</> AI Coding · AMD ROCm Blog
GPU-Initiated DMA Copy Engines in RCCL and rocSHMEM
Summary · 摘要
As GPU-accelerated workloads scale across multiple devices and nodes, the efficiency of inter-GPU co…
阅读原文 rocm.blogs.amd.com
继续读 · AI Coding
ROCm 10.2.0: Advancing Performance, Stability, and Developer ExperienceAMD ROCm Blog · 1 天前An AITER Pin Keyed by Kernel Text: Faster Glue Than the Inductor DefaultAMD ROCm Blog · 2 天前Keep the Agent Warm: How ATOM Serves AgentX Workloads on AMD Instinct MI355X GPUsAMD ROCm Blog · 2 天前Reproducing AMD MLPerf Training v6.1 Submission ResultAMD ROCm Blog · 3 天前Technical Deep Dive into AMD MLPerf Training v6.1 ResultsAMD ROCm Blog · 3 天前