A Study of Persistent Threads Style GPU Programming for GPGPU Workloads
| Autor: | Kshitij Gupta, John D. Owens, Jeff A. Stuart |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2012 |
| Předmět: |
Speedup
Programming language Computer science GPGPU GPU Computing GPU Programming Style Persistent Threads media_common.quotation_subject Locality Thread (computing) Parallel computing Load balancing (computing) computer.software_genre Programming style Engineering Synchronization (computer science) Parallelism (grammar) Use case General-purpose computing on graphics processing units computer media_common |
| Zdroj: | Gupta, Kshitij; Stuart, Jeff A.; & Owens, John D.(2012). A Study of Persistent Threads Style GPU Programming for GPGPU Workloads. UC Davis: Institute for Data Analysis and Visualization. Retrieved from: http://www.escholarship.org/uc/item/3j76d3td |
| Popis: | In this paper, we characterize and analyze an increasingly popular style of programming for the GPU called Persistent Threads (PT). We present a concise formal definition for this programming style, and discuss the difference between the traditional GPU programming style (nonPT) and PT, why PT is attractive for some high-performance usage scenarios, and when using PT may or may not be appropriate. We identify limitations of the nonPT style and identify four primary use cases it could be useful in addressing -- CPU-GPU synchronization, load balancing/irregular parallelism, producer-consumer locality, and global synchronization. Through micro-kernel benchmarks we show the PT approach can achieve up to an order-of-magnitude speedup over nonPT kernels, but can also result in performance loss in many cases. We conclude by discussing the hardware and software fundamentals that will influence the development of Persistent Threads as a programming style in future systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|