[llvm-branch-commits] [llvm] f3261a5 - [AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)
Tobias Hieta via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Sat Aug 10 03:17:52 PDT 2024
Author: David Green
Date: 2024-08-10T12:17:41+02:00
New Revision: f3261a5a64d8ff2c76eb9c1ae2aa7d348c75e97c
URL: https://github.com/llvm/llvm-project/commit/f3261a5a64d8ff2c76eb9c1ae2aa7d348c75e97c
DIFF: https://github.com/llvm/llvm-project/commit/f3261a5a64d8ff2c76eb9c1ae2aa7d348c75e97c.diff
LOG: [AArch64] Add invalid 1 x vscale costs for reductions and reduction-operations. (#102105)
The code-generator is currently not able to handle scalable vectors of
<vscale x 1 x eltty>. The usual "fix" for this until it is supported is
to mark the costs of loads/stores with an invalid cost, preventing the
vectorizer from vectorizing at those factors. But on rare occasions
loops do not contain load/stores, only reductions.
So whilst this is still unsupported return an invalid cost to avoid
selecting vscale x 1 VFs. The cost of a reduction is not currently used
by the vectorizer so this adds the cost to the add/mul/and/or/xor or
min/max that should feed the reduction. It includes reduction costs
too, for completeness. This change will be removed when code-generation
for these types is sufficiently reliable.
Fixes #99760
(cherry picked from commit 0b745a10843fc85e579bbf459f78b3f43e7ab309)
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
llvm/test/Analysis/CostModel/AArch64/cttz_elts.ll
llvm/test/Analysis/CostModel/AArch64/sve-arith.ll
llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 237ba67b668fcd..39fba6a257bb02 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -541,7 +541,15 @@ static InstructionCost getHistogramCost(const IntrinsicCostAttributes &ICA) {
InstructionCost
AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
TTI::TargetCostKind CostKind) {
+ // The code-generator is currently not able to handle scalable vectors
+ // of <vscale x 1 x eltty> yet, so return an invalid cost to avoid selecting
+ // it. This change will be removed when code-generation for these types is
+ // sufficiently reliable.
auto *RetTy = ICA.getReturnType();
+ if (auto *VTy = dyn_cast<ScalableVectorType>(RetTy))
+ if (VTy->getElementCount() == ElementCount::getScalable(1))
+ return InstructionCost::getInvalid();
+
switch (ICA.getID()) {
case Intrinsic::experimental_vector_histogram_add:
if (!ST->hasSVE2())
@@ -3024,6 +3032,14 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
ArrayRef<const Value *> Args,
const Instruction *CxtI) {
+ // The code-generator is currently not able to handle scalable vectors
+ // of <vscale x 1 x eltty> yet, so return an invalid cost to avoid selecting
+ // it. This change will be removed when code-generation for these types is
+ // sufficiently reliable.
+ if (auto *VTy = dyn_cast<ScalableVectorType>(Ty))
+ if (VTy->getElementCount() == ElementCount::getScalable(1))
+ return InstructionCost::getInvalid();
+
// TODO: Handle more cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info,
@@ -3798,6 +3814,14 @@ InstructionCost
AArch64TTIImpl::getMinMaxReductionCost(Intrinsic::ID IID, VectorType *Ty,
FastMathFlags FMF,
TTI::TargetCostKind CostKind) {
+ // The code-generator is currently not able to handle scalable vectors
+ // of <vscale x 1 x eltty> yet, so return an invalid cost to avoid selecting
+ // it. This change will be removed when code-generation for these types is
+ // sufficiently reliable.
+ if (auto *VTy = dyn_cast<ScalableVectorType>(Ty))
+ if (VTy->getElementCount() == ElementCount::getScalable(1))
+ return InstructionCost::getInvalid();
+
std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Ty);
if (LT.second.getScalarType() == MVT::f16 && !ST->hasFullFP16())
@@ -3842,6 +3866,14 @@ InstructionCost
AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
std::optional<FastMathFlags> FMF,
TTI::TargetCostKind CostKind) {
+ // The code-generator is currently not able to handle scalable vectors
+ // of <vscale x 1 x eltty> yet, so return an invalid cost to avoid selecting
+ // it. This change will be removed when code-generation for these types is
+ // sufficiently reliable.
+ if (auto *VTy = dyn_cast<ScalableVectorType>(ValTy))
+ if (VTy->getElementCount() == ElementCount::getScalable(1))
+ return InstructionCost::getInvalid();
+
if (TTI::requiresOrderedReduction(FMF)) {
if (auto *FixedVTy = dyn_cast<FixedVectorType>(ValTy)) {
InstructionCost BaseCost =
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll b/llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
index 18a1c31c03f748..770d3087b07522 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll
@@ -8,6 +8,7 @@ define void @fadd() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fadd <vscale x 4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fadd <vscale x 8 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fadd <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1F32 = fadd <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fadd <vscale x 2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fadd <vscale x 4 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fadd <vscale x 8 x float> undef, undef
@@ -19,6 +20,7 @@ define void @fadd() {
%V8F16 = fadd <vscale x 8 x half> undef, undef
%V16F16 = fadd <vscale x 16 x half> undef, undef
+ %V1F32 = fadd <vscale x 1 x float> undef, undef
%V2F32 = fadd <vscale x 2 x float> undef, undef
%V4F32 = fadd <vscale x 4 x float> undef, undef
%V8F32 = fadd <vscale x 8 x float> undef, undef
@@ -34,6 +36,7 @@ define void @fsub() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fsub <vscale x 4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fsub <vscale x 8 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fsub <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1F32 = fsub <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fsub <vscale x 2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fsub <vscale x 4 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fsub <vscale x 8 x float> undef, undef
@@ -45,6 +48,7 @@ define void @fsub() {
%V8F16 = fsub <vscale x 8 x half> undef, undef
%V16F16 = fsub <vscale x 16 x half> undef, undef
+ %V1F32 = fsub <vscale x 1 x float> undef, undef
%V2F32 = fsub <vscale x 2 x float> undef, undef
%V4F32 = fsub <vscale x 4 x float> undef, undef
%V8F32 = fsub <vscale x 8 x float> undef, undef
diff --git a/llvm/test/Analysis/CostModel/AArch64/cttz_elts.ll b/llvm/test/Analysis/CostModel/AArch64/cttz_elts.ll
index e1a9ee114d2613..98d5bd5bd13f43 100644
--- a/llvm/test/Analysis/CostModel/AArch64/cttz_elts.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/cttz_elts.ll
@@ -3,6 +3,7 @@
define void @foo_no_vscale_range() {
; CHECK-LABEL: 'foo_no_vscale_range'
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %res.i64.nxv1i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv1i1(<vscale x 1 x i1> undef, i1 true)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.i64.nxv2i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv2i1(<vscale x 2 x i1> undef, i1 true)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.i64.nxv4i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv4i1(<vscale x 4 x i1> undef, i1 true)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res.i64.nxv8i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv8i1(<vscale x 8 x i1> undef, i1 true)
@@ -45,6 +46,7 @@ define void @foo_no_vscale_range() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %res.i32.v32i1.nzip = call i32 @llvm.experimental.cttz.elts.i32.v32i1(<32 x i1> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %res.i64.nxv1i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv1i1(<vscale x 1 x i1> undef, i1 true)
%res.i64.nxv2i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv2i1(<vscale x 2 x i1> undef, i1 true)
%res.i64.nxv4i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv4i1(<vscale x 4 x i1> undef, i1 true)
%res.i64.nxv8i1.zip = call i64 @llvm.experimental.cttz.elts.i64.nxv8i1(<vscale x 8 x i1> undef, i1 true)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-arith.ll b/llvm/test/Analysis/CostModel/AArch64/sve-arith.ll
index f4dfea4cce349d..46450e68f40e23 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-arith.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-arith.ll
@@ -43,6 +43,7 @@ define void @scalable_mul() #0 {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mul_nxv8i16 = mul <vscale x 8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mul_nxv4i32 = mul <vscale x 4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mul_nxv2i64 = mul <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv1i64 = mul <vscale x 1 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
entry:
@@ -50,6 +51,26 @@ entry:
%mul_nxv8i16 = mul <vscale x 8 x i16> undef, undef
%mul_nxv4i32 = mul <vscale x 4 x i32> undef, undef
%mul_nxv2i64 = mul <vscale x 2 x i64> undef, undef
+ %mul_nxv1i64 = mul <vscale x 1 x i64> undef, undef
+
+ ret void
+}
+
+define void @scalable_add() #0 {
+; CHECK-LABEL: 'scalable_add'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add_nxv16i8 = add <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add_nxv8i16 = add <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add_nxv4i32 = add <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %add_nxv2i64 = add <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %add_nxv1i64 = add <vscale x 1 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+entry:
+ %add_nxv16i8 = add <vscale x 16 x i8> undef, undef
+ %add_nxv8i16 = add <vscale x 8 x i16> undef, undef
+ %add_nxv4i32 = add <vscale x 4 x i32> undef, undef
+ %add_nxv2i64 = add <vscale x 2 x i64> undef, undef
+ %add_nxv1i64 = add <vscale x 1 x i64> undef, undef
ret void
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 1993023c91e261..a3e260d211c431 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -116,82 +116,118 @@ 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-LABEL: 'reductions'
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
; CHECK-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-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-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-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-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-NEXT: Cost Model: Invalid cost for instruction: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
; CHECK-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-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-NEXT: Cost Model: Invalid cost for instruction: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
; CHECK-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-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPE_BASED_ONLY-LABEL: 'reductions'
+; TYPE_BASED_ONLY-NEXT: Cost Model: 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
;
+ %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)
%add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
+ %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> undef)
%mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
%mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
+ %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> undef)
%and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
%and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
+ %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> undef)
%or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
%or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
+ %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> undef)
%xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
%xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
+ %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> undef)
%umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
%umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+ %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> undef)
%smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
%smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+ %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> undef)
%umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
%umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+ %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> undef)
%smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
%smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+ %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.0, <vscale x 1 x float> undef)
%fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.0, <vscale x 4 x float> %v2)
%fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.0, <vscale x 4 x double> %v3)
+ %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> undef)
%fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
%fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
+ %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> undef)
%fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
%fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
index 7a801db1f35faa..777f4a2c4a64ed 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
@@ -14,6 +14,7 @@ define void @umin() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1i32 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -30,6 +31,7 @@ define void @umin() {
%V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
%V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
%V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+ %V1i32 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
%V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
%V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
%V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -49,6 +51,7 @@ define void @umax() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1i32 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -65,6 +68,7 @@ define void @umax() {
%V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
%V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
%V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+ %V1i32 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
%V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
%V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
%V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -84,6 +88,7 @@ define void @smin() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1i32 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -100,6 +105,7 @@ define void @smin() {
%V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
%V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
%V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+ %V1i32 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
%V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
%V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
%V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -119,6 +125,7 @@ define void @smax() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1i32 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -135,6 +142,7 @@ define void @smax() {
%V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
%V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
%V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+ %V1i32 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
%V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
%V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
%V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -145,6 +153,7 @@ define void @smax() {
define void @minnum() {
; CHECK-LABEL: 'minnum'
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1f32 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f32 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f32 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -156,6 +165,7 @@ define void @minnum() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <vscale x 16 x half> @llvm.minnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %V1f32 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
%V2f32 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
%V4f32 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
%V8f32 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -170,6 +180,7 @@ define void @minnum() {
define void @maxnum() {
; CHECK-LABEL: 'maxnum'
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %V1f32 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2f32 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4f32 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8f32 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -181,6 +192,7 @@ define void @maxnum() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16f16 = call <vscale x 16 x half> @llvm.maxnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %V1f32 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
%V2f32 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
%V4f32 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
%V8f32 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
More information about the llvm-branch-commits
mailing list