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
88 lines
2.7 KiB
LLVM
88 lines
2.7 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}fmul_f32:
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}{{T[0-9]+\.[XYZW]}}, KC0[2].Z, KC0[2].W
|
|
define amdgpu_kernel void @fmul_f32(ptr addrspace(1) %out, float %a, float %b) {
|
|
entry:
|
|
%0 = fmul float %a, %b
|
|
store float %0, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmul_v2f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}
|
|
define amdgpu_kernel void @fmul_v2f32(ptr addrspace(1) %out, <2 x float> %a, <2 x float> %b) {
|
|
entry:
|
|
%0 = fmul <2 x float> %a, %b
|
|
store <2 x float> %0, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmul_v4f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
define amdgpu_kernel void @fmul_v4f32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
|
|
%b_ptr = getelementptr <4 x float>, ptr addrspace(1) %in, i32 1
|
|
%a = load <4 x float>, ptr addrspace(1) %in
|
|
%b = load <4 x float>, ptr addrspace(1) %b_ptr
|
|
%result = fmul <4 x float> %a, %b
|
|
store <4 x float> %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_mul_2_k:
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @test_mul_2_k(ptr addrspace(1) %out, float %x) #0 {
|
|
%y = fmul float %x, 2.0
|
|
%z = fmul float %y, 3.0
|
|
store float %z, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_mul_2_k_inv:
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; GCN-NOT: v_mad_f32
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @test_mul_2_k_inv(ptr addrspace(1) %out, float %x) #0 {
|
|
%y = fmul float %x, 3.0
|
|
%z = fmul float %y, 2.0
|
|
store float %z, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; There should be three multiplies here; %a should be used twice (once
|
|
; negated), not duplicated into mul x, 5.0 and mul x, -5.0.
|
|
; FUNC-LABEL: {{^}}test_mul_twouse:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; GCN-NOT: v_mul_f32
|
|
define amdgpu_kernel void @test_mul_twouse(ptr addrspace(1) %out, float %x, float %y) #0 {
|
|
%a = fmul float %x, 5.0
|
|
%b = fsub float -0.0, %a
|
|
%c = fmul float %b, %y
|
|
%d = fmul float %c, %a
|
|
store float %d, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|