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
129 lines
4.3 KiB
LLVM
129 lines
4.3 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.fabs.f64(double %Val)
|
|
declare double @llvm.floor.f64(double) nounwind readnone
|
|
declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone
|
|
declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone
|
|
declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone
|
|
declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64:
|
|
; CI: v_floor_f64_e32
|
|
; SI: v_fract_f64_e32
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_add_f64
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @ffloor_f64(ptr addrspace(1) %out, double %x) {
|
|
%y = call fast double @llvm.floor.f64(double %x) nounwind readnone
|
|
store double %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64_neg:
|
|
; CI: v_floor_f64_e64
|
|
; SI: v_fract_f64_e64 {{v\[[0-9]+:[0-9]+\]}}, -[[INPUT:s\[[0-9]+:[0-9]+\]]]
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, -[[INPUT]]
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @ffloor_f64_neg(ptr addrspace(1) %out, double %x) {
|
|
%neg = fsub nsz double 0.0, %x
|
|
%y = call fast double @llvm.floor.f64(double %neg) nounwind readnone
|
|
store double %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64_neg_abs:
|
|
; CI: v_floor_f64_e64
|
|
; SI: v_fract_f64_e64 {{v\[[0-9]+:[0-9]+\]}}, -|[[INPUT:s\[[0-9]+:[0-9]+\]]]|
|
|
; SI-DAG: v_min_f64
|
|
; SI-DAG: v_cmp_class_f64_e64 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_add_f64 {{v\[[0-9]+:[0-9]+\]}}, -|[[INPUT]]|
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @ffloor_f64_neg_abs(ptr addrspace(1) %out, double %x) {
|
|
%abs = call fast double @llvm.fabs.f64(double %x)
|
|
%neg = fsub nsz double 0.0, %abs
|
|
%y = call fast double @llvm.floor.f64(double %neg) nounwind readnone
|
|
store double %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v2f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define amdgpu_kernel void @ffloor_v2f64(ptr addrspace(1) %out, <2 x double> %x) {
|
|
%y = call fast <2 x double> @llvm.floor.v2f64(<2 x double> %x) nounwind readnone
|
|
store <2 x double> %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v3f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI-NOT: v_floor_f64_e32
|
|
define amdgpu_kernel void @ffloor_v3f64(ptr addrspace(1) %out, <3 x double> %x) {
|
|
%y = call fast <3 x double> @llvm.floor.v3f64(<3 x double> %x) nounwind readnone
|
|
store <3 x double> %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v4f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define amdgpu_kernel void @ffloor_v4f64(ptr addrspace(1) %out, <4 x double> %x) {
|
|
%y = call fast <4 x double> @llvm.floor.v4f64(<4 x double> %x) nounwind readnone
|
|
store <4 x double> %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v8f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define amdgpu_kernel void @ffloor_v8f64(ptr addrspace(1) %out, <8 x double> %x) {
|
|
%y = call fast <8 x double> @llvm.floor.v8f64(<8 x double> %x) nounwind readnone
|
|
store <8 x double> %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v16f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define amdgpu_kernel void @ffloor_v16f64(ptr addrspace(1) %out, <16 x double> %x) {
|
|
%y = call fast <16 x double> @llvm.floor.v16f64(<16 x double> %x) nounwind readnone
|
|
store <16 x double> %y, ptr addrspace(1) %out
|
|
ret void
|
|
}
|