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
39 lines
1.8 KiB
LLVM
39 lines
1.8 KiB
LLVM
;RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s
|
|
|
|
;CHECK-LABEL: test1:
|
|
;CHECK: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
|
|
;CHECK-NEXT: MUL NON-IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
|
|
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
|
|
|
|
define amdgpu_ps void @test1(<4 x float> inreg %reg0) {
|
|
%r0 = extractelement <4 x float> %reg0, i32 0
|
|
%r1 = extractelement <4 x float> %reg0, i32 1
|
|
%r2 = call float @llvm.pow.f32( float %r0, float %r1)
|
|
%vec = insertelement <4 x float> poison, float %r2, i32 0
|
|
call void @llvm.r600.store.swizzle(<4 x float> %vec, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: test2:
|
|
;CHECK: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
|
|
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
|
|
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
|
|
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
|
|
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
|
|
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
|
|
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
|
|
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
|
|
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
|
|
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
|
|
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
|
|
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
|
|
define amdgpu_ps void @test2(<4 x float> inreg %reg0, <4 x float> inreg %reg1) {
|
|
%vec = call <4 x float> @llvm.pow.v4f32( <4 x float> %reg0, <4 x float> %reg1)
|
|
call void @llvm.r600.store.swizzle(<4 x float> %vec, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.pow.f32(float ,float ) readonly
|
|
declare <4 x float> @llvm.pow.v4f32(<4 x float> ,<4 x float> ) readonly
|
|
declare void @llvm.r600.store.swizzle(<4 x float>, i32, i32)
|