| ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py |
| ; RUN: opt < %s -enable-no-nans-fp-math -cost-model -analyze -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s |
| |
| define i32 @fadd(i32 %arg) { |
| ; CHECK-LABEL: 'fadd' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fadd half undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <4 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fadd <8 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fadd <16 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fadd float undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <2 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fadd <8 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fadd double undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <2 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <4 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fadd half undef, undef |
| %V4F16 = fadd <4 x half> undef, undef |
| %V8F16 = fadd <8 x half> undef, undef |
| %V16F16 = fadd <16 x half> undef, undef |
| |
| %F32 = fadd float undef, undef |
| %V2F32 = fadd <2 x float> undef, undef |
| %V4F32 = fadd <4 x float> undef, undef |
| %V8F32 = fadd <8 x float> undef, undef |
| |
| %F64 = fadd double undef, undef |
| %V2F64 = fadd <2 x double> undef, undef |
| %V4F64 = fadd <4 x double> undef, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fsub(i32 %arg) { |
| ; CHECK-LABEL: 'fsub' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <8 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fsub <16 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fsub float undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <2 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <8 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fsub double undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fsub half undef, undef |
| %V4F16 = fsub <4 x half> undef, undef |
| %V8F16 = fsub <8 x half> undef, undef |
| %V16F16 = fsub <16 x half> undef, undef |
| |
| %F32 = fsub float undef, undef |
| %V2F32 = fsub <2 x float> undef, undef |
| %V4F32 = fsub <4 x float> undef, undef |
| %V8F32 = fsub <8 x float> undef, undef |
| |
| %F64 = fsub double undef, undef |
| %V2F64 = fsub <2 x double> undef, undef |
| %V4F64 = fsub <4 x double> undef, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fneg_idiom(i32 %arg) { |
| ; CHECK-LABEL: 'fneg_idiom' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half 0xH8000, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> <half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <8 x half> <half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000, half 0xH8000>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fsub float -0.000000e+00, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fsub double -0.000000e+00, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fsub half -0.0, undef |
| %V4F16 = fsub <4 x half> <half -0.0, half -0.0, half -0.0, half -0.0>, undef |
| %V8F16 = fsub <8 x half> <half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0>, undef |
| |
| %F32 = fsub float -0.0, undef |
| %V2F32 = fsub <2 x float> <float -0.0, float -0.0>, undef |
| %V4F32 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, undef |
| %V8F32 = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, undef |
| |
| %F64 = fsub double -0.0, undef |
| %V2F64 = fsub <2 x double> <double -0.0, double -0.0>, undef |
| %V4F64 = fsub <4 x double> <double -0.0, double -0.0, double -0.0, double -0.0>, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fneg(i32 %arg) { |
| ; CHECK-LABEL: 'fneg' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fneg half undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fneg <2 x half> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fneg <4 x half> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fneg <8 x half> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fneg <16 x half> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fneg float undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fneg <2 x float> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fneg <4 x float> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fneg <8 x float> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fneg double undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fneg <2 x double> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fneg <4 x double> undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fneg half undef |
| %V2F16 = fneg <2 x half> undef |
| %V4F16 = fneg <4 x half> undef |
| %V8F16 = fneg <8 x half> undef |
| %V16F16 = fneg <16 x half> undef |
| |
| %F32 = fneg float undef |
| %V2F32 = fneg <2 x float> undef |
| %V4F32 = fneg <4 x float> undef |
| %V8F32 = fneg <8 x float> undef |
| |
| %F64 = fneg double undef |
| %V2F64 = fneg <2 x double> undef |
| %V4F64 = fneg <4 x double> undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fmul(i32 %arg) { |
| ; CHECK-LABEL: 'fmul' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <8 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <16 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fmul float undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <2 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <8 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <2 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <4 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fmul half undef, undef |
| %V4F16 = fmul <4 x half> undef, undef |
| %V8F16 = fmul <8 x half> undef, undef |
| %V16F16 = fmul <16 x half> undef, undef |
| |
| %F32 = fmul float undef, undef |
| %V2F32 = fmul <2 x float> undef, undef |
| %V4F32 = fmul <4 x float> undef, undef |
| %V8F32 = fmul <8 x float> undef, undef |
| |
| %F64 = fmul double undef, undef |
| %V2F64 = fmul <2 x double> undef, undef |
| %V4F64 = fmul <4 x double> undef, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fdiv(i32 %arg) { |
| ; CHECK-LABEL: 'fdiv' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <8 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fdiv float undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <2 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <4 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <8 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fdiv double undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fdiv <2 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <4 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = fdiv half undef, undef |
| %V4F16 = fdiv <4 x half> undef, undef |
| %V8F16 = fdiv <8 x half> undef, undef |
| %V16F16 = fdiv <16 x half> undef, undef |
| |
| %F32 = fdiv float undef, undef |
| %V2F32 = fdiv <2 x float> undef, undef |
| %V4F32 = fdiv <4 x float> undef, undef |
| %V8F32 = fdiv <8 x float> undef, undef |
| |
| %F64 = fdiv double undef, undef |
| %V2F64 = fdiv <2 x double> undef, undef |
| %V4F64 = fdiv <4 x double> undef, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @frem(i32 %arg) { |
| ; CHECK-LABEL: 'frem' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = frem half undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V4F16 = frem <4 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8F16 = frem <8 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 116 for instruction: %V16F16 = frem <16 x half> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2F32 = frem <2 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V4F32 = frem <4 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8F32 = frem <8 x float> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2F64 = frem <2 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4F64 = frem <4 x double> undef, undef |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = frem half undef, undef |
| %V4F16 = frem <4 x half> undef, undef |
| %V8F16 = frem <8 x half> undef, undef |
| %V16F16 = frem <16 x half> undef, undef |
| |
| %F32 = frem float undef, undef |
| %V2F32 = frem <2 x float> undef, undef |
| %V4F32 = frem <4 x float> undef, undef |
| %V8F32 = frem <8 x float> undef, undef |
| |
| %F64 = frem double undef, undef |
| %V2F64 = frem <2 x double> undef, undef |
| %V4F64 = frem <4 x double> undef, undef |
| |
| ret i32 undef |
| } |
| |
| define i32 @fsqrt(i32 %arg) { |
| ; CHECK-LABEL: 'fsqrt' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.sqrt.f16(half undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = call half @llvm.sqrt.f16(half undef) |
| %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef) |
| %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef) |
| %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef) |
| |
| %F32 = call float @llvm.sqrt.f32(float undef) |
| %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef) |
| %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef) |
| %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef) |
| |
| %F64 = call double @llvm.sqrt.f64(double undef) |
| %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef) |
| %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef) |
| |
| ret i32 undef |
| } |
| |
| define i32 @fabs(i32 %arg) { |
| ; CHECK-LABEL: 'fabs' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.fabs.f16(half undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fabs.f32(float undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fabs.f64(double undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = call half @llvm.fabs.f16(half undef) |
| %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef) |
| %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef) |
| %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef) |
| |
| %F32 = call float @llvm.fabs.f32(float undef) |
| %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef) |
| %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef) |
| %V8F32 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef) |
| |
| %F64 = call double @llvm.fabs.f64(double undef) |
| %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef) |
| %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef) |
| |
| ret i32 undef |
| } |
| |
| define i32 @fcopysign(i32 %arg) { |
| ; CHECK-LABEL: 'fcopysign' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = call half @llvm.copysign.f16(half undef, half undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = call half @llvm.copysign.f16(half undef, half undef) |
| %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef) |
| %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef) |
| %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef) |
| |
| %F32 = call float @llvm.copysign.f32(float undef, float undef) |
| %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef) |
| %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef) |
| %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef) |
| |
| %F64 = call double @llvm.copysign.f64(double undef, double undef) |
| %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef) |
| %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef) |
| |
| ret i32 undef |
| } |
| |
| define i32 @fma(i32 %arg) { |
| ; CHECK-LABEL: 'fma' |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call float @llvm.fma.f32(float undef, float undef, float undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef) |
| ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef |
| ; |
| %F16 = call float @llvm.fma.f32(float undef, float undef, float undef) |
| %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef) |
| %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef) |
| %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef) |
| |
| %F32 = call float @llvm.fma.f32(float undef, float undef, float undef) |
| %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef) |
| %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef) |
| %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef) |
| |
| %F64 = call double @llvm.fma.f64(double undef, double undef, double undef) |
| %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef) |
| %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef) |
| |
| ret i32 undef |
| } |
| |
| declare half @llvm.sqrt.f16(half) |
| declare <4 x half> @llvm.sqrt.v4f16(<4 x half>) |
| declare <8 x half> @llvm.sqrt.v8f16(<8 x half>) |
| declare <16 x half> @llvm.sqrt.v16f16(<16 x half>) |
| |
| declare float @llvm.sqrt.f32(float) |
| declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) |
| declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) |
| declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) |
| |
| declare double @llvm.sqrt.f64(double) |
| declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) |
| declare <4 x double> @llvm.sqrt.v4f64(<4 x double>) |
| |
| declare half @llvm.fabs.f16(half) |
| declare <4 x half> @llvm.fabs.v4f16(<4 x half>) |
| declare <8 x half> @llvm.fabs.v8f16(<8 x half>) |
| declare <16 x half> @llvm.fabs.v16f16(<16 x half>) |
| |
| declare float @llvm.fabs.f32(float) |
| declare <2 x float> @llvm.fabs.v2f32(<2 x float>) |
| declare <4 x float> @llvm.fabs.v4f32(<4 x float>) |
| declare <8 x float> @llvm.fabs.v8f32(<8 x float>) |
| |
| declare double @llvm.fabs.f64(double) |
| declare <2 x double> @llvm.fabs.v2f64(<2 x double>) |
| declare <4 x double> @llvm.fabs.v4f64(<4 x double>) |
| |
| declare half @llvm.copysign.f16(half, half) |
| declare <4 x half> @llvm.copysign.v4f16(<4 x half>, <4 x half>) |
| declare <8 x half> @llvm.copysign.v8f16(<8 x half>, <8 x half>) |
| declare <16 x half> @llvm.copysign.v16f16(<16 x half>, <16 x half>) |
| |
| declare float @llvm.copysign.f32(float, float) |
| declare <2 x float> @llvm.copysign.v2f32(<2 x float>, <2 x float>) |
| declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>) |
| declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>) |
| |
| declare double @llvm.copysign.f64(double, double) |
| declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>) |
| declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>) |
| |
| declare half @llvm.fma.f16(half, half, half) |
| declare <4 x half> @llvm.fma.v4f16(<4 x half>, <4 x half>, <4 x half>) |
| declare <8 x half> @llvm.fma.v8f16(<8 x half>, <8 x half>, <8 x half>) |
| declare <16 x half> @llvm.fma.v16f16(<16 x half>, <16 x half>, <16 x half>) |
| |
| declare float @llvm.fma.f32(float, float, float) |
| declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>) |
| declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>) |
| declare <8 x float> @llvm.fma.v8f32(<8 x float>, <8 x float>, <8 x float>) |
| |
| declare double @llvm.fma.f64(double, double, double) |
| declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) |
| declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>) |
