|
| 1 | +; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 4 |
| 2 | +; RUN: opt < %s -mtriple=riscv32 -mattr=+v -riscv-v-vector-bits-min=256 -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s |
| 3 | +; RUN: opt < %s -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=256 -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s |
| 4 | +; RUN: opt < %s -mtriple=riscv32 -mattr=+v -riscv-v-vector-bits-min=256 -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE |
| 5 | +; RUN: opt < %s -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=256 -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE |
| 6 | + |
| 7 | +define float @reduce_fmaximum_f32(float %arg) { |
| 8 | +; CHECK-LABEL: 'reduce_fmaximum_f32' |
| 9 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fmaximum.v2f32(<2 x float> undef) |
| 10 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call float @llvm.vector.reduce.fmaximum.v4f32(<4 x float> undef) |
| 11 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call float @llvm.vector.reduce.fmaximum.v8f32(<8 x float> undef) |
| 12 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call float @llvm.vector.reduce.fmaximum.v16f32(<16 x float> undef) |
| 13 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call float @llvm.vector.reduce.fmaximum.v32f32(<32 x float> undef) |
| 14 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call float @llvm.vector.reduce.fmaximum.v64f32(<64 x float> undef) |
| 15 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128 = call float @llvm.vector.reduce.fmaximum.v128f32(<128 x float> undef) |
| 16 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef |
| 17 | +; |
| 18 | +; SIZE-LABEL: 'reduce_fmaximum_f32' |
| 19 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call float @llvm.vector.reduce.fmaximum.v2f32(<2 x float> undef) |
| 20 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call float @llvm.vector.reduce.fmaximum.v4f32(<4 x float> undef) |
| 21 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call float @llvm.vector.reduce.fmaximum.v8f32(<8 x float> undef) |
| 22 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call float @llvm.vector.reduce.fmaximum.v16f32(<16 x float> undef) |
| 23 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call float @llvm.vector.reduce.fmaximum.v32f32(<32 x float> undef) |
| 24 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call float @llvm.vector.reduce.fmaximum.v64f32(<64 x float> undef) |
| 25 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call float @llvm.vector.reduce.fmaximum.v128f32(<128 x float> undef) |
| 26 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef |
| 27 | +; |
| 28 | +%V2 = call float @llvm.vector.reduce.fmaximum.v2f32(<2 x float> undef) |
| 29 | +%V4 = call float @llvm.vector.reduce.fmaximum.v4f32(<4 x float> undef) |
| 30 | +%V8 = call float @llvm.vector.reduce.fmaximum.v8f32(<8 x float> undef) |
| 31 | +%V16 = call float @llvm.vector.reduce.fmaximum.v16f32(<16 x float> undef) |
| 32 | +%V32 = call float @llvm.vector.reduce.fmaximum.v32f32(<32 x float> undef) |
| 33 | +%V64 = call float @llvm.vector.reduce.fmaximum.v64f32(<64 x float> undef) |
| 34 | +%V128 = call float @llvm.vector.reduce.fmaximum.v128f32(<128 x float> undef) |
| 35 | +ret float undef |
| 36 | +} |
| 37 | +declare float @llvm.vector.reduce.fmaximum.v2f32(<2 x float>) |
| 38 | +declare float @llvm.vector.reduce.fmaximum.v4f32(<4 x float>) |
| 39 | +declare float @llvm.vector.reduce.fmaximum.v8f32(<8 x float>) |
| 40 | +declare float @llvm.vector.reduce.fmaximum.v16f32(<16 x float>) |
| 41 | +declare float @llvm.vector.reduce.fmaximum.v32f32(<32 x float>) |
| 42 | +declare float @llvm.vector.reduce.fmaximum.v64f32(<64 x float>) |
| 43 | +declare float @llvm.vector.reduce.fmaximum.v128f32(<128 x float>) |
| 44 | + |
| 45 | +define double @reduce_fmaximum_f64(double %arg) { |
| 46 | +; CHECK-LABEL: 'reduce_fmaximum_f64' |
| 47 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> undef) |
| 48 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call double @llvm.vector.reduce.fmaximum.v4f64(<4 x double> undef) |
| 49 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call double @llvm.vector.reduce.fmaximum.v8f64(<8 x double> undef) |
| 50 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call double @llvm.vector.reduce.fmaximum.v16f64(<16 x double> undef) |
| 51 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call double @llvm.vector.reduce.fmaximum.v32f64(<32 x double> undef) |
| 52 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V64 = call double @llvm.vector.reduce.fmaximum.v64f64(<64 x double> undef) |
| 53 | +; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double undef |
| 54 | +; |
| 55 | +; SIZE-LABEL: 'reduce_fmaximum_f64' |
| 56 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> undef) |
| 57 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call double @llvm.vector.reduce.fmaximum.v4f64(<4 x double> undef) |
| 58 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call double @llvm.vector.reduce.fmaximum.v8f64(<8 x double> undef) |
| 59 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call double @llvm.vector.reduce.fmaximum.v16f64(<16 x double> undef) |
| 60 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call double @llvm.vector.reduce.fmaximum.v32f64(<32 x double> undef) |
| 61 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call double @llvm.vector.reduce.fmaximum.v64f64(<64 x double> undef) |
| 62 | +; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret double undef |
| 63 | +; |
| 64 | +%V2 = call double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> undef) |
| 65 | +%V4 = call double @llvm.vector.reduce.fmaximum.v4f64(<4 x double> undef) |
| 66 | +%V8 = call double @llvm.vector.reduce.fmaximum.v8f64(<8 x double> undef) |
| 67 | +%V16 = call double @llvm.vector.reduce.fmaximum.v16f64(<16 x double> undef) |
| 68 | +%V32 = call double @llvm.vector.reduce.fmaximum.v32f64(<32 x double> undef) |
| 69 | +%V64 = call double @llvm.vector.reduce.fmaximum.v64f64(<64 x double> undef) |
| 70 | +ret double undef |
| 71 | +} |
| 72 | +declare double @llvm.vector.reduce.fmaximum.v2f64(<2 x double>) |
| 73 | +declare double @llvm.vector.reduce.fmaximum.v4f64(<4 x double>) |
| 74 | +declare double @llvm.vector.reduce.fmaximum.v8f64(<8 x double>) |
| 75 | +declare double @llvm.vector.reduce.fmaximum.v16f64(<16 x double>) |
| 76 | +declare double @llvm.vector.reduce.fmaximum.v32f64(<32 x double>) |
| 77 | +declare double @llvm.vector.reduce.fmaximum.v64f64(<64 x double>) |
0 commit comments