Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911382092382208 |
|---|---|
| author | Xu, Yechen Wang, Yifei Ren, Nathanael Chen, Yiran Zhuo, Danyang |
| author_facet | Xu, Yechen Wang, Yifei Ren, Nathanael Chen, Yiran Zhuo, Danyang |
| contents | Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs, consumer GPUs serve single-user, rapidly changing workloads, and each model's working set often nearly fills the GPU memory. As a result, existing sharing mechanisms (e.g., NVIDIA Unified Virtual Memory) perform poorly due to memory thrashing and excessive use of CPU pinned memory when multiple applications are active.
We design and implement Nixie, a system that enables efficient and transparent temporal multiplexing on consumer GPUs without requiring any application or driver changes. Nixie is a system service that coordinates GPU memory allocation and kernel launch behavior to efficiently utilize the CPU-GPU bi-directional bandwidth and CPU pinned memory. A lightweight scheduler in Nixie further improves responsiveness by automatically prioritizing latency-sensitive interactive jobs using MLFQ-inspired techniques. Our evaluations show that Nixie improves latency of real interactive code-completion tasks by up to $3.8\times$ and saves up to 66.8% CPU pinned memory usage given the same latency requirement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11743 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs Xu, Yechen Wang, Yifei Ren, Nathanael Chen, Yiran Zhuo, Danyang Operating Systems Distributed, Parallel, and Cluster Computing Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs, consumer GPUs serve single-user, rapidly changing workloads, and each model's working set often nearly fills the GPU memory. As a result, existing sharing mechanisms (e.g., NVIDIA Unified Virtual Memory) perform poorly due to memory thrashing and excessive use of CPU pinned memory when multiple applications are active. We design and implement Nixie, a system that enables efficient and transparent temporal multiplexing on consumer GPUs without requiring any application or driver changes. Nixie is a system service that coordinates GPU memory allocation and kernel launch behavior to efficiently utilize the CPU-GPU bi-directional bandwidth and CPU pinned memory. A lightweight scheduler in Nixie further improves responsiveness by automatically prioritizing latency-sensitive interactive jobs using MLFQ-inspired techniques. Our evaluations show that Nixie improves latency of real interactive code-completion tasks by up to $3.8\times$ and saves up to 66.8% CPU pinned memory usage given the same latency requirement. |
| title | Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs |
| topic | Operating Systems Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.11743 |