Found an estimated cost of " << *CostVal;
       else

diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index e31a038..cfa6e3a 100644 (file)
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -58,14 +58,16 @@ bool HardwareLoopInfo::canAnalyze(LoopInfo &LI) {
 }
 
 IntrinsicCostAttributes::IntrinsicCostAttributes(
-    Intrinsic::ID Id, const CallBase &CI, InstructionCost ScalarizationCost)
+    Intrinsic::ID Id, const CallBase &CI, InstructionCost ScalarizationCost,
+    bool TypeBasedOnly)
     : II(dyn_cast<IntrinsicInst>(&CI)), RetTy(CI.getType()), IID(Id),
       ScalarizationCost(ScalarizationCost) {
 
   if (const auto *FPMO = dyn_cast<FPMathOperator>(&CI))
     FMF = FPMO->getFastMathFlags();
 
-  Arguments.insert(Arguments.begin(), CI.arg_begin(), CI.arg_end());
+  if (!TypeBasedOnly)
+    Arguments.insert(Arguments.begin(), CI.arg_begin(), CI.arg_end());
   FunctionType *FTy = CI.getCalledFunction()->getFunctionType();
   ParamTys.insert(ParamTys.begin(), FTy->param_begin(), FTy->param_end());
 }

diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 4482d31..0207930 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes='print<cost-model>' 2>&1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s
+; RUN: opt < %s -passes='print<cost-model>' 2>&1 -type-based-intrinsic-cost -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=TYPE_BASED_ONLY
 
 define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
 ; CHECK-LABEL: 'vector_insert_extract'
@@ -9,6 +10,13 @@ define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
   %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
   %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
@@ -49,6 +57,33 @@ define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'reductions'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
   %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
   %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
@@ -86,6 +121,13 @@ define void @strict_fp_reductions(<vscale x 4 x float> %v0, <vscale x 4 x double
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'strict_fp_reductions'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.0, <vscale x 4 x float> %v0)
   %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.0, <vscale x 4 x double> %v1)
   %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.0, <vscale x 4 x float> %v0)
@@ -128,6 +170,11 @@ define void  @count_zeroes(<vscale x 4 x i32> %A) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'count_zeroes'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
   %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
   ret void
@@ -167,6 +214,36 @@ define void @vector_reverse() #0 {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'vector_reverse'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
 
   %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
   %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
@@ -238,6 +315,18 @@ define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'unsupported_fp_ops'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
 
   %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
   %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
@@ -256,6 +345,10 @@ define void @powi(<vscale x 4 x float> %vec) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'powi'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
   ret void
 }
@@ -328,6 +421,63 @@ define void @vector_splice() #0 {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'vector_splice'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
 
   %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
   %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
@@ -441,6 +591,29 @@ define void @get_lane_mask() #0 {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'get_lane_mask'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
   %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
   %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
@@ -478,6 +651,13 @@ define void @fshr() #0 {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'fshr'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
   call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
   call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
@@ -493,6 +673,13 @@ define void @fshl() #0 {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
+; TYPE_BASED_ONLY-LABEL: 'fshl'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
   call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
   call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
   call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
@@ -500,6 +687,114 @@ define void @fshl() #0 {
   ret void
 }
 
+define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x i32*> %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru) {
+; CHECK-LABEL: 'masked_gather_nxv4i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 4 x i32> %res
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_gather_nxv4i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 4 x i32> %res
+;
+  %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i32> @masked_gather_nxv8i32(<vscale x 8 x i32*> %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru) {
+; CHECK-LABEL: 'masked_gather_nxv8i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %res
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_gather_nxv8i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %res
+;
+  %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+  ret <vscale x 8 x i32> %res
+}
+
+define <4 x i32> @masked_gather_v4i32(<4 x i32*> %ld, <4 x i1> %masks, <4 x i32> %passthru) {
+; CHECK-LABEL: 'masked_gather_v4i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_gather_v4i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+  %res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+  ret <4 x i32> %res
+}
+
+define <1 x i128> @masked_gather_v1i128(<1 x i128*> %ld, <1 x i1> %masks, <1 x i128> %passthru) {
+; CHECK-LABEL: 'masked_gather_v1i128'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <1 x i128> %res
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_gather_v1i128'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <1 x i128> %res
+;
+  %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+  ret <1 x i128> %res
+}
+
+define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, <vscale x 4 x i1> %masks) {
+; CHECK-LABEL: 'masked_scatter_nxv4i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_scatter_nxv4i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+
+  call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+  ret void
+}
+
+define void @masked_scatter_nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, <vscale x 8 x i1> %masks) {
+; CHECK-LABEL: 'masked_scatter_nxv8i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_scatter_nxv8i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+
+  call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+  ret void
+}
+
+define void @masked_scatter_v4i32(<4 x i32> %data, <4 x i32*> %ptrs, <4 x i1> %masks) {
+; CHECK-LABEL: 'masked_scatter_v4i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_scatter_v4i32'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+
+  call void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
+  ret void
+}
+
+define void @masked_scatter_v1i128(<1 x i128> %data, <1 x i128*> %ptrs, <1 x i1> %masks) {
+; CHECK-LABEL: 'masked_scatter_v1i128'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPE_BASED_ONLY-LABEL: 'masked_scatter_v1i128'
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+
+  call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+  ret void
+}
+
 declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64, i64)
 declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64, i64)
 declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64, i64)
@@ -528,5 +823,13 @@ declare <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x
 declare <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
 declare <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
 declare <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+declare <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 %align, <4 x i1> %masks, <4 x i32> %passthru)
+declare <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*>, i32, <1 x i1>, <1 x i128>)
+declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks)
+declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks)
+declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 %align, <4 x i1> %masks)
+declare void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 %align, <1 x i1> %masks)
 
 attributes #0 = { "target-features"="+sve,+bf16" }