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
77 lines
2.5 KiB
LLVM
77 lines
2.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.maxnum.f64(double, double) #0
|
|
declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>) #0
|
|
declare <4 x double> @llvm.maxnum.v4f64(<4 x double>, <4 x double>) #0
|
|
declare <8 x double> @llvm.maxnum.v8f64(<8 x double>, <8 x double>) #0
|
|
declare <16 x double> @llvm.maxnum.v16f64(<16 x double>, <16 x double>) #0
|
|
|
|
; FUNC-LABEL: @test_fmax_f64
|
|
; SI: v_max_f64
|
|
define amdgpu_kernel void @test_fmax_f64(ptr addrspace(1) %out, double %a, double %b) nounwind {
|
|
%val = call double @llvm.maxnum.f64(double %a, double %b) #0
|
|
store double %val, ptr addrspace(1) %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: @test_fmax_v2f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
define amdgpu_kernel void @test_fmax_v2f64(ptr addrspace(1) %out, <2 x double> %a, <2 x double> %b) nounwind {
|
|
%val = call <2 x double> @llvm.maxnum.v2f64(<2 x double> %a, <2 x double> %b) #0
|
|
store <2 x double> %val, ptr addrspace(1) %out, align 16
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: @test_fmax_v4f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
define amdgpu_kernel void @test_fmax_v4f64(ptr addrspace(1) %out, <4 x double> %a, <4 x double> %b) nounwind {
|
|
%val = call <4 x double> @llvm.maxnum.v4f64(<4 x double> %a, <4 x double> %b) #0
|
|
store <4 x double> %val, ptr addrspace(1) %out, align 32
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: @test_fmax_v8f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
define amdgpu_kernel void @test_fmax_v8f64(ptr addrspace(1) %out, <8 x double> %a, <8 x double> %b) nounwind {
|
|
%val = call <8 x double> @llvm.maxnum.v8f64(<8 x double> %a, <8 x double> %b) #0
|
|
store <8 x double> %val, ptr addrspace(1) %out, align 64
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: @test_fmax_v16f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
; SI: v_max_f64
|
|
define amdgpu_kernel void @test_fmax_v16f64(ptr addrspace(1) %out, <16 x double> %a, <16 x double> %b) nounwind {
|
|
%val = call <16 x double> @llvm.maxnum.v16f64(<16 x double> %a, <16 x double> %b) #0
|
|
store <16 x double> %val, ptr addrspace(1) %out, align 128
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|