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
76 lines
2.4 KiB
LLVM
76 lines
2.4 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck %s -check-prefix=SI -check-prefix=FUNC
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck %s -check-prefix=SI -check-prefix=FUNC
|
|
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
|
|
|
|
; FUNC-LABEL: {{^}}fadd_f32:
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, KC0[2].W
|
|
; SI: v_add_f32
|
|
define amdgpu_kernel void @fadd_f32(ptr addrspace(1) %out, float %a, float %b) #0 {
|
|
%add = fadd float %a, %b
|
|
store float %add, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fadd_v2f32:
|
|
; R600-DAG: ADD {{\** *}}T{{[0-9]\.[XYZW]}}, KC0[3].X, KC0[3].Z
|
|
; R600-DAG: ADD {{\** *}}T{{[0-9]\.[XYZW]}}, KC0[2].W, KC0[3].Y
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
define amdgpu_kernel void @fadd_v2f32(ptr addrspace(1) %out, <2 x float> %a, <2 x float> %b) #0 {
|
|
%add = fadd <2 x float> %a, %b
|
|
store <2 x float> %add, ptr addrspace(1) %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fadd_v4f32:
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
define amdgpu_kernel void @fadd_v4f32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
|
|
%b_ptr = getelementptr <4 x float>, ptr addrspace(1) %in, i32 1
|
|
%a = load <4 x float>, ptr addrspace(1) %in, align 16
|
|
%b = load <4 x float>, ptr addrspace(1) %b_ptr, align 16
|
|
%result = fadd <4 x float> %a, %b
|
|
store <4 x float> %result, ptr addrspace(1) %out, align 16
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fadd_v8f32:
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; R600: ADD
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
; SI: v_add_f32
|
|
define amdgpu_kernel void @fadd_v8f32(ptr addrspace(1) %out, <8 x float> %a, <8 x float> %b) #0 {
|
|
%add = fadd <8 x float> %a, %b
|
|
store <8 x float> %add, ptr addrspace(1) %out, align 32
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fadd_0_nsz_attr_f32:
|
|
; SI-NOT: v_add_f32
|
|
define amdgpu_kernel void @fadd_0_nsz_attr_f32(ptr addrspace(1) %out, float %a) #1 {
|
|
%add = fadd nsz float %a, 0.0
|
|
store float %add, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind "no-signed-zeros-fp-math"="true" }
|