Notes about GPU Direct Storage

本文将mark下GPU Direct Storage相关notes。

从IO读取链路来看，NVMe控制器通过DMA引擎将硬盘数据直接写入GPU显存，避免了主机内存和CPU的参与，从而实现CPU和主存的IO旁路，使IO吞吐能力不在受限于系统总线的带宽压力。

说白了，就是支持NVMe与GPU的PCIe p2p，不过只支持NVMe到GPU的方向。

GPUDirect Storage enables a direct data path between local or remote storage, such as NVMe or NVMe over Fabric (NVMe-oF), and GPU memory. It avoids extra copies through a bounce buffer in the CPU’s memory, enabling a direct memory access (DMA) engine near the NIC or storage to move data on a direct path into or out of GPU memory — all without burdening the CPU.

---

参考资料:

1. GPU Direct Storage
2. NVIDIA GPUDirect