maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64] Add getCFInstrCost, treat branches as free for throughput. 

D79164/2596da31740f changed getCFInstrCost to return 1 per default.
AArch64 did not have its own implementation, hence the throughput cost
of CFI instructions is overestimated. On most cores, most branches should
be predicated and essentially free throughput wise.

This restores a 9% performance regression on a SPEC2006 benchmark on
AArch64 with -O3 LTO & PGO.

This patch effectively restores pre 2596da3174 behavior for AArch64
and undoes the AArch64 test changes of the patch.

Reviewers: samparker, dmgreen, anemet

Reviewed By: samparker

Differential Revision: https://reviews.llvm.org/D82755
This commit is contained in:
Florian Hahn 2020-06-30 10:39:23 +01:00
parent 4ab4398045
commit 1ccc49924a
11 changed files with 116 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -469,6 +469,14 @@ int AArch64TTIImpl::getExtractWithExtendCost(unsigned Opcode, Type *Dst,
return Cost + getCastInstrCost(Opcode, Dst, Src, CostKind);
}
unsigned AArch64TTIImpl::getCFInstrCost(unsigned Opcode,
TTI::TargetCostKind CostKind) {
if (CostKind != TTI::TCK_RecipThroughput)
return Opcode == Instruction::PHI ? 0 : 1;
// Branches are assumed to be predicted.
return CostKind == TTI::TCK_RecipThroughput ? 0 : 1;
}
int AArch64TTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
unsigned Index) {
assert(Val->isVectorTy() && "This must be a vector type");

2
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
View File

@ -120,6 +120,8 @@ public:
int getExtractWithExtendCost(unsigned Opcode, Type *Dst, VectorType *VecTy,
unsigned Index);
unsigned getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
int getArithmeticInstrCost(

112
llvm/test/Analysis/CostModel/AArch64/aggregates.ll
View File

@ -4,63 +4,119 @@
; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -cost-model -cost-kind=code-size -analyze | FileCheck %s --check-prefixes=ALL,CODESIZE
define i32 @extract_first_i32({i32, i32} %agg) {
; ALL-LABEL: 'extract_first_i32'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 0
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
; THROUGHPUT-LABEL: 'extract_first_i32'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 0
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; LATENCY-LABEL: 'extract_first_i32'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 0
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
; CODESIZE-LABEL: 'extract_first_i32'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 0
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
%r = extractvalue {i32, i32} %agg, 0
ret i32 %r
}
define i32 @extract_second_i32({i32, i32} %agg) {
; ALL-LABEL: 'extract_second_i32'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
; THROUGHPUT-LABEL: 'extract_second_i32'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; LATENCY-LABEL: 'extract_second_i32'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
; CODESIZE-LABEL: 'extract_second_i32'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i32 } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
%r = extractvalue {i32, i32} %agg, 1
ret i32 %r
}
define i32 @extract_i32({i32, i1} %agg) {
; ALL-LABEL: 'extract_i32'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 0
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
; THROUGHPUT-LABEL: 'extract_i32'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 0
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
;
; LATENCY-LABEL: 'extract_i32'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 0
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
; CODESIZE-LABEL: 'extract_i32'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 0
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r
;
%r = extractvalue {i32, i1} %agg, 0
ret i32 %r
}
define i1 @extract_i1({i32, i1} %agg) {
; ALL-LABEL: 'extract_i1'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i1 %r
; THROUGHPUT-LABEL: 'extract_i1'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i1 %r
;
; LATENCY-LABEL: 'extract_i1'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i1 %r
;
; CODESIZE-LABEL: 'extract_i1'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, i1 } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i1 %r
;
%r = extractvalue {i32, i1} %agg, 1
ret i1 %r
}
define float @extract_float({i32, float} %agg) {
; ALL-LABEL: 'extract_float'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, float } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float %r
; THROUGHPUT-LABEL: 'extract_float'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, float } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
;
; LATENCY-LABEL: 'extract_float'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, float } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float %r
;
; CODESIZE-LABEL: 'extract_float'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, float } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float %r
;
%r = extractvalue {i32, float} %agg, 1
ret float %r
}
define [42 x i42] @extract_array({i32, [42 x i42]} %agg) {
; ALL-LABEL: 'extract_array'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, [42 x i42] } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret [42 x i42] %r
; THROUGHPUT-LABEL: 'extract_array'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, [42 x i42] } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret [42 x i42] %r
;
; LATENCY-LABEL: 'extract_array'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, [42 x i42] } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret [42 x i42] %r
;
; CODESIZE-LABEL: 'extract_array'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, [42 x i42] } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret [42 x i42] %r
;
%r = extractvalue {i32, [42 x i42]} %agg, 1
ret [42 x i42] %r
}
define <42 x i42> @extract_vector({i32, <42 x i42>} %agg) {
; ALL-LABEL: 'extract_vector'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, <42 x i42> } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <42 x i42> %r
; THROUGHPUT-LABEL: 'extract_vector'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, <42 x i42> } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <42 x i42> %r
;
; LATENCY-LABEL: 'extract_vector'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, <42 x i42> } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <42 x i42> %r
;
; CODESIZE-LABEL: 'extract_vector'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, <42 x i42> } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <42 x i42> %r
;
%r = extractvalue {i32, <42 x i42>} %agg, 1
ret <42 x i42> %r
@ -69,9 +125,17 @@ define <42 x i42> @extract_vector({i32, <42 x i42>} %agg) {
%T1 = type { i32, float, <4 x i1> }
define %T1 @extract_struct({i32, %T1} %agg) {
; ALL-LABEL: 'extract_struct'
; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, %T1 } %agg, 1
; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret %T1 %r
; THROUGHPUT-LABEL: 'extract_struct'
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, %T1 } %agg, 1
; THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret %T1 %r
;
; LATENCY-LABEL: 'extract_struct'
; LATENCY-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, %T1 } %agg, 1
; LATENCY-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret %T1 %r
;
; CODESIZE-LABEL: 'extract_struct'
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractvalue { i32, %T1 } %agg, 1
; CODESIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret %T1 %r
;
%r = extractvalue {i32, %T1} %agg, 1
ret %T1 %r

10
llvm/test/Analysis/CostModel/AArch64/cast.ll
View File

@ -267,7 +267,7 @@ define i32 @casts_no_users() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %r247 = sitofp <16 x i16> undef to <16 x double>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r248 = uitofp <16 x i64> undef to <16 x double>
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r249 = sitofp <16 x i64> undef to <16 x double>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%r0 = sext i1 undef to i8
%r1 = zext i1 undef to i8
@ -609,7 +609,7 @@ define i32 @casts_with_users(i8 %a, i16 %b, i32 %c, i64 %d, i1 %e) {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store i16 %r23, i16* undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store i32 %r24, i32* undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store i64 %r25, i64* undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 %r12
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r12
;
%r0 = sext i8 %a to i16
%r1 = sext i8 %a to i32
@ -683,7 +683,7 @@ define i32 @bitcasts() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f = bitcast double undef to i64
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g = bitcast half undef to i16
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h = bitcast i16 undef to half
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%a = bitcast i32 undef to i32
%b = bitcast float undef to float
@ -731,7 +731,7 @@ define i32 @load_extends() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%loadi8 = load i8, i8* undef
%loadi16 = load i16, i16* undef
@ -786,7 +786,7 @@ define i32 @store_truncs() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store i16 %r4, i16* undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r5 = trunc i16 undef to i8
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store i8 %r5, i8* undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%r0 = trunc i64 undef to i8
store i8 %r0, i8* undef

2
llvm/test/Analysis/CostModel/AArch64/cmp.ll
View File

@ -17,7 +17,7 @@ define i32 @cmps() {
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %a10 = fcmp olt <8 x half> undef, undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %a11 = fcmp oge <4 x float> undef, undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %a12 = fcmp oge <2 x double> undef, undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; CHECK-SIZE-LABEL: 'cmps'
; CHECK-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %a0 = icmp slt i8 undef, undef

2
llvm/test/Analysis/CostModel/AArch64/select.ll
View File

@ -18,7 +18,7 @@ define void @select() {
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
; CHECK-THROUGHPUT-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-SIZE-LABEL: 'select'
; CHECK-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = select i1 undef, i8 undef, i8 undef

2
llvm/test/Analysis/CostModel/AArch64/shuffle-broadcast.ll
View File

@ -14,7 +14,7 @@ define void @broadcast() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v15 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32> zeroinitializer
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v17 = shufflevector <4 x float> undef, <4 x float> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v7 = shufflevector <2 x i8> undef, <2 x i8>undef, <2 x i32> zeroinitializer
%v8 = shufflevector <4 x i8> undef, <4 x i8>undef, <4 x i32> zeroinitializer

4
llvm/test/Analysis/CostModel/AArch64/store.ll
View File

@ -27,7 +27,7 @@ define void @getMemoryOpCost() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, <4 x i8>* undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %1 = load <2 x i8>, <2 x i8>* undef, align 2
; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %2 = load <4 x i8>, <4 x i8>* undef, align 4
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SIZE-LABEL: 'getMemoryOpCost'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <4 x i64> undef, <4 x i64>* undef, align 4
@ -69,7 +69,7 @@ define void @getMemoryOpCost() {
; SLOW_MISALIGNED_128_STORE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, <4 x i8>* undef, align 4
; SLOW_MISALIGNED_128_STORE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %1 = load <2 x i8>, <2 x i8>* undef, align 2
; SLOW_MISALIGNED_128_STORE-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %2 = load <4 x i8>, <4 x i8>* undef, align 4
; SLOW_MISALIGNED_128_STORE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
; SLOW_MISALIGNED_128_STORE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
store <4 x i64> undef, <4 x i64> * undef
store <8 x i32> undef, <8 x i32> * undef

4
llvm/test/Transforms/LoopVectorize/AArch64/aarch64-predication.ll
View File

@ -7,12 +7,12 @@ target triple = "aarch64--linux-gnu"
; This test checks that we correctly compute the scalarized operands for a
; user-specified vectorization factor when interleaving is disabled. We use the
; "optsize" attribute to disable all interleaving calculations. A cost of 5
; "optsize" attribute to disable all interleaving calculations. A cost of 4
; for %tmp4 indicates that we would scalarize it's operand (%tmp3), giving
; %tmp4 a lower scalarization overhead.
;
; COST-LABEL: predicated_udiv_scalarized_operand
; COST: LV: Found an estimated cost of 5 for VF 2 For instruction: %tmp4 = udiv i64 %tmp2, %tmp3
; COST: LV: Found an estimated cost of 4 for VF 2 For instruction: %tmp4 = udiv i64 %tmp2, %tmp3
;
; CHECK-LABEL: @predicated_udiv_scalarized_operand(
; CHECK: vector.body:

4
llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll
View File

@ -8,7 +8,7 @@
; Check scalar cost for extractvalue. The constant and loop invariant operands are free,
; leaving cost 3 for scalarizing the result + 2 for executing the op with VF 2.
; CM: LV: Scalar loop costs: 9.
; CM: LV: Scalar loop costs: 7.
; CM: LV: Found an estimated cost of 5 for VF 2 For instruction: %a = extractvalue { i64, i64 } %sv, 0
; CM-NEXT: LV: Found an estimated cost of 5 for VF 2 For instruction: %b = extractvalue { i64, i64 } %sv, 1
@ -57,7 +57,7 @@ exit:
; Similar to the test case above, but checks getVectorCallCost as well.
declare float @pow(float, float) readnone nounwind
; CM: LV: Scalar loop costs: 18.
; CM: LV: Scalar loop costs: 16.
; CM: LV: Found an estimated cost of 5 for VF 2 For instruction: %a = extractvalue { float, float } %sv, 0
; CM-NEXT: LV: Found an estimated cost of 5 for VF 2 For instruction: %b = extractvalue { float, float } %sv, 1

8
llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll
View File

@ -19,7 +19,7 @@ target triple = "aarch64--linux-gnu"
; (udiv(2) + extractelement(6) + insertelement(3)) / 2 = 5
;
; CHECK: Scalarizing and predicating: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 6 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
;
define i32 @predicated_udiv(i32* %a, i32* %b, i1 %c, i64 %n) {
entry:
@ -101,7 +101,7 @@ for.end:
; CHECK: Scalarizing: %tmp3 = add nsw i32 %tmp2, %x
; CHECK: Scalarizing and predicating: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 2 for VF 2 For instruction: %tmp3 = add nsw i32 %tmp2, %x
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 4 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
;
define i32 @predicated_udiv_scalarized_operand(i32* %a, i1 %c, i32 %x, i64 %n) {
entry:
@ -198,8 +198,8 @@ for.end:
; CHECK: Scalarizing: %tmp5 = sub i32 %tmp4, %x
; CHECK: Scalarizing and predicating: store i32 %tmp5, i32* %tmp0, align 4
; CHECK: Found an estimated cost of 1 for VF 2 For instruction: %tmp2 = add i32 %tmp1, %x
; CHECK: Found an estimated cost of 6 for VF 2 For instruction: %tmp3 = sdiv i32 %tmp1, %tmp2
; CHECK: Found an estimated cost of 6 for VF 2 For instruction: %tmp4 = udiv i32 %tmp3, %tmp2
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: %tmp3 = sdiv i32 %tmp1, %tmp2
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: %tmp4 = udiv i32 %tmp3, %tmp2
; CHECK: Found an estimated cost of 2 for VF 2 For instruction: %tmp5 = sub i32 %tmp4, %x
; CHECK: Found an estimated cost of 2 for VF 2 For instruction: store i32 %tmp5, i32* %tmp0, align 4
;