168 lines · plain
1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py2; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefix=FAST %s3; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=FAST %s4; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s5 6; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefix=FAST-SIZE %s7; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -mattr=+half-rate-64-ops < %s | FileCheck -check-prefix=FAST-SIZE %s8; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefix=SLOW-SIZE %s9 10 11define void @fmuladd_f16() {12; FAST-LABEL: 'fmuladd_f16'13; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)14; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)15; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.fmuladd.v3f16(<3 x half> undef, <3 x half> undef, <3 x half> undef)16; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)17; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.fmuladd.v5f16(<5 x half> undef, <5 x half> undef, <5 x half> undef)18; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)19; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %v17f16 = call <17 x half> @llvm.fmuladd.v17f16(<17 x half> undef, <17 x half> undef, <17 x half> undef)20; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void21;22; SLOW-LABEL: 'fmuladd_f16'23; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)24; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v2f16 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)25; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v3f16 = call <3 x half> @llvm.fmuladd.v3f16(<3 x half> undef, <3 x half> undef, <3 x half> undef)26; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4f16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)27; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v5f16 = call <5 x half> @llvm.fmuladd.v5f16(<5 x half> undef, <5 x half> undef, <5 x half> undef)28; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v16f16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)29; SLOW-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %v17f16 = call <17 x half> @llvm.fmuladd.v17f16(<17 x half> undef, <17 x half> undef, <17 x half> undef)30; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void31;32; FAST-SIZE-LABEL: 'fmuladd_f16'33; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)34; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)35; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.fmuladd.v3f16(<3 x half> undef, <3 x half> undef, <3 x half> undef)36; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)37; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v5f16 = call <5 x half> @llvm.fmuladd.v5f16(<5 x half> undef, <5 x half> undef, <5 x half> undef)38; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v16f16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)39; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %v17f16 = call <17 x half> @llvm.fmuladd.v17f16(<17 x half> undef, <17 x half> undef, <17 x half> undef)40; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void41;42; SLOW-SIZE-LABEL: 'fmuladd_f16'43; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)44; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)45; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v3f16 = call <3 x half> @llvm.fmuladd.v3f16(<3 x half> undef, <3 x half> undef, <3 x half> undef)46; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)47; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5f16 = call <5 x half> @llvm.fmuladd.v5f16(<5 x half> undef, <5 x half> undef, <5 x half> undef)48; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)49; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %v17f16 = call <17 x half> @llvm.fmuladd.v17f16(<17 x half> undef, <17 x half> undef, <17 x half> undef)50; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void51;52 %f16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)53 %v2f16 = call <2 x half> @llvm.fmuladd.v2f16(<2 x half> undef, <2 x half> undef, <2 x half> undef)54 %v3f16 = call <3 x half> @llvm.fmuladd.v3f16(<3 x half> undef, <3 x half> undef, <3 x half> undef)55 %v4f16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)56 %v5f16 = call <5 x half> @llvm.fmuladd.v5f16(<5 x half> undef, <5 x half> undef, <5 x half> undef)57 %v16f16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)58 %v17f16 = call <17 x half> @llvm.fmuladd.v17f16(<17 x half> undef, <17 x half> undef, <17 x half> undef)59 ret void60}61 62define void @fmuladd_bf16() {63; FAST-LABEL: 'fmuladd_bf16'64; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)65; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)66; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.fmuladd.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef, <3 x bfloat> undef)67; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)68; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5bf16 = call <5 x bfloat> @llvm.fmuladd.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef, <5 x bfloat> undef)69; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)70; FAST-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %v17bf16 = call <17 x bfloat> @llvm.fmuladd.v17bf16(<17 x bfloat> undef, <17 x bfloat> undef, <17 x bfloat> undef)71; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void72;73; SLOW-LABEL: 'fmuladd_bf16'74; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bf16 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)75; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v2bf16 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)76; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v3bf16 = call <3 x bfloat> @llvm.fmuladd.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef, <3 x bfloat> undef)77; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4bf16 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)78; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v5bf16 = call <5 x bfloat> @llvm.fmuladd.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef, <5 x bfloat> undef)79; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v16bf16 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)80; SLOW-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %v17bf16 = call <17 x bfloat> @llvm.fmuladd.v17bf16(<17 x bfloat> undef, <17 x bfloat> undef, <17 x bfloat> undef)81; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void82;83; FAST-SIZE-LABEL: 'fmuladd_bf16'84; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)85; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)86; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.fmuladd.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef, <3 x bfloat> undef)87; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)88; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5bf16 = call <5 x bfloat> @llvm.fmuladd.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef, <5 x bfloat> undef)89; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)90; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %v17bf16 = call <17 x bfloat> @llvm.fmuladd.v17bf16(<17 x bfloat> undef, <17 x bfloat> undef, <17 x bfloat> undef)91; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void92;93; SLOW-SIZE-LABEL: 'fmuladd_bf16'94; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)95; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)96; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.fmuladd.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef, <3 x bfloat> undef)97; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)98; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5bf16 = call <5 x bfloat> @llvm.fmuladd.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef, <5 x bfloat> undef)99; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)100; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %v17bf16 = call <17 x bfloat> @llvm.fmuladd.v17bf16(<17 x bfloat> undef, <17 x bfloat> undef, <17 x bfloat> undef)101; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void102;103 %bf16 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)104 %v2bf16 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)105 %v3bf16 = call <3 x bfloat> @llvm.fmuladd.v3bf16(<3 x bfloat> undef, <3 x bfloat> undef, <3 x bfloat> undef)106 %v4bf16 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)107 %v5bf16 = call <5 x bfloat> @llvm.fmuladd.v5bf16(<5 x bfloat> undef, <5 x bfloat> undef, <5 x bfloat> undef)108 %v16bf16 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)109 %v17bf16 = call <17 x bfloat> @llvm.fmuladd.v17bf16(<17 x bfloat> undef, <17 x bfloat> undef, <17 x bfloat> undef)110 ret void111}112 113define void @fmuladd_f32() {114; SLOW-LABEL: 'fmuladd_f32'115; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f32 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)116; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v2f32 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)117; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v3f32 = call <3 x float> @llvm.fmuladd.v3f32(<3 x float> undef, <3 x float> undef, <3 x float> undef)118; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4f32 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)119; SLOW-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %v5f32 = call <5 x float> @llvm.fmuladd.v5f32(<5 x float> undef, <5 x float> undef, <5 x float> undef)120; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v8f32 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)121; SLOW-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %v9f32 = call <9 x float> @llvm.fmuladd.v9f32(<9 x float> undef, <9 x float> undef, <9 x float> undef)122; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void123;124; SLOW-SIZE-LABEL: 'fmuladd_f32'125; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f32 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)126; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f32 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)127; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f32 = call <3 x float> @llvm.fmuladd.v3f32(<3 x float> undef, <3 x float> undef, <3 x float> undef)128; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f32 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)129; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v5f32 = call <5 x float> @llvm.fmuladd.v5f32(<5 x float> undef, <5 x float> undef, <5 x float> undef)130; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8f32 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)131; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %v9f32 = call <9 x float> @llvm.fmuladd.v9f32(<9 x float> undef, <9 x float> undef, <9 x float> undef)132; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void133;134 %f32 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)135 %v2f32 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)136 %v3f32 = call <3 x float> @llvm.fmuladd.v3f32(<3 x float> undef, <3 x float> undef, <3 x float> undef)137 %v4f32 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)138 %v5f32 = call <5 x float> @llvm.fmuladd.v5f32(<5 x float> undef, <5 x float> undef, <5 x float> undef)139 %v8f32 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)140 %v9f32 = call <9 x float> @llvm.fmuladd.v9f32(<9 x float> undef, <9 x float> undef, <9 x float> undef)141 ret void142}143 144define void @fmuladd_f64() {145; SLOW-LABEL: 'fmuladd_f64'146; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f64 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)147; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v2f64 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)148; SLOW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %v3f64 = call <3 x double> @llvm.fmuladd.v3f64(<3 x double> undef, <3 x double> undef, <3 x double> undef)149; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4f64 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)150; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %v5f64 = call <5 x double> @llvm.fmuladd.v5f64(<5 x double> undef, <5 x double> undef, <5 x double> undef)151; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void152;153; SLOW-SIZE-LABEL: 'fmuladd_f64'154; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f64 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)155; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2f64 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)156; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %v3f64 = call <3 x double> @llvm.fmuladd.v3f64(<3 x double> undef, <3 x double> undef, <3 x double> undef)157; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v4f64 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)158; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %v5f64 = call <5 x double> @llvm.fmuladd.v5f64(<5 x double> undef, <5 x double> undef, <5 x double> undef)159; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void160;161 %f64 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)162 %v2f64 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)163 %v3f64 = call <3 x double> @llvm.fmuladd.v3f64(<3 x double> undef, <3 x double> undef, <3 x double> undef)164 %v4f64 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)165 %v5f64 = call <5 x double> @llvm.fmuladd.v5f64(<5 x double> undef, <5 x double> undef, <5 x double> undef)166 ret void167}168