跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.18145 · v1

Compiling Specialized GPU-Initiated Networking

首次提交 2026-11-13 21:19
版本更新 2026-11-13 21:19
雷达观测 2026-11-16 11:41
arXiv ↗PDF ↗

摘要

Machine learning systems specialize computation to the workload and hardware, but communication remains in generic libraries whose device code and transport decisions are not visible to high-level compilers. We present Obaleth, a compiler that makes GPU-initiated communication part of a kernel's intermediate representation, co-optimizes it alongside computation, and lowers it to specialized transport code. Obaleth plans completions around buffer lifetimes and optimizes memory ordering, synchronization, and batching across NVIDIA and AMD GPUs. On H100 GPUs, Obaleth sends small messages up to 3.3×\times faster, and on 256 GPUs runs all-to-all 1.25×\times and 2.3×\times faster than NVSHMEM and NCCL GIN, with much smaller memory and register use. In vLLM, it serves Qwen3-235B on 16 B200 GPUs and answers requests up to 1.29×\times faster than with DeepEP.

作者备注:20 pages, 13 figures, 6 tables. Equal contribution from first two authors. Code: https://github.com/ParCoreLab/aboleth

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-13 21:19 · 最新观测版本

Compiling Specialized GPU-Initiated Networking

Machine learning systems specialize computation to the workload and hardware, but communication remains in generic libraries whose device code and transport decisions are not visible to high-level compilers. We present Obaleth, a compiler that makes GPU-initiated communication part of a kernel's intermediate representation, co-optimizes it alongside computation, and lowers it to specialized transport code. Obaleth plans completions around buffer lifetimes and optimizes memory ordering, synchronization, and batching across NVIDIA and AMD GPUs. On H100 GPUs, Obaleth sends small messages up to 3.3×\times faster, and on 256 GPUs runs all-to-all 1.25×\times and 2.3×\times faster than NVSHMEM and NCCL GIN, with much smaller memory and register use. In vLLM, it serves Qwen3-235B on 16 B200 GPUs and answers requests up to 1.29×\times faster than with DeepEP.

查看此版本解读 →查看此版本原文 ↗