Files
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

71 lines
1.7 KiB
C++

// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#pragma once
#include <hip/hip_runtime.h>
#include <stdint.h>
#if __clang_major__ >= 23
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wlifetime-safety-intra-tu-suggestions"
#endif
namespace ck {
struct workgroup_barrier
{
__device__ workgroup_barrier(uint32_t* ptr) : base_ptr(ptr) {}
__device__ uint32_t ld(uint32_t offset)
{
return __atomic_load_n(base_ptr + offset, __ATOMIC_RELAXED);
}
__device__ void wait_eq(uint32_t offset, uint32_t value)
{
if(threadIdx.x == 0)
{
while(ld(offset) != value) {}
}
__syncthreads();
}
__device__ void wait_lt(uint32_t offset, uint32_t value)
{
if(threadIdx.x == 0)
{
while(ld(offset) < value) {}
}
__syncthreads();
}
__device__ void wait_set(uint32_t offset, uint32_t compare, uint32_t value)
{
if(threadIdx.x == 0)
{
while(atomicCAS(base_ptr + offset, compare, value) != compare) {}
}
__syncthreads();
}
// enter critical zoon, assume buffer is zero when launch kernel
__device__ void aquire(uint32_t offset) { wait_set(offset, 0, 1); }
// exit critical zoon, assume buffer is zero when launch kernel
__device__ void release(uint32_t offset) { wait_set(offset, 1, 0); }
__device__ void inc(uint32_t offset)
{
__syncthreads();
if(threadIdx.x == 0)
{
atomicAdd(base_ptr + offset, 1);
}
}
uint32_t* base_ptr;
};
} // namespace ck
#if __clang_major__ >= 23
#pragma clang diagnostic pop
#endif