Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/divergence-driven-ctlz-cttz.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

66 lines
2.6 KiB
LLVM

; RUN: llc -mtriple=amdgcn -stop-after=amdgpu-isel < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn -enable-new-pm -stop-after=amdgpu-isel < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: name: s_ctlz_i32
; GCN: S_FLBIT_I32_B32
define amdgpu_kernel void @s_ctlz_i32(ptr addrspace(1) noalias %out, i32 %val) nounwind {
%ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
store i32 %ctlz, ptr addrspace(1) %out, align 4
ret void
}
; GCN-LABEL: name: v_ctlz_i32
; GCN: V_FFBH_U32_e64
define amdgpu_kernel void @v_ctlz_i32(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %valptr) nounwind {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%in.gep = getelementptr i32, ptr addrspace(1) %valptr, i32 %tid
%val = load i32, ptr addrspace(1) %in.gep, align 4
%ctlz = call i32 @llvm.ctlz.i32(i32 %val, i1 false) nounwind readnone
store i32 %ctlz, ptr addrspace(1) %out, align 4
ret void
}
; GCN-LABEL: name: s_cttz_i32
; GCN: S_FF1_I32_B32
define amdgpu_kernel void @s_cttz_i32(ptr addrspace(1) noalias %out, i32 %val) nounwind {
%cttz = call i32 @llvm.cttz.i32(i32 %val, i1 false) nounwind readnone
store i32 %cttz, ptr addrspace(1) %out, align 4
ret void
}
; GCN-LABEL: name: v_cttz_i32
; GCN: V_FFBL_B32_e64
define amdgpu_kernel void @v_cttz_i32(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %valptr) nounwind {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%in.gep = getelementptr i32, ptr addrspace(1) %valptr, i32 %tid
%val = load i32, ptr addrspace(1) %in.gep, align 4
%cttz = call i32 @llvm.cttz.i32(i32 %val, i1 false) nounwind readnone
store i32 %cttz, ptr addrspace(1) %out, align 4
ret void
}
; GCN-LABEL: name: s_flbit
; GCN: S_FLBIT_I32
define amdgpu_kernel void @s_flbit(ptr addrspace(1) noalias %out, i32 %val) #0 {
%r = call i32 @llvm.amdgcn.sffbh.i32(i32 %val)
store i32 %r, ptr addrspace(1) %out, align 4
ret void
}
; GCN-LABEL: name: v_flbit
; GCN: V_FFBH_I32_e64
define amdgpu_kernel void @v_flbit(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %valptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%in.gep = getelementptr i32, ptr addrspace(1) %valptr, i32 %tid
%val = load i32, ptr addrspace(1) %in.gep, align 4
%r = call i32 @llvm.amdgcn.sffbh.i32(i32 %val)
store i32 %r, ptr addrspace(1) %out, align 4
ret void
}
declare i32 @llvm.ctlz.i32(i32, i1) nounwind readnone
declare i32 @llvm.cttz.i32(i32, i1) nounwind readnone
declare i32 @llvm.amdgcn.sffbh.i32(i32)
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone