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
53 lines
2.0 KiB
LLVM
53 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck %s
|
|
|
|
; CHECK-LABEL: {{^}}v_fadd_f64:
|
|
; CHECK: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}
|
|
define amdgpu_kernel void @v_fadd_f64(ptr addrspace(1) %out, ptr addrspace(1) %in1,
|
|
ptr addrspace(1) %in2) {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%gep1 = getelementptr inbounds double, ptr addrspace(1) %in1, i32 %tid
|
|
%gep2 = getelementptr inbounds double, ptr addrspace(1) %in2, i32 %tid
|
|
%r0 = load double, ptr addrspace(1) %gep1
|
|
%r1 = load double, ptr addrspace(1) %gep2
|
|
%r2 = fadd double %r0, %r1
|
|
store double %r2, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}s_fadd_f64:
|
|
; CHECK: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}
|
|
define amdgpu_kernel void @s_fadd_f64(ptr addrspace(1) %out, double %r0, double %r1) {
|
|
%r2 = fadd double %r0, %r1
|
|
store double %r2, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}v_fadd_v2f64:
|
|
; CHECK: v_add_f64
|
|
; CHECK: v_add_f64
|
|
; CHECK: _store_dwordx4
|
|
define amdgpu_kernel void @v_fadd_v2f64(ptr addrspace(1) %out, ptr addrspace(1) %in1,
|
|
ptr addrspace(1) %in2) {
|
|
%r0 = load <2 x double>, ptr addrspace(1) %in1
|
|
%r1 = load <2 x double>, ptr addrspace(1) %in2
|
|
%r2 = fadd <2 x double> %r0, %r1
|
|
store <2 x double> %r2, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}s_fadd_v2f64:
|
|
; CHECK: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}
|
|
; CHECK: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}
|
|
; CHECK: _store_dwordx4
|
|
define amdgpu_kernel void @s_fadd_v2f64(ptr addrspace(1) %out, <2 x double> %r0, <2 x double> %r1) {
|
|
%r2 = fadd <2 x double> %r0, %r1
|
|
store <2 x double> %r2, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|