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
56 lines
1.8 KiB
LLVM
56 lines
1.8 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
|
|
|
|
; FUNC-LABEL: {{^}}fpext_f32_to_f64:
|
|
; SI: v_cvt_f64_f32_e32 {{v\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @fpext_f32_to_f64(ptr addrspace(1) %out, float %in) {
|
|
%result = fpext float %in to double
|
|
store double %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fpext_v2f32_to_v2f64:
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
define amdgpu_kernel void @fpext_v2f32_to_v2f64(ptr addrspace(1) %out, <2 x float> %in) {
|
|
%result = fpext <2 x float> %in to <2 x double>
|
|
store <2 x double> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fpext_v3f32_to_v3f64:
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
define amdgpu_kernel void @fpext_v3f32_to_v3f64(ptr addrspace(1) %out, <3 x float> %in) {
|
|
%result = fpext <3 x float> %in to <3 x double>
|
|
store <3 x double> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fpext_v4f32_to_v4f64:
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
define amdgpu_kernel void @fpext_v4f32_to_v4f64(ptr addrspace(1) %out, <4 x float> %in) {
|
|
%result = fpext <4 x float> %in to <4 x double>
|
|
store <4 x double> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fpext_v8f32_to_v8f64:
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
; SI: v_cvt_f64_f32_e32
|
|
define amdgpu_kernel void @fpext_v8f32_to_v8f64(ptr addrspace(1) %out, <8 x float> %in) {
|
|
%result = fpext <8 x float> %in to <8 x double>
|
|
store <8 x double> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|