Skip to content

Commit eb3f1ae

Browse files
LiqinWengLiqinWeng
authored
[TTI][RISCV] Implement cost of some intrinsics with LMUL (#117874)
Intrinsics include: sadd_sat/ssub_sat/uadd_sat/usub_sat/fabs/fsqrt/cttz/ctlz/ctpop
1 parent 9ea993f commit eb3f1ae

File tree

5 files changed

+223
-160
lines changed

5 files changed

+223
-160
lines changed

‎llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

Lines changed: 50 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1013,20 +1013,65 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
10131013
case Intrinsic::sadd_sat:
10141014
case Intrinsic::ssub_sat:
10151015
case Intrinsic::uadd_sat:
1016-
case Intrinsic::usub_sat:
1016+
case Intrinsic::usub_sat: {
1017+
auto LT = getTypeLegalizationCost(RetTy);
1018+
if (ST->hasVInstructions() && LT.second.isVector()) {
1019+
unsigned Op;
1020+
switch (ICA.getID()) {
1021+
case Intrinsic::sadd_sat:
1022+
Op = RISCV::VSADD_VV;
1023+
break;
1024+
case Intrinsic::ssub_sat:
1025+
Op = RISCV::VSSUBU_VV;
1026+
break;
1027+
case Intrinsic::uadd_sat:
1028+
Op = RISCV::VSADDU_VV;
1029+
break;
1030+
case Intrinsic::usub_sat:
1031+
Op = RISCV::VSSUBU_VV;
1032+
break;
1033+
}
1034+
return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
1035+
}
1036+
break;
1037+
}
10171038
case Intrinsic::fabs:
10181039
case Intrinsic::sqrt: {
10191040
auto LT = getTypeLegalizationCost(RetTy);
1020-
if (ST->hasVInstructions() && LT.second.isVector())
1021-
return LT.first;
1041+
// TODO: add f16/bf16, bf16 with zvfbfmin && f16 with zvfhmin
1042+
if (ST->hasVInstructions() && LT.second.isVector()) {
1043+
unsigned Op;
1044+
switch (ICA.getID()) {
1045+
case Intrinsic::fabs:
1046+
Op = RISCV::VFSGNJX_VV;
1047+
break;
1048+
case Intrinsic::sqrt:
1049+
Op = RISCV::VFSQRT_V;
1050+
break;
1051+
}
1052+
return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
1053+
}
10221054
break;
10231055
}
10241056
case Intrinsic::cttz:
10251057
case Intrinsic::ctlz:
10261058
case Intrinsic::ctpop: {
10271059
auto LT = getTypeLegalizationCost(RetTy);
1028-
if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector())
1029-
return LT.first;
1060+
if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector()) {
1061+
unsigned Op;
1062+
switch (ICA.getID()) {
1063+
case Intrinsic::cttz:
1064+
Op = RISCV::VCTZ_V;
1065+
break;
1066+
case Intrinsic::ctlz:
1067+
Op = RISCV::VCLZ_V;
1068+
break;
1069+
case Intrinsic::ctpop:
1070+
Op = RISCV::VCPOP_V;
1071+
break;
1072+
}
1073+
return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
1074+
}
10301075
break;
10311076
}
10321077
case Intrinsic::abs: {

‎llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll

Lines changed: 42 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -1,30 +1,48 @@
11
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
2-
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfh | FileCheck %s --check-prefixes=CHECK,ZVFH
3-
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
2+
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfh,+zvfbfmin | FileCheck %s --check-prefixes=CHECK,ZVFH
3+
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfbfmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
44

55
define void @fabs() {
66
; CHECK-LABEL: 'fabs'
7-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.fabs.f32(float undef)
8-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
9-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
10-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
11-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
12-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.fabs.nxv1f32(<vscale x 1 x float> undef)
13-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
14-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
15-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
16-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
17-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.fabs.f64(double undef)
18-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
19-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
20-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
21-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
22-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
23-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
24-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
25-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
7+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call bfloat @llvm.fabs.bf16(bfloat undef)
8+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
9+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
10+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
11+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
12+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
13+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
14+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
15+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
16+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.fabs.f32(float undef)
17+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
18+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
19+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
20+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
21+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x float> @llvm.fabs.nxv1f32(<vscale x 1 x float> undef)
22+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
23+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
24+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
25+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
26+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call double @llvm.fabs.f64(double undef)
27+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
28+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
29+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
30+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
31+
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
32+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
33+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
34+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
2635
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
2736
;
37+
call bfloat @llvm.fabs.bf16(bfloat undef)
38+
call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
39+
call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
40+
call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
41+
call <16 x bfloat> @llvm.fabs.v16f16(<16 x bfloat> undef)
42+
call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
43+
call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
44+
call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
45+
call <vscale x 16 x bfloat> @llvm.fabs.nxv16f16(<vscale x 16 x bfloat> undef)
2846
call float @llvm.fabs.f32(float undef)
2947
call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
3048
call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
@@ -53,11 +71,11 @@ define void @fabs_f16() {
5371
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
5472
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
5573
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
56-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
74+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
5775
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
5876
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
59-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
60-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
77+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
78+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
6179
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
6280
;
6381
call half @llvm.fabs.f16(half undef)

‎llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll

Lines changed: 17 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -8,30 +8,30 @@ define void @sqrt() {
88
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.sqrt.v2bf16(<2 x bfloat> undef)
99
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.sqrt.v4bf16(<4 x bfloat> undef)
1010
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.sqrt.v8bf16(<8 x bfloat> undef)
11-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x bfloat> @llvm.sqrt.v16bf16(<16 x bfloat> undef)
11+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.sqrt.v16bf16(<16 x bfloat> undef)
1212
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.sqrt.nxv2bf16(<vscale x 2 x bfloat> undef)
1313
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.sqrt.nxv4bf16(<vscale x 4 x bfloat> undef)
14-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.sqrt.nxv8bf16(<vscale x 8 x bfloat> undef)
15-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.sqrt.nxv16bf16(<vscale x 16 x bfloat> undef)
14+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.sqrt.nxv8bf16(<vscale x 8 x bfloat> undef)
15+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.sqrt.nxv16bf16(<vscale x 16 x bfloat> undef)
1616
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.sqrt.f32(float undef)
1717
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
1818
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
19-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
20-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
19+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
20+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
2121
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x float> @llvm.sqrt.nxv1f32(<vscale x 1 x float> undef)
2222
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
23-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
24-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
25-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
23+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
24+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
25+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
2626
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call double @llvm.sqrt.f64(double undef)
2727
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
28-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
29-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
30-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
28+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
29+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
30+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
3131
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
32-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
33-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
34-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
32+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
33+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
34+
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
3535
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
3636
;
3737
call bfloat @llvm.sqrt.bf16(bfloat undef)
@@ -71,11 +71,11 @@ define void @sqrt_f16() {
7171
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.sqrt.v2f16(<2 x half> undef)
7272
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
7373
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
74-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
74+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
7575
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.sqrt.nxv2f16(<vscale x 2 x half> undef)
7676
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.sqrt.nxv4f16(<vscale x 4 x half> undef)
77-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
78-
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
77+
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
78+
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
7979
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
8080
;
8181
call half @llvm.sqrt.f16(half undef)

0 commit comments

Comments
 (0)