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
64 lines
5.9 KiB
LLVM
64 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=x86_64-- -mattr=+xop | FileCheck %s --check-prefixes=XOP
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=x86_64-- -mattr=+fma,+avx | FileCheck %s --check-prefixes=AVX
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=x86_64-- -mattr=+fma,+avx2 | FileCheck %s --check-prefixes=AVX
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=x86_64-- -mattr=+fma,+avx512f | FileCheck %s --check-prefixes=AVX512
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=x86_64-- -mattr=+fma,+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512
|
|
|
|
define i32 @fma(i32 %arg) {
|
|
; XOP-LABEL: 'fma'
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 4 for: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 1 for: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of 4 for: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
|
|
; XOP-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
|
|
;
|
|
; AVX-LABEL: 'fma'
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 4 for: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 1 for: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of 4 for: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
|
|
; AVX-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
|
|
;
|
|
; AVX512-LABEL: 'fma'
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V8F32 = call <8 x float> @llvm.fma.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of 1 for: %V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
|
|
; AVX512-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
|
|
;
|
|
%F32 = call float @llvm.fma.f32(float undef, float undef, 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)
|
|
%V16F32 = call <16 x float> @llvm.fma.v16f32(<16 x float> undef, <16 x float> undef, <16 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)
|
|
%V8F64 = call <8 x double> @llvm.fma.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
|
|
|
|
ret i32 undef
|
|
}
|
|
|
|
declare float @llvm.fma.f32(float, float, 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 <16 x float> @llvm.fma.v16f32(<16 x float>, <16 x float>, <16 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>)
|
|
declare <8 x double> @llvm.fma.v8f64(<8 x double>, <8 x double>, <8 x double>)
|