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
177 lines
4.9 KiB
LLVM
177 lines
4.9 KiB
LLVM
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=kaveri < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=fiji < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
|
|
|
|
; FUNC-LABEL: sin_f32
|
|
; EG: MULADD_IEEE *
|
|
; EG: FRACT *
|
|
; EG: ADD *
|
|
; EG: SIN * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
; EG-NOT: SIN
|
|
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @sin_f32(ptr addrspace(1) %out, float %x) {
|
|
%sin = call float @llvm.sin.f32(float %x)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}safe_sin_3x_f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @safe_sin_3x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul float 3.0, %x
|
|
%sin = call float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}unsafe_sin_3x_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN: 0x3ef47644
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @unsafe_sin_3x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 3.0, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmf_sin_3x_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN: 0x3ef47644
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @fmf_sin_3x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 3.0, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}safe_sin_2x_f32:
|
|
; GCN: v_add_f32
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @safe_sin_2x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul float 2.0, %x
|
|
%sin = call float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}unsafe_sin_2x_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN: 0x3ea2f983
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @unsafe_sin_2x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 2.0, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmf_sin_2x_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN: 0x3ea2f983
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @fmf_sin_2x_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 2.0, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}safe_sin_cancel_f32:
|
|
; GCN: v_mul_f32
|
|
; GCN: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @safe_sin_cancel_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul float 0x401921FB60000000, %x
|
|
%sin = call float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}unsafe_sin_cancel_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @unsafe_sin_cancel_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 0x401921FB60000000, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fmf_sin_cancel_f32:
|
|
; GCN-NOT: v_add_f32
|
|
; GCN-NOT: v_mul_f32
|
|
; SICIVI: v_fract_f32
|
|
; GFX9-NOT: v_fract_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @fmf_sin_cancel_f32(ptr addrspace(1) %out, float %x) {
|
|
%y = fmul reassoc float 0x401921FB60000000, %x
|
|
%sin = call reassoc float @llvm.sin.f32(float %y)
|
|
store float %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}sin_v4f32:
|
|
; EG: SIN * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
; EG: SIN * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
; EG: SIN * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
; EG: SIN * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
; EG-NOT: SIN
|
|
|
|
; GCN: v_sin_f32
|
|
; GCN: v_sin_f32
|
|
; GCN: v_sin_f32
|
|
; GCN: v_sin_f32
|
|
; GCN-NOT: v_sin_f32
|
|
define amdgpu_kernel void @sin_v4f32(ptr addrspace(1) %out, <4 x float> %vx) {
|
|
%sin = call <4 x float> @llvm.sin.v4f32( <4 x float> %vx)
|
|
store <4 x float> %sin, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.sin.f32(float) #0
|
|
declare <4 x float> @llvm.sin.v4f32(<4 x float>) #0
|
|
|
|
attributes #0 = { nounwind readnone }
|