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
55 lines
2.4 KiB
LLVM
55 lines
2.4 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_ctpop_i32
|
|
; GCN: S_BCNT1_I32_B32
|
|
define amdgpu_kernel void @s_ctpop_i32(ptr addrspace(1) noalias %out, i32 %val) nounwind {
|
|
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
|
|
store i32 %ctpop, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: name: s_ctpop_i64
|
|
; GCN: %[[BCNT:[0-9]+]]:sreg_32 = S_BCNT1_I32_B64
|
|
; GCN: %[[SREG1:[0-9]+]]:sreg_32 = COPY killed %[[BCNT]]
|
|
; GCN: %[[SREG2:[0-9]+]]:sreg_32 = S_MOV_B32 0
|
|
; GCN: REG_SEQUENCE killed %[[SREG1]], %subreg.sub0, killed %[[SREG2]], %subreg.sub1
|
|
define amdgpu_kernel void @s_ctpop_i64(ptr addrspace(1) noalias %out, i64 %val) nounwind {
|
|
%ctpop = call i64 @llvm.ctpop.i64(i64 %val) nounwind readnone
|
|
%truncctpop = trunc i64 %ctpop to i32
|
|
store i32 %truncctpop, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: name: v_ctpop_i32
|
|
; GCN: V_BCNT_U32_B32_e64
|
|
define amdgpu_kernel void @v_ctpop_i32(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) nounwind {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%in.gep = getelementptr i32, ptr addrspace(1) %in, i32 %tid
|
|
%val = load i32, ptr addrspace(1) %in.gep, align 4
|
|
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
|
|
store i32 %ctpop, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: name: v_ctpop_i64
|
|
; GCN: %[[BCNT1:[0-9]+]]:vgpr_32 = V_BCNT_U32_B32_e64 killed %{{[0-9]+}}, 0, implicit $exec
|
|
; GCN: %[[BCNT2:[0-9]+]]:vgpr_32 = V_BCNT_U32_B32_e64 killed %{{[0-9]+}}, killed %[[BCNT1]], implicit $exec
|
|
; GCN: %[[VGPR1:[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
; GCN: REG_SEQUENCE killed %[[BCNT2]], %subreg.sub0, killed %[[VGPR1]], %subreg.sub1
|
|
define amdgpu_kernel void @v_ctpop_i64(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) nounwind {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%in.gep = getelementptr i64, ptr addrspace(1) %in, i32 %tid
|
|
%val = load i64, ptr addrspace(1) %in.gep, align 8
|
|
%ctpop = call i64 @llvm.ctpop.i64(i64 %val) nounwind readnone
|
|
%truncctpop = trunc i64 %ctpop to i32
|
|
store i32 %truncctpop, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
declare i64 @llvm.ctpop.i64(i64) nounwind readnone
|
|
|
|
declare i32 @llvm.ctpop.i32(i32) nounwind readnone
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
|