[llvm] cdf1833 - [CostModel] Add -cost-kind=all costmodel output (#130490)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 11 03:55:41 PDT 2025
Author: David Green
Date: 2025-03-11T10:55:37Z
New Revision: cdf18331eb51ba5953182a2fb9248640f43a7d13
URL: https://github.com/llvm/llvm-project/commit/cdf18331eb51ba5953182a2fb9248640f43a7d13
DIFF: https://github.com/llvm/llvm-project/commit/cdf18331eb51ba5953182a2fb9248640f43a7d13.diff
LOG: [CostModel] Add -cost-kind=all costmodel output (#130490)
In order to make the different cost model kinds easier to test, and to
manage the complexity of all the different variants, this patch
introduces a -cost-kind=all option that will print the output of all
cost model kinds. It feel especially helpful for tests that already have
multiple run lines (with / without +fullfp16 for example).
It currently produces the output:
```
Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fadd half undef, undef
```
The output is collapsed into a single value if all costs are the same.
Invalid costs print "Invalid" via the normal InstructionCost printing.
Two test files are updated to show some examples with
-intrinsic-cost-strategy=type-based-intrinsic-cost and Invalid costs.
Once we have something we are happy with I will try to use this to
update more tests, as in b021bdbb3997ef6dd13980dc44f24754f15f3652 but
for more variants.
Added:
Modified:
llvm/lib/Analysis/CostModel.cpp
llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/lib/Analysis/CostModel.cpp b/llvm/lib/Analysis/CostModel.cpp
index b863bf77c6ddd..cec0fb6b98dea 100644
--- a/llvm/lib/Analysis/CostModel.cpp
+++ b/llvm/lib/Analysis/CostModel.cpp
@@ -28,17 +28,25 @@
using namespace llvm;
-static cl::opt<TargetTransformInfo::TargetCostKind> CostKind(
+enum class OutputCostKind {
+ RecipThroughput,
+ Latency,
+ CodeSize,
+ SizeAndLatency,
+ All,
+};
+
+static cl::opt<OutputCostKind> CostKind(
"cost-kind", cl::desc("Target cost kind"),
- cl::init(TargetTransformInfo::TCK_RecipThroughput),
- cl::values(clEnumValN(TargetTransformInfo::TCK_RecipThroughput,
- "throughput", "Reciprocal throughput"),
- clEnumValN(TargetTransformInfo::TCK_Latency,
- "latency", "Instruction latency"),
- clEnumValN(TargetTransformInfo::TCK_CodeSize,
- "code-size", "Code size"),
- clEnumValN(TargetTransformInfo::TCK_SizeAndLatency,
- "size-latency", "Code size and latency")));
+ cl::init(OutputCostKind::RecipThroughput),
+ cl::values(clEnumValN(OutputCostKind::RecipThroughput, "throughput",
+ "Reciprocal throughput"),
+ clEnumValN(OutputCostKind::Latency, "latency",
+ "Instruction latency"),
+ clEnumValN(OutputCostKind::CodeSize, "code-size", "Code size"),
+ clEnumValN(OutputCostKind::SizeAndLatency, "size-latency",
+ "Code size and latency"),
+ clEnumValN(OutputCostKind::All, "all", "Print all cost kinds")));
enum class IntrinsicCostStrategy {
InstructionCost,
@@ -79,6 +87,22 @@ static InstructionCost getCost(Instruction &Inst, TTI::TargetCostKind CostKind,
return TTI.getInstructionCost(&Inst, CostKind);
}
+static TTI::TargetCostKind
+OutputCostKindToTargetCostKind(OutputCostKind CostKind) {
+ switch (CostKind) {
+ case OutputCostKind::RecipThroughput:
+ return TTI::TCK_RecipThroughput;
+ case OutputCostKind::Latency:
+ return TTI::TCK_Latency;
+ case OutputCostKind::CodeSize:
+ return TTI::TCK_CodeSize;
+ case OutputCostKind::SizeAndLatency:
+ return TTI::TCK_SizeAndLatency;
+ default:
+ llvm_unreachable("Unexpected OutputCostKind!");
+ };
+}
+
PreservedAnalyses CostModelPrinterPass::run(Function &F,
FunctionAnalysisManager &AM) {
auto &TTI = AM.getResult<TargetIRAnalysis>(F);
@@ -86,15 +110,30 @@ PreservedAnalyses CostModelPrinterPass::run(Function &F,
OS << "Printing analysis 'Cost Model Analysis' for function '" << F.getName() << "':\n";
for (BasicBlock &B : F) {
for (Instruction &Inst : B) {
- // TODO: Use a pass parameter instead of cl::opt CostKind to determine
- // which cost kind to print.
- InstructionCost Cost = getCost(Inst, CostKind, TTI, TLI);
- if (auto CostVal = Cost.getValue())
- OS << "Cost Model: Found an estimated cost of " << *CostVal;
- else
- OS << "Cost Model: Invalid cost";
-
- OS << " for instruction: " << Inst << "\n";
+ OS << "Cost Model: ";
+ if (CostKind == OutputCostKind::All) {
+ OS << "Found costs of ";
+ InstructionCost RThru =
+ getCost(Inst, TTI::TCK_RecipThroughput, TTI, TLI);
+ InstructionCost CodeSize = getCost(Inst, TTI::TCK_CodeSize, TTI, TLI);
+ InstructionCost Lat = getCost(Inst, TTI::TCK_Latency, TTI, TLI);
+ InstructionCost SizeLat =
+ getCost(Inst, TTI::TCK_SizeAndLatency, TTI, TLI);
+ if (RThru == CodeSize && RThru == Lat && RThru == SizeLat)
+ OS << RThru;
+ else
+ OS << "RThru:" << RThru << " CodeSize:" << CodeSize << " Lat:" << Lat
+ << " SizeLat:" << SizeLat;
+ OS << " for: " << Inst << "\n";
+ } else {
+ InstructionCost Cost =
+ getCost(Inst, OutputCostKindToTargetCostKind(CostKind), TTI, TLI);
+ if (auto CostVal = Cost.getValue())
+ OS << "Found an estimated cost of " << *CostVal;
+ else
+ OS << "Invalid cost";
+ OS << " for instruction: " << Inst << "\n";
+ }
}
}
return PreservedAnalyses::all();
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
index 3e9d2259cf5f4..de6b918afe943 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
@@ -1,37 +1,22 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -enable-no-nans-fp-math -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s --check-prefix=RECIP
-; RUN: opt < %s -enable-no-nans-fp-math -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s --check-prefix=SIZE
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define i32 @fadd(i32 %arg) {
-; RECIP-LABEL: 'fadd'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fadd half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fadd <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fadd <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fadd <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fadd <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fadd'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fadd half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fadd <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fadd <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fadd <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fadd float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fadd <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fadd <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fadd double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fadd <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fadd <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fadd'
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fadd half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fadd <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fadd <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fadd <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fadd float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fadd <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fadd <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fadd <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fadd double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fadd <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fadd <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fadd half undef, undef
%V4F16 = fadd <4 x half> undef, undef
@@ -51,33 +36,19 @@ define i32 @fadd(i32 %arg) {
}
define i32 @fsub(i32 %arg) {
-; RECIP-LABEL: 'fsub'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fsub half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fsub <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fsub <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fsub <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fsub <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fsub'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fsub half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fsub <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fsub <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fsub <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fsub <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fsub'
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fsub <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fsub float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fsub <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fsub <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fsub <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fsub double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fsub <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fsub <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fsub half undef, undef
%V4F16 = fsub <4 x half> undef, undef
@@ -97,31 +68,18 @@ define i32 @fsub(i32 %arg) {
}
define i32 @fneg_idiom(i32 %arg) {
-; RECIP-LABEL: 'fneg_idiom'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fsub half 0xH8000, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fsub <2 x float> splat (float -0.000000e+00), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> splat (float -0.000000e+00), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <8 x float> splat (float -0.000000e+00), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> splat (double -0.000000e+00), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fsub <4 x double> splat (double -0.000000e+00), undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fneg_idiom'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fsub half 0xH8000, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fsub float -0.000000e+00, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fsub <2 x float> splat (float -0.000000e+00), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <4 x float> splat (float -0.000000e+00), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fsub <8 x float> splat (float -0.000000e+00), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fsub double -0.000000e+00, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fsub <2 x double> splat (double -0.000000e+00), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fsub <4 x double> splat (double -0.000000e+00), undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fneg_idiom'
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half 0xH8000, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fsub float -0.000000e+00, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fsub <2 x float> splat (float -0.000000e+00), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fsub <4 x float> splat (float -0.000000e+00), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fsub <8 x float> splat (float -0.000000e+00), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fsub double -0.000000e+00, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fsub <2 x double> splat (double -0.000000e+00), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fsub <4 x double> splat (double -0.000000e+00), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fsub half -0.0, undef
%V4F16 = fsub <4 x half> <half -0.0, half -0.0, half -0.0, half -0.0>, undef
@@ -140,35 +98,20 @@ define i32 @fneg_idiom(i32 %arg) {
}
define i32 @fneg(i32 %arg) {
-; RECIP-LABEL: 'fneg'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fneg half undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fneg <16 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fneg <8 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fneg <4 x double> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fneg'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fneg half undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fneg <16 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fneg <8 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fneg <4 x double> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fneg'
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fneg <2 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fneg <4 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fneg <8 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fneg double undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fneg <2 x double> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fneg half undef
%V2F16 = fneg <2 x half> undef
@@ -189,59 +132,32 @@ define i32 @fneg(i32 %arg) {
}
define i32 @fmulfneg(i32 %arg) {
-; RECIP-LABEL: 'fmulfneg'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F16 = fneg half undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16M = fmul half %F16, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16M = fmul <2 x half> %V2F16, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16M = fmul <4 x half> %V4F16, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16M = fmul <8 x half> %V8F16, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fneg <16 x half> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16M = fmul <16 x half> %V16F16, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F32 = fneg float undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32M = fmul float %F32, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32M = fmul <2 x float> %V2F32, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32M = fmul <4 x float> %V4F32, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fneg <8 x float> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32M = fmul <8 x float> %V8F32, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F64 = fneg double undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64M = fmul double %F64, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64M = fmul <2 x double> %V2F64, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fneg <4 x double> undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64M = fmul <4 x double> %V4F64, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fmulfneg'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fneg half undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16M = fmul half %F16, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16M = fmul <2 x half> %V2F16, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16M = fmul <4 x half> %V4F16, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16M = fmul <8 x half> %V8F16, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fneg <16 x half> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16M = fmul <16 x half> %V16F16, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32M = fmul float %F32, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32M = fmul <2 x float> %V2F32, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32M = fmul <4 x float> %V4F32, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fneg <8 x float> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32M = fmul <8 x float> %V8F32, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64M = fmul double %F64, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64M = fmul <2 x double> %V2F64, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fneg <4 x double> undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64M = fmul <4 x double> %V4F64, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fmulfneg'
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half %F16, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> %V2F16, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> %V4F16, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> %V8F16, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> %V16F16, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32M = fmul float %F32, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fneg <2 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32M = fmul <2 x float> %V2F32, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fneg <4 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32M = fmul <4 x float> %V4F32, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fneg <8 x float> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32M = fmul <8 x float> %V8F32, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fneg double undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F64M = fmul double %F64, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fneg <2 x double> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64M = fmul <2 x double> %V2F64, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64M = fmul <4 x double> %V4F64, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fneg half undef
%F16M = fmul half %F16, undef
@@ -274,59 +190,32 @@ define i32 @fmulfneg(i32 %arg) {
}
define i32 @fnegfmul(i32 %arg) {
-; RECIP-LABEL: 'fnegfmul'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16M = fmul half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F16 = fneg half %F16M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16M = fmul <2 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> %V2F16M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16M = fmul <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> %V4F16M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16M = fmul <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> %V8F16M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16M = fmul <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fneg <16 x half> %V16F16M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32M = fmul float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F32 = fneg float %F32M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32M = fmul <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> %V2F32M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32M = fmul <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> %V4F32M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32M = fmul <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fneg <8 x float> %V8F32M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64M = fmul double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F64 = fneg double %F64M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64M = fmul <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> %V2F64M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64M = fmul <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fneg <4 x double> %V4F64M
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fnegfmul'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16M = fmul half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fneg half %F16M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16M = fmul <2 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fneg <2 x half> %V2F16M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16M = fmul <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fneg <4 x half> %V4F16M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16M = fmul <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fneg <8 x half> %V8F16M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16M = fmul <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fneg <16 x half> %V16F16M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32M = fmul float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fneg float %F32M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32M = fmul <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fneg <2 x float> %V2F32M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32M = fmul <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fneg <4 x float> %V4F32M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32M = fmul <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fneg <8 x float> %V8F32M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64M = fmul double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fneg double %F64M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64M = fmul <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fneg <2 x double> %V2F64M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64M = fmul <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fneg <4 x double> %V4F64M
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fnegfmul'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half %F16M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> %V2F16M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> %V4F16M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> %V8F16M
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> %V16F16M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32M = fmul float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float %F32M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32M = fmul <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fneg <2 x float> %V2F32M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32M = fmul <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fneg <4 x float> %V4F32M
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32M = fmul <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fneg <8 x float> %V8F32M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F64M = fmul double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fneg double %F64M
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64M = fmul <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fneg <2 x double> %V2F64M
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64M = fmul <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> %V4F64M
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16M = fmul half undef, undef
%F16 = fneg half %F16M
@@ -359,33 +248,19 @@ define i32 @fnegfmul(i32 %arg) {
}
define i32 @fmul(i32 %arg) {
-; RECIP-LABEL: 'fmul'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fmul float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fmul'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = fmul half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fmul <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fmul <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = fmul <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = fmul float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fmul <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fmul <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = fmul <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = fmul double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fmul <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = fmul <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fmul'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fmul half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fmul <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fmul <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fmul <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fmul float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fmul <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fmul <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V8F32 = fmul <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fmul double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fmul <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fmul <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fmul half undef, undef
%V4F16 = fmul <4 x half> undef, undef
@@ -405,33 +280,19 @@ define i32 @fmul(i32 %arg) {
}
define i32 @fdiv(i32 %arg) {
-; RECIP-LABEL: 'fdiv'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fdiv float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fdiv double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fdiv <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fdiv'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F16 = fdiv half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F16 = fdiv <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fdiv <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F32 = fdiv float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = fdiv <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = fdiv <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F64 = fdiv double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fdiv <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fdiv'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = fdiv half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = fdiv <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = fdiv <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = fdiv <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F32 = fdiv float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V2F32 = fdiv <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4F32 = fdiv <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = fdiv <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F64 = fdiv double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V2F64 = fdiv <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = fdiv <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = fdiv half undef, undef
%V4F16 = fdiv <4 x half> undef, undef
@@ -451,33 +312,19 @@ define i32 @fdiv(i32 %arg) {
}
define i32 @frem(i32 %arg) {
-; RECIP-LABEL: 'frem'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F16 = frem half undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V4F16 = frem <4 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %V8F16 = frem <8 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16F16 = frem <16 x half> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F32 = frem float undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F32 = frem <2 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V4F32 = frem <4 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8F32 = frem <8 x float> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %F64 = frem double undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2F64 = frem <2 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V4F64 = frem <4 x double> undef, undef
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'frem'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F16 = frem half undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F16 = frem <4 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = frem <8 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = frem <16 x half> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F32 = frem float undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = frem <2 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = frem <4 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = frem <8 x float> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F64 = frem double undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = frem <2 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = frem <4 x double> undef, undef
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'frem'
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = frem half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:52 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = frem <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:108 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = frem <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:216 CodeSize:4 Lat:4 SizeLat:4 for: %V16F16 = frem <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F32 = frem float undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V2F32 = frem <2 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:52 CodeSize:4 Lat:4 SizeLat:4 for: %V4F32 = frem <4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:104 CodeSize:4 Lat:4 SizeLat:4 for: %V8F32 = frem <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F64 = frem double undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V2F64 = frem <2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:48 CodeSize:4 Lat:4 SizeLat:4 for: %V4F64 = frem <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = frem half undef, undef
%V4F16 = frem <4 x half> undef, undef
@@ -497,33 +344,19 @@ define i32 @frem(i32 %arg) {
}
define i32 @fsqrt(i32 %arg) {
-; RECIP-LABEL: 'fsqrt'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.sqrt.f16(half undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fsqrt'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.sqrt.f16(half undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fsqrt'
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.sqrt.f16(half undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.sqrt.f32(float undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.sqrt.f64(double undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = call half @llvm.sqrt.f16(half undef)
%V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
@@ -543,33 +376,19 @@ define i32 @fsqrt(i32 %arg) {
}
define i32 @fabs(i32 %arg) {
-; RECIP-LABEL: 'fabs'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.fabs.f16(half undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fabs'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.fabs.f16(half undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fabs.f32(float undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fabs.f64(double undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fabs'
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fabs.f16(half undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fabs.f32(float undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fabs.f64(double undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = call half @llvm.fabs.f16(half undef)
%V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
@@ -589,33 +408,19 @@ define i32 @fabs(i32 %arg) {
}
define i32 @fcopysign(i32 %arg) {
-; RECIP-LABEL: 'fcopysign'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = call half @llvm.copysign.f16(half undef, half undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fcopysign'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = call half @llvm.copysign.f16(half undef, half undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fcopysign'
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %F16 = call half @llvm.copysign.f16(half undef, half undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = call half @llvm.copysign.f16(half undef, half undef)
%V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
@@ -635,33 +440,19 @@ define i32 @fcopysign(i32 %arg) {
}
define i32 @fma(i32 %arg) {
-; RECIP-LABEL: 'fma'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
-;
-; SIZE-LABEL: 'fma'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+; CHECK-LABEL: 'fma'
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
;
%F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
%V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index f38d81a85fe63..09fd1de99d6c1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -1,31 +1,31 @@
; 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 --check-prefix=CHECK-VSCALE-1
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -mcpu=neoverse-v1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=CHECK-VSCALE-2
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -intrinsic-cost-strategy=type-based-intrinsic-cost -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=TYPE_BASED_ONLY
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=CHECK-VSCALE-1
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -mcpu=neoverse-v1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=CHECK-VSCALE-2
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -intrinsic-cost-strategy=type-based-intrinsic-cost -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=TYPE_BASED_ONLY
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 54 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 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)
-; CHECK-VSCALE-1-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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 54 for: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 54 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %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-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 54 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 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)
-; CHECK-VSCALE-2-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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 54 for: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 54 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %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-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %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: Found costs of Invalid for: %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: Found costs of Invalid for: %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: Found costs of Invalid for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -40,40 +40,40 @@ declare <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x
define void @vector_insert_extract_idxzero_128b() #1 {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_128b'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 42 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_128b'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 42 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_128b'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> undef, i64 0)
%extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> undef, i64 0)
@@ -97,40 +97,40 @@ declare <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x
define void @vector_insert_extract_idxzero_256b() #2 {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_256b'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 42 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_256b'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 42 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_256b'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> undef, <vscale x 2 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> undef, <2 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> undef, <vscale x 2 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> undef, i64 0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> undef, <16 x i16> undef, i64 0)
%extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nx4f32(<vscale x 4 x float> undef, i64 0)
@@ -148,121 +148,121 @@ declare <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float>, i64
define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale x 4 x float> %v2, <vscale x 4 x double> %v3) {
; CHECK-VSCALE-1-LABEL: 'reductions'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'reductions'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'reductions'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
-; 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_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
-; 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: Invalid cost for instruction: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
-; 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: Invalid cost for instruction: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
-; 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: Invalid cost for instruction: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
-; 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: Invalid cost for instruction: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
-; 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 3 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
-; 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 3 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
-; 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 3 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
-; 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 3 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
-; 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 3 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: Invalid cost for instruction: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
-; 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: Invalid cost for instruction: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
-; 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %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 costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %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 costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
%add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
@@ -307,25 +307,25 @@ define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale
define void @strict_fp_reductions(<vscale x 4 x float> %v0, <vscale x 4 x double> %v1) {
; CHECK-VSCALE-1-LABEL: 'strict_fp_reductions'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'strict_fp_reductions'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:24 SizeLat:8 for: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:24 SizeLat:8 for: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'strict_fp_reductions'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 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 4 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %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 costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %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: Found costs of Invalid for: %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: Found costs of Invalid for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -365,19 +365,19 @@ declare double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double>)
define void @count_zeroes(<vscale x 4 x i32> %A) {
; CHECK-VSCALE-1-LABEL: 'count_zeroes'
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'count_zeroes'
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 2 for: %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 costs of 2 for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -389,94 +389,94 @@ declare <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32>, i1)
define void @vector_reverse() #0 {
; CHECK-VSCALE-1-LABEL: 'vector_reverse'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_reverse'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
@@ -538,40 +538,40 @@ declare <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1>)
define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
; CHECK-VSCALE-1-LABEL: 'unsupported_fp_ops'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'unsupported_fp_ops'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %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: Found costs of Invalid for: %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: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
@@ -588,16 +588,16 @@ define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
define void @powi(<vscale x 4 x float> %vec) {
; CHECK-VSCALE-1-LABEL: 'powi'
-; CHECK-VSCALE-1-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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:14 CodeSize:7 Lat:21 SizeLat:7 for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'powi'
-; CHECK-VSCALE-2-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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:14 CodeSize:7 Lat:21 SizeLat:7 for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
ret void
@@ -615,196 +615,196 @@ declare <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float>)
define void @vector_splice() #0 {
; CHECK-VSCALE-1-LABEL: 'vector_splice'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 6 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_splice'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 2 for: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 3 for: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 6 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.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.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.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.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.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.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_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.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.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_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.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.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.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.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_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.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.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.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_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.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.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_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.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.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.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.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.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.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.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.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_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i64_neg = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
@@ -912,73 +912,73 @@ declare <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double>,
define void @get_lane_mask() #0 {
; CHECK-VSCALE-1-LABEL: 'get_lane_mask'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'get_lane_mask'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'get_lane_mask'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 1 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: Found an estimated cost of 48 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: Found an estimated cost of 6 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 32 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 16 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 8 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 4 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 32 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 16 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 8 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 4 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 48 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 6 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of 1 for: %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: Found costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %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: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %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 costs of 32 for: %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 costs of 16 for: %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 costs of 8 for: %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 costs of 4 for: %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 costs of 32 for: %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 costs of 16 for: %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 costs of 8 for: %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 costs of 4 for: %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 costs of RThru:48 CodeSize:33 Lat:33 SizeLat:33 for: %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 costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -1011,25 +1011,25 @@ define void @get_lane_mask() #0 {
define void @fshr() #0 {
; CHECK-VSCALE-1-LABEL: 'fshr'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'fshr'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshr'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 7 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: Found an estimated cost of 7 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: Found an estimated cost of 7 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: Found an estimated cost of 7 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %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: Found costs of 7 for: %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: Found costs of 7 for: %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: Found costs of 7 for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -1040,25 +1040,25 @@ define void @fshr() #0 {
define void @fshl() #0 {
; CHECK-VSCALE-1-LABEL: 'fshl'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 5 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-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 5 for: %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-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'fshl'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 5 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-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 5 for: %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-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshl'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 7 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: Found an estimated cost of 7 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: Found an estimated cost of 7 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: Found an estimated cost of 7 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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 7 for: %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: Found costs of 7 for: %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: Found costs of 7 for: %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: Found costs of 7 for: %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 costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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)
@@ -1069,16 +1069,16 @@ define void @fshl() #0 {
define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x ptr> %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_nxv4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 4 x i32> %res
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 40 for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 4 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_nxv4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 4 x i32> %res
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 80 for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.nxv4p0(<vscale x 4 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 4 x i32> %res
;
%res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
ret <vscale x 4 x i32> %res
@@ -1086,16 +1086,16 @@ define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x ptr> %ld, <vscale
define <vscale x 8 x i32> @masked_gather_nxv8i32(<vscale x 8 x ptr> %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_nxv8i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %res
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 80 for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 8 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_nxv8i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %res
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 160 for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.nxv8p0(<vscale x 8 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 8 x i32> %res
;
%res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
ret <vscale x 8 x i32> %res
@@ -1103,16 +1103,16 @@ define <vscale x 8 x i32> @masked_gather_nxv8i32(<vscale x 8 x ptr> %ld, <vscale
define <4 x i32> @masked_gather_v4i32(<4 x ptr> %ld, <4 x i1> %masks, <4 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_v4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:28 CodeSize:32 Lat:32 SizeLat:32 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_v4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:28 CodeSize:32 Lat:32 SizeLat:32 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
; TYPE_BASED_ONLY-LABEL: 'masked_gather_v4i32'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 36 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
%res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
ret <4 x i32> %res
@@ -1120,16 +1120,16 @@ define <4 x i32> @masked_gather_v4i32(<4 x ptr> %ld, <4 x i1> %masks, <4 x i32>
define <1 x i128> @masked_gather_v1i128(<1 x ptr> %ld, <1 x i1> %masks, <1 x i128> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_v1i128'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <1 x i128> %res
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:9 Lat:8 SizeLat:9 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <1 x i128> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_v1i128'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <1 x i128> %res
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:9 Lat:8 SizeLat:9 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.v1p0(<1 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <1 x i128> %res
;
%res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
ret <1 x i128> %res
@@ -1137,16 +1137,16 @@ define <1 x i128> @masked_gather_v1i128(<1 x ptr> %ld, <1 x i1> %masks, <1 x i12
define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_nxv4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 40 for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_nxv4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 80 for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
@@ -1155,16 +1155,16 @@ define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr>
define void @masked_scatter_nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_nxv8i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 80 for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_nxv8i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 160 for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %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
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
@@ -1173,16 +1173,16 @@ define void @masked_scatter_nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr>
define void @masked_scatter_v4i32(<4 x i32> %data, <4 x ptr> %ptrs, <4 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_v4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:28 CodeSize:32 Lat:32 SizeLat:32 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_v4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:28 CodeSize:32 Lat:32 SizeLat:32 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 28 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
@@ -1191,16 +1191,16 @@ define void @masked_scatter_v4i32(<4 x i32> %data, <4 x ptr> %ptrs, <4 x i1> %ma
define void @masked_scatter_v1i128(<1 x i128> %data, <1 x ptr> %ptrs, <1 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_v1i128'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:8 CodeSize:9 Lat:8 SizeLat:9 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_v1i128'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:8 CodeSize:9 Lat:8 SizeLat:9 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: 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.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 1 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
@@ -1209,16 +1209,16 @@ define void @masked_scatter_v1i128(<1 x i128> %data, <1 x ptr> %ptrs, <1 x i1> %
define void @histogram_nxv2i64(<vscale x 2 x ptr> %buckets, <vscale x 2 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv2i64'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv2i64'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv2i64'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
ret void
@@ -1226,16 +1226,16 @@ define void @histogram_nxv2i64(<vscale x 2 x ptr> %buckets, <vscale x 2 x i1> %m
define void @histogram_nxv4i32(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i32'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
ret void
@@ -1243,16 +1243,16 @@ define void @histogram_nxv4i32(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %m
define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv8i16'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv8i16'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv8i16'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
ret void
@@ -1260,16 +1260,16 @@ define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %m
define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv16i8'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv16i8'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv16i8'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv16p0.i64(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
ret void
@@ -1277,16 +1277,16 @@ define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1>
define void @histogram_v2i64(<2 x ptr> %buckets, <2 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v2i64'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v2i64'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v2i64'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
ret void
@@ -1294,16 +1294,16 @@ define void @histogram_v2i64(<2 x ptr> %buckets, <2 x i1> %mask) {
define void @histogram_v4i32(<4 x ptr> %buckets, <4 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v4i32'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v4i32'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v4i32'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
ret void
@@ -1311,16 +1311,16 @@ define void @histogram_v4i32(<4 x ptr> %buckets, <4 x i1> %mask) {
define void @histogram_v8i16(<8 x ptr> %buckets, <8 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v8i16'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v8i16'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v8i16'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
ret void
@@ -1328,16 +1328,16 @@ define void @histogram_v8i16(<8 x ptr> %buckets, <8 x i1> %mask) {
define void @histogram_v16i8(<16 x ptr> %buckets, <16 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v16i8'
-; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v16i8'
-; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v16i8'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of Invalid for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.v16p0.i64(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
ret void
@@ -1345,16 +1345,16 @@ define void @histogram_v16i8(<16 x ptr> %buckets, <16 x i1> %mask) {
define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv4i64'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv4i64'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i64'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
ret void
@@ -1362,37 +1362,37 @@ define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %m
define void @match() #3 {
; CHECK-VSCALE-1-LABEL: 'match'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 21 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 11 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 21 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of 11 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'match'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 21 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 11 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 21 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of 11 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'match'
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> undef, <vscale x 8 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 21 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> undef, <vscale x 4 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 11 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> undef, <vscale x 2 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 21 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of 11 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
%match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> undef, <vscale x 16 x i1> undef)
More information about the llvm-commits
mailing list