跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.14904 · v1

SubGPU Pipelining: Intra-GPU Fine-Grained Spatial Parallelism for LLM Inference

首次提交 2026-11-11 09:51
版本更新 2026-11-11 09:51
雷达观测 2026-11-13 10:09
arXiv ↗PDF ↗

摘要

Large language model (LLM) decode is dominated by short, predominantly memory-bound kernels that make bursty use of on-chip execution resources and memory bandwidth. This paper introduces SubGPU Pipelining, a fine-grained, intra-GPU spatial execution model that cuts an operator graph into ordered contiguous segments, binds those segments to spatial stages backed by disjoint streaming-multiprocessor (SM) pools, and streams microbatches through the resulting schedule. Selecting the graph cuts, segment-to-stage binding, per-stage SM allocation, and microbatch size is a coupled optimization problem: each choice changes the overlap pattern, shared-resource contention, cache state, and execution times of the others. We evaluate SubGPU Pipelining through both simulation and silicon experiment using the GPT-OSS 120B workload with 32-GPU B200 deployment settings. The analytical shared-resource simulator searches across SubGPU pipeline structures and batch sizes to map the per-user/per-GPU throughput Pareto frontier. At matched per-GPU throughput, the modeled SubGPU frontier provides up to 2.2x higher per-user throughput than temporal execution, and at matched per-user throughput it provides up to 1.9x higher per-GPU throughput. To test physical feasibility and further validate the simulation results, silicon experiments are performed, using one B200 GPU to emulate a 32-GPU B200 deployment. The experiment evaluates one selected two-stage pipeline configuration at global batch 2,048 using CUDA Green Contexts and TensorRT-LLM kernels. Results show that SubGPU Pipelining improves mean DRAM read-plus-write throughput from 71.8% to 83.6% of peak, and reduces the 36-layer decoder iteration time by 10.33%.

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 · 2026-11-11 09:51 · 最新观测版本

SubGPU Pipelining: Intra-GPU Fine-Grained Spatial Parallelism for LLM Inference

Large language model (LLM) decode is dominated by short, predominantly memory-bound kernels that make bursty use of on-chip execution resources and memory bandwidth. This paper introduces SubGPU Pipelining, a fine-grained, intra-GPU spatial execution model that cuts an operator graph into ordered contiguous segments, binds those segments to spatial stages backed by disjoint streaming-multiprocessor (SM) pools, and streams microbatches through the resulting schedule. Selecting the graph cuts, segment-to-stage binding, per-stage SM allocation, and microbatch size is a coupled optimization problem: each choice changes the overlap pattern, shared-resource contention, cache state, and execution times of the others. We evaluate SubGPU Pipelining through both simulation and silicon experiment using the GPT-OSS 120B workload with 32-GPU B200 deployment settings. The analytical shared-resource simulator searches across SubGPU pipeline structures and batch sizes to map the per-user/per-GPU throughput Pareto frontier. At matched per-GPU throughput, the modeled SubGPU frontier provides up to 2.2x higher per-user throughput than temporal execution, and at matched per-user throughput it provides up to 1.9x higher per-GPU throughput. To test physical feasibility and further validate the simulation results, silicon experiments are performed, using one B200 GPU to emulate a 32-GPU B200 deployment. The experiment evaluates one selected two-stage pipeline configuration at global batch 2,048 using CUDA Green Contexts and TensorRT-LLM kernels. Results show that SubGPU Pipelining improves mean DRAM read-plus-write throughput from 71.8% to 83.6% of peak, and reduces the 36-layer decoder iteration time by 10.33%.

查看此版本解读 →查看此版本原文 ↗