[llvm] 8b0448c - [AArch64][Analysis] Add on overhead costs for SVE gathers and scatters
David Sherwood via llvm-commits
llvm-commits at lists.llvm.org
Thu Dec 9 08:03:10 PST 2021
Author: David Sherwood
Date: 2021-12-09T16:02:59Z
New Revision: 8b0448ce5d60abdeb7b2c7d33deca26690cacaf4
URL: https://github.com/llvm/llvm-project/commit/8b0448ce5d60abdeb7b2c7d33deca26690cacaf4
DIFF: https://github.com/llvm/llvm-project/commit/8b0448ce5d60abdeb7b2c7d33deca26690cacaf4.diff
LOG: [AArch64][Analysis] Add on overhead costs for SVE gathers and scatters
This patch adds on an overhead cost for gathers and scatters, which
is a rough estimate based on performance investigations I have
performed on SVE hardware for various micro-benchmarks.
Differential Revision: https://reviews.llvm.org/D115143
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/mem-op-cost-model.ll
llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 32df9d9dfa2dd..e8722af88579b 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -30,6 +30,12 @@ using namespace llvm::PatternMatch;
static cl::opt<bool> EnableFalkorHWPFUnrollFix("enable-falkor-hwpf-unroll-fix",
cl::init(true), cl::Hidden);
+static cl::opt<unsigned> SVEGatherOverhead("sve-gather-overhead", cl::init(10),
+ cl::Hidden);
+
+static cl::opt<unsigned> SVEScatterOverhead("sve-scatter-overhead",
+ cl::init(10), cl::Hidden);
+
bool AArch64TTIImpl::areInlineCompatible(const Function *Caller,
const Function *Callee) const {
const TargetMachine &TM = getTLI()->getTargetMachine();
@@ -1777,6 +1783,10 @@ AArch64TTIImpl::getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
return LT.first * 2;
}
+static unsigned getSVEGatherScatterOverhead(unsigned Opcode) {
+ return Opcode == Instruction::Load ? SVEGatherOverhead : SVEScatterOverhead;
+}
+
InstructionCost AArch64TTIImpl::getGatherScatterOpCost(
unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) {
@@ -1799,6 +1809,10 @@ InstructionCost AArch64TTIImpl::getGatherScatterOpCost(
ElementCount LegalVF = LT.second.getVectorElementCount();
InstructionCost MemOpCost =
getMemoryOpCost(Opcode, VT->getElementType(), Alignment, 0, CostKind, I);
+ // Add on an overhead cost for using gathers/scatters.
+ // TODO: At the moment this is applied unilaterally for all CPUs, but at some
+ // point we may want a per-CPU overhead.
+ MemOpCost *= getSVEGatherScatterOverhead(Opcode);
return LT.first * MemOpCost * getMaxNumElements(LegalVF);
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/mem-op-cost-model.ll b/llvm/test/Analysis/CostModel/AArch64/mem-op-cost-model.ll
index fa51efd0a87c9..31b49f76d9838 100644
--- a/llvm/test/Analysis/CostModel/AArch64/mem-op-cost-model.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/mem-op-cost-model.ll
@@ -92,8 +92,8 @@ define <4 x i8> @gather_load_4xi8_constant_mask(<4 x i8*> %ptrs) {
; CHECK: gather_load_4xi8_constant_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 17 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
; CHECK-SVE-128: Cost Model: Found an estimated cost of 17 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
;
%lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %ptrs, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i8> undef)
ret <4 x i8> %lv
@@ -103,8 +103,8 @@ define <4 x i8> @gather_load_4xi8_variable_mask(<4 x i8*> %ptrs, <4 x i1> %cond)
; CHECK: gather_load_4xi8_variable_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 29 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
; CHECK-SVE-128: Cost Model: Found an estimated cost of 29 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8
;
%lv = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %ptrs, i32 1, <4 x i1> %cond, <4 x i8> undef)
ret <4 x i8> %lv
@@ -115,8 +115,8 @@ define void @scatter_store_4xi8_constant_mask(<4 x i8> %val, <4 x i8*> %ptrs) {
; CHECK: scatter_store_4xi8_constant_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
; CHECK-SVE-128: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
;
call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %val, <4 x i8*> %ptrs, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
ret void
@@ -126,8 +126,8 @@ define void @scatter_store_4xi8_variable_mask(<4 x i8> %val, <4 x i8*> %ptrs, <4
; CHECK: scatter_store_4xi8_variable_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
; CHECK-SVE-128: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(
;
call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %val, <4 x i8*> %ptrs, i32 1, <4 x i1> %cond)
ret void
@@ -138,8 +138,8 @@ define <4 x i32> @gather_load_4xi32_constant_mask(<4 x i32*> %ptrs) {
; CHECK: gather_load_4xi32_constant_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 17 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
; CHECK-SVE-128: Cost Model: Found an estimated cost of 17 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
;
%lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
ret <4 x i32> %lv
@@ -149,8 +149,8 @@ define <4 x i32> @gather_load_4xi32_variable_mask(<4 x i32*> %ptrs, <4 x i1> %co
; CHECK: gather_load_4xi32_variable_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 29 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
; CHECK-SVE-128: Cost Model: Found an estimated cost of 29 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: %lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32
;
%lv = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 1, <4 x i1> %cond, <4 x i32> undef)
ret <4 x i32> %lv
@@ -161,8 +161,8 @@ define void @scatter_store_4xi32_constant_mask(<4 x i32> %val, <4 x i32*> %ptrs)
; CHECK: scatter_store_4xi32_constant_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
; CHECK-SVE-128: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
;
call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %val, <4 x i32*> %ptrs, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
ret void
@@ -172,8 +172,8 @@ define void @scatter_store_4xi32_variable_mask(<4 x i32> %val, <4 x i32*> %ptrs,
; CHECK: scatter_store_4xi32_variable_mask
; CHECK-NEON: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
; CHECK-SVE-128: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(
;
call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %val, <4 x i32*> %ptrs, i32 1, <4 x i1> %cond)
ret void
@@ -184,8 +184,8 @@ define void @sve_gather_vls(<256 x i1> %v256i1mask) {
; CHECK-LABEL: 'sve_scatter_vls'
; CHECK-NEON: Cost Model: Found an estimated cost of 1952 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
; CHECK-SVE-128: Cost Model: Found an estimated cost of 1952 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 256 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 256 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 2560 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 2560 for instruction: %res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
entry:
%res.v256i16 = call <256 x i16> @llvm.masked.gather.v256i16.v256p0i16(<256 x i16*> undef, i32 0, <256 x i1> %v256i1mask, <256 x i16> zeroinitializer)
ret void
@@ -196,8 +196,8 @@ define void @sve_gather_vls_float(<256 x i1> %v256i1mask) {
; CHECK-LABEL: 'sve_gather_vls_float'
; CHECK-NEON: Cost Model: Found an estimated cost of 1856 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
; CHECK-SVE-128: Cost Model: Found an estimated cost of 1856 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 256 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 256 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 2560 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 2560 for instruction: %res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
entry:
%res.v256f32 = call <256 x float> @llvm.masked.gather.v256f32.v256p0f32(<256 x float*> undef, i32 0, <256 x i1> %v256i1mask, <256 x float> zeroinitializer)
ret void
@@ -208,8 +208,8 @@ define void @sve_scatter_vls(<256 x i1> %v256i1mask){
; CHECK-LABEL: 'sve_scatter_vls'
; CHECK-NEON: Cost Model: Found an estimated cost of 2000 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
; CHECK-SVE-128: Cost Model: Found an estimated cost of 2000 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 2560 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 2560 for instruction: call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
entry:
call void @llvm.masked.scatter.v256i8.v256p0i8(<256 x i8> undef, <256 x i8*> undef, i32 0, <256 x i1> %v256i1mask)
ret void
@@ -220,8 +220,8 @@ define void @sve_scatter_vls_float(<512 x i1> %v512i1mask){
; CHECK-LABEL: 'sve_scatter_vls_float'
; CHECK-NEON: Cost Model: Found an estimated cost of 3904 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
; CHECK-SVE-128: Cost Model: Found an estimated cost of 3904 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
-; CHECK-SVE-256: Cost Model: Found an estimated cost of 512 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
-; CHECK-SVE-512: Cost Model: Found an estimated cost of 512 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
+; CHECK-SVE-256: Cost Model: Found an estimated cost of 5120 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
+; CHECK-SVE-512: Cost Model: Found an estimated cost of 5120 for instruction: call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
call void @llvm.masked.scatter.v512f16.v512p0f16(<512 x half> undef, <512 x half*> undef, i32 0, <512 x i1> %v512i1mask)
ret void
-}
\ No newline at end of file
+}
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-gather.ll b/llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
index 61cd1750d6939..d86048de990ab 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
@@ -8,20 +8,20 @@ target triple="aarch64--linux-gnu"
define void @masked_gathers(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #0 {
; CHECK-LABEL: 'masked_gathers'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_gathers'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_gathers'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -33,20 +33,20 @@ define void @masked_gathers(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nx
define void @masked_gathers_tune_generic(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #1 {
; CHECK-LABEL: 'masked_gathers_tune_generic'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_gathers_tune_generic'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_gathers_tune_generic'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i32 = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask, <vscale x 4 x i32> zeroinitializer)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i32 = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0i32(<vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask, <vscale x 8 x i32> zeroinitializer)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: %res.nxv1i64 = call <vscale x 1 x i64> @llvm.masked.gather.nxv1i64.nxv1p0i64(<vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask, <vscale x 1 x i64> zeroinitializer)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -58,36 +58,36 @@ define void @masked_gathers_tune_generic(<vscale x 4 x i1> %nxv4i1mask, <vscale
define void @masked_gathers_no_vscale_range() #2 {
; CHECK-LABEL: 'masked_gathers_no_vscale_range'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_gathers_no_vscale_range'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_gathers_no_vscale_range'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %res.nxv2f64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv8f32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv4f32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %res.nxv2f32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %res.nxv16i16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %res.nxv8i16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res.nxv4i16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%res.nxv4f64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll b/llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
index 9e2948cc46893..f001d2278dd8d 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
@@ -8,20 +8,20 @@ target triple="aarch64--linux-gnu"
define void @masked_scatters(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #0 {
; CHECK-LABEL: 'masked_scatters'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_scatters'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -33,20 +33,20 @@ define void @masked_scatters(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %n
define void @masked_scatters_tune_generic(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #1 {
; CHECK-LABEL: 'masked_scatters_tune_generic'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters_tune_generic'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_scatters_tune_generic'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef, <vscale x 4 x i32*> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0i32(<vscale x 8 x i32> undef, <vscale x 8 x i32*> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0i64(<vscale x 1 x i64> undef, <vscale x 1 x i64*> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -58,36 +58,36 @@ define void @masked_scatters_tune_generic(<vscale x 4 x i1> %nxv4i1mask, <vscale
define void @masked_scatters_no_vscale_range() #2 {
; CHECK-LABEL: 'masked_scatters_no_vscale_range'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters_no_vscale_range'
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-1-LABEL: 'masked_scatters_no_vscale_range'
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.masked.scatter.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
index c40e219d54799..e0b2b1d038db0 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll
@@ -4,7 +4,7 @@
target triple="aarch64--linux-gnu"
; CHECK: LV: Checking a loop in "gather_nxv4i32_loaded_index"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: %1 = load float, float* %arrayidx3, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %1 = load float, float* %arrayidx3, align 4
define void @gather_nxv4i32_loaded_index(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 {
entry:
br label %for.body
@@ -26,7 +26,7 @@ for.cond.cleanup: ; preds = %for.cond.cleanup.lo
}
; CHECK: LV: Checking a loop in "scatter_nxv4i32_loaded_index"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: store float %1, float* %arrayidx5, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %1, float* %arrayidx5, align 4
define void @scatter_nxv4i32_loaded_index(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 {
entry:
br label %for.body
@@ -94,7 +94,7 @@ for.cond.cleanup: ; preds = %for.cond.cleanup.lo
}
; CHECK: LV: Checking a loop in "gather_nxv4i32_stride2"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4
define void @gather_nxv4i32_stride2(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 {
entry:
br label %for.body
@@ -115,7 +115,7 @@ for.cond.cleanup: ; preds = %for.cond.cleanup.lo
}
; CHECK: LV: Checking a loop in "scatter_nxv4i32_stride2"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4
define void @scatter_nxv4i32_stride2(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 {
entry:
br label %for.body
@@ -137,7 +137,7 @@ for.cond.cleanup: ; preds = %for.cond.cleanup.lo
; CHECK: LV: Checking a loop in "gather_nxv4i32_stride64"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4
define void @gather_nxv4i32_stride64(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 {
entry:
br label %for.body
@@ -158,7 +158,7 @@ for.cond.cleanup: ; preds = %for.cond.cleanup.lo
}
; CHECK: LV: Checking a loop in "scatter_nxv4i32_stride64"
-; CHECK: LV: Found an estimated cost of 9 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4
+; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4
define void @scatter_nxv4i32_stride64(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 {
entry:
br label %for.body
More information about the llvm-commits
mailing list