derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
65 lines
6.0 KiB
LLVM
65 lines
6.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
|
|
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
|
|
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE
|
|
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE
|
|
|
|
define float @reduce_fmaximum_f32(float %arg) {
|
|
; CHECK-LABEL: 'reduce_fmaximum_f32'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2 = call float @llvm.vector.reduce.fminimum.v2f32(<2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fminimum.v4f32(<4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call float @llvm.vector.reduce.fminimum.v8f32(<8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call float @llvm.vector.reduce.fminimum.v16f32(<16 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V32 = call float @llvm.vector.reduce.fminimum.v32f32(<32 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V64 = call float @llvm.vector.reduce.fminimum.v64f32(<64 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V128 = call float @llvm.vector.reduce.fminimum.v128f32(<128 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_fmaximum_f32'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call float @llvm.vector.reduce.fminimum.v2f32(<2 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fminimum.v4f32(<4 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call float @llvm.vector.reduce.fminimum.v8f32(<8 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call float @llvm.vector.reduce.fminimum.v16f32(<16 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call float @llvm.vector.reduce.fminimum.v32f32(<32 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call float @llvm.vector.reduce.fminimum.v64f32(<64 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V128 = call float @llvm.vector.reduce.fminimum.v128f32(<128 x float> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef
|
|
;
|
|
%V2 = call float @llvm.vector.reduce.fminimum.v2f32(<2 x float> undef)
|
|
%V4 = call float @llvm.vector.reduce.fminimum.v4f32(<4 x float> undef)
|
|
%V8 = call float @llvm.vector.reduce.fminimum.v8f32(<8 x float> undef)
|
|
%V16 = call float @llvm.vector.reduce.fminimum.v16f32(<16 x float> undef)
|
|
%V32 = call float @llvm.vector.reduce.fminimum.v32f32(<32 x float> undef)
|
|
%V64 = call float @llvm.vector.reduce.fminimum.v64f32(<64 x float> undef)
|
|
%V128 = call float @llvm.vector.reduce.fminimum.v128f32(<128 x float> undef)
|
|
ret float undef
|
|
}
|
|
|
|
define double @reduce_fmaximum_f64(double %arg) {
|
|
; CHECK-LABEL: 'reduce_fmaximum_f64'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2 = call double @llvm.vector.reduce.fminimum.v2f64(<2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fminimum.v4f64(<4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8 = call double @llvm.vector.reduce.fminimum.v8f64(<8 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call double @llvm.vector.reduce.fminimum.v16f64(<16 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call double @llvm.vector.reduce.fminimum.v32f64(<32 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64 = call double @llvm.vector.reduce.fminimum.v64f64(<64 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_fmaximum_f64'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call double @llvm.vector.reduce.fminimum.v2f64(<2 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call double @llvm.vector.reduce.fminimum.v4f64(<4 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call double @llvm.vector.reduce.fminimum.v8f64(<8 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call double @llvm.vector.reduce.fminimum.v16f64(<16 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call double @llvm.vector.reduce.fminimum.v32f64(<32 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call double @llvm.vector.reduce.fminimum.v64f64(<64 x double> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret double undef
|
|
;
|
|
%V2 = call double @llvm.vector.reduce.fminimum.v2f64(<2 x double> undef)
|
|
%V4 = call double @llvm.vector.reduce.fminimum.v4f64(<4 x double> undef)
|
|
%V8 = call double @llvm.vector.reduce.fminimum.v8f64(<8 x double> undef)
|
|
%V16 = call double @llvm.vector.reduce.fminimum.v16f64(<16 x double> undef)
|
|
%V32 = call double @llvm.vector.reduce.fminimum.v32f64(<32 x double> undef)
|
|
%V64 = call double @llvm.vector.reduce.fminimum.v64f64(<64 x double> undef)
|
|
ret double undef
|
|
}
|