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
60 lines
2.1 KiB
C
60 lines
2.1 KiB
C
/*
|
|
* Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
*
|
|
* SPDX-License-Identifier: MIT
|
|
*/
|
|
|
|
static const char* global_atomics_sum_reduction_all_to_zero =
|
|
"#pragma OPENCL EXTENSION cl_khr_global_int32_base_atomics : enable\n"
|
|
" __kernel void global_atomics_sum_reduction_all_to_zero(uint "
|
|
"ItemsPerThread, __global uint *Input, __global atomic_int *Output )\n"
|
|
"{\n"
|
|
" uint sum = 0;\n"
|
|
" const uint msk = (uint)3;\n"
|
|
" const uint shft = (uint)8;\n"
|
|
" \n"
|
|
" uint tid = get_global_id(0);\n"
|
|
" uint Stride = get_global_size(0);\n"
|
|
" for( int i = 0; i < ItemsPerThread; i++)\n"
|
|
" {\n"
|
|
" uint data = Input[tid];\n"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" tid += Stride;\n"
|
|
" }\n"
|
|
" atomic_fetch_add_explicit( &(Output[0]), sum, memory_order_relaxed, "
|
|
"memory_scope_device);\n"
|
|
"}\n";
|
|
|
|
static const char* global_atomics_sum_reduction_workgroup =
|
|
"#pragma OPENCL EXTENSION cl_khr_global_int32_base_atomics : enable\n"
|
|
" __kernel void global_atomics_sum_reduction_workgroup(uint "
|
|
"ItemsPerThread, __global uint *Input, __global atomic_int *Output )\n"
|
|
"{\n"
|
|
" uint sum = 0;\n"
|
|
" const uint msk = (uint)3;\n"
|
|
" const uint shft = (uint)8;\n"
|
|
" \n"
|
|
" uint tid = get_global_id(0);\n"
|
|
" uint Stride = get_global_size(0);\n"
|
|
" for( int i = 0; i < ItemsPerThread; i++)\n"
|
|
" {\n"
|
|
" uint data = Input[tid];\n"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" data = data >> shft;"
|
|
" sum += data & msk;\n"
|
|
" tid += Stride;\n"
|
|
" }\n"
|
|
" atomic_fetch_add_explicit( &(Output[get_group_id(0)]), sum, "
|
|
"memory_order_relaxed, memory_scope_device);\n"
|
|
"}\n";
|