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
40 lines
1.6 KiB
LLVM
40 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}test_fmed3_f16:
|
|
; GCN: v_med3_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
|
|
define amdgpu_kernel void @test_fmed3_f16(ptr addrspace(1) %out, i32 %src0.arg, i32 %src1.arg, i32 %src2.arg) #1 {
|
|
%src0.f16 = trunc i32 %src0.arg to i16
|
|
%src0 = bitcast i16 %src0.f16 to half
|
|
%src1.f16 = trunc i32 %src1.arg to i16
|
|
%src1 = bitcast i16 %src1.f16 to half
|
|
%src2.f16 = trunc i32 %src2.arg to i16
|
|
%src2 = bitcast i16 %src2.f16 to half
|
|
%mad = call half @llvm.amdgcn.fmed3.f16(half %src0, half %src1, half %src2)
|
|
store half %mad, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_fmed3_srcmods_f16:
|
|
; GCN: v_med3_f16 v{{[0-9]+}}, -s{{[0-9]+}}, |v{{[0-9]+}}|, -|v{{[0-9]+}}|
|
|
define amdgpu_kernel void @test_fmed3_srcmods_f16(ptr addrspace(1) %out, i32 %src0.arg, i32 %src1.arg, i32 %src2.arg) #1 {
|
|
%src0.f16 = trunc i32 %src0.arg to i16
|
|
%src0 = bitcast i16 %src0.f16 to half
|
|
%src1.f16 = trunc i32 %src1.arg to i16
|
|
%src1 = bitcast i16 %src1.f16 to half
|
|
%src2.f16 = trunc i32 %src2.arg to i16
|
|
%src2 = bitcast i16 %src2.f16 to half
|
|
%src0.fneg = fsub half -0.0, %src0
|
|
%src1.fabs = call half @llvm.fabs.f16(half %src1)
|
|
%src2.fabs = call half @llvm.fabs.f16(half %src2)
|
|
%src2.fneg.fabs = fsub half -0.0, %src2.fabs
|
|
%mad = call half @llvm.amdgcn.fmed3.f16(half %src0.fneg, half %src1.fabs, half %src2.fneg.fabs)
|
|
store half %mad, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare half @llvm.amdgcn.fmed3.f16(half, half, half) #0
|
|
declare half @llvm.fabs.f16(half) #0
|
|
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { nounwind }
|