Scalable Concurrent Queues for GPU
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917553545150464 |
|---|---|
| author | Shetty, Pratheek Prakash Scogland, Thomas R. W. Feng, Wu-chun |
| author_facet | Shetty, Pratheek Prakash Scogland, Thomas R. W. Feng, Wu-chun |
| contents | Concurrent queues can significantly impact supercomputing performance by being critical bottlenecks for task distribution, load balancing, and resource utilization. As HPC systems move beyond 10-million processor cores, the ability to rapidly move items between producer and consumer threads without excessive locking is essential for efficient queues, preventing idle cores, maximizing utilization, and achieving high parallel speedup. While concurrent queues are well studied on CPUs, they remain largely unexplored on modern GPUs, where SIMT execution, massive parallelism, and atomic contention reshape the design space. We present three linearizable GPU concurrent queues spanning from lock-free to wait-free guarantees: (1) G-WFQ-YMC, an adaptation of Yang and Mellor-Crummey's wait-free queue using preallocated segments; (2) G-LFQ, a bounded lock-free queue that uses wave-batched fast paths to maximize throughput; and (3) G-WFQ, a bounded wait-free queue that packs shared state into 64-bit compare-and-swap operations while preserving linearizability and bounded memory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01693 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scalable Concurrent Queues for GPU Shetty, Pratheek Prakash Scogland, Thomas R. W. Feng, Wu-chun Distributed, Parallel, and Cluster Computing Data Structures and Algorithms D.1.3; C.1.2; C.4 Concurrent queues can significantly impact supercomputing performance by being critical bottlenecks for task distribution, load balancing, and resource utilization. As HPC systems move beyond 10-million processor cores, the ability to rapidly move items between producer and consumer threads without excessive locking is essential for efficient queues, preventing idle cores, maximizing utilization, and achieving high parallel speedup. While concurrent queues are well studied on CPUs, they remain largely unexplored on modern GPUs, where SIMT execution, massive parallelism, and atomic contention reshape the design space. We present three linearizable GPU concurrent queues spanning from lock-free to wait-free guarantees: (1) G-WFQ-YMC, an adaptation of Yang and Mellor-Crummey's wait-free queue using preallocated segments; (2) G-LFQ, a bounded lock-free queue that uses wave-batched fast paths to maximize throughput; and (3) G-WFQ, a bounded wait-free queue that packs shared state into 64-bit compare-and-swap operations while preserving linearizability and bounded memory. |
| title | Scalable Concurrent Queues for GPU |
| topic | Distributed, Parallel, and Cluster Computing Data Structures and Algorithms D.1.3; C.1.2; C.4 |
| url | https://arxiv.org/abs/2606.01693 |