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
38 lines
1.6 KiB
LLVM
38 lines
1.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 < %s | FileCheck -check-prefixes=GCN %s
|
|
|
|
define amdgpu_kernel void @uniform_build_vector(i64 %in, ptr addrspace(1) %out) {
|
|
; GCN-LABEL: uniform_build_vector:
|
|
; GCN: ; %bb.0: ; %entry
|
|
; GCN-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: s_lshr_b64 s[4:5], s[0:1], 1
|
|
; GCN-NEXT: s_mov_b32 s5, 0
|
|
; GCN-NEXT: s_mov_b32 s6, s5
|
|
; GCN-NEXT: s_mov_b32 s7, s5
|
|
; GCN-NEXT: buffer_load_dwordx4 v[0:3], off, s[4:7], 0
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: v_mov_b32_e32 v1, 0
|
|
; GCN-NEXT: ; sched_barrier mask(0x00000000)
|
|
; GCN-NEXT: v_and_b32_e32 v0, 1, v0
|
|
; GCN-NEXT: v_cvt_f32_ubyte0_e32 v0, v0
|
|
; GCN-NEXT: global_store_dword v1, v0, s[2:3]
|
|
; GCN-NEXT: s_endpgm
|
|
entry:
|
|
%shifted = lshr i64 %in, 1
|
|
%trunc = trunc i64 %shifted to i32
|
|
%insert = insertelement <4 x i32> zeroinitializer, i32 %trunc, i64 0
|
|
%load = tail call <4 x i32> @llvm.amdgcn.raw.buffer.load.v4i32(<4 x i32> %insert, i32 0, i32 0, i32 0)
|
|
tail call void @llvm.amdgcn.sched.barrier(i32 0)
|
|
%extract = extractelement <4 x i32> %load, i64 0
|
|
%and = and i32 %extract, 1
|
|
%convert = sitofp i32 %and to float
|
|
store float %convert, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: convergent nocallback nofree nounwind willreturn
|
|
declare void @llvm.amdgcn.sched.barrier(i32 immarg) #0
|
|
|
|
; Function Attrs: nocallback nofree nosync nounwind willreturn memory(read)
|
|
declare <4 x i32> @llvm.amdgcn.raw.buffer.load.v4i32(<4 x i32>, i32, i32, i32 immarg) #1 |