2 个仓库
Awesome GitHub RepositoriesDirect-Pointer Memory Access
Allows compute kernels to interface directly with raw tensor memory addresses for optimized hardware performance.
Distinct from Operator Kernel Implementations: Focuses on raw memory pointer access for GPU kernels rather than the logical implementation of the operator itself.
Explore 2 awesome GitHub repositories matching operating systems & systems programming · Direct-Pointer Memory Access. Refine with filters or upvote what's useful.
Awesome Direct-Pointer Memory Access GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- flashlight/flashlight
flashlight/flashlight
5,443在 GitHub 上查看Flashlight is a standalone C++ machine learning library and tensor library used for building and training neural networks. It functions as a comprehensive neural network framework and automatic differentiation engine, providing the tools to construct computation graphs and calculate gradients via backpropagation. The project serves as a distributed training framework, utilizing all-reduce operations to synchronize gradients and parameters across multiple compute nodes and devices. It distinguishes itself through deep integration of high-performance tensor manipulation, native device memory in
Enables custom GPU kernels to operate on raw tensor memory addresses for high-performance mathematical operations.
C++ - nvidia/nccl
NVIDIA/nccl
4,816在 GitHub 上查看NCCL 是一个高性能通信库和分布式 GPU 计算框架，专为在单节点或多节点系统中的多个 GPU 之间执行集合和点对点数据交换而设计。它充当 RDMA GPU 传输层和内存编排器，为分布式 GPU 训练和推理提供高带宽的数据和模型梯度同步。 该库的特色在于能够直接从 GPU 内核执行通信原语，将主机 CPU 从关键路径中移除。它利用拓扑感知路径选择来优化数据移动，并采用包括 InfiniBand 和 NVLink 在内的基于 RDMA 的网络传输，以实现设备跨不同物理节点之间的零拷贝内存访问。 该项目涵盖了广泛的集合通信模式，包括归约（Reductions）、广播（Broadcasts）、收集（Gathers）和全对全交换（All-to-all exchanges），以及点对点远程内存访问。它提供全面的通信器管理，用于初始化、分区和调整 GPU 组大小，以及用于注册缓冲区和协调共享设备内存的专用内存管理。 该系统包括一套用于健康跟踪、诊断日志记录和实时事件监控的监控与可观测性工具，以及用于机器学习框架、CUDA Graphs、MPI 和 Python 的集成接口。
Implements direct access to raw memory addresses for high-performance GPU kernel communication.
C++
