GPGPU-Sim：一款支持Nvidia的CUDA和OpenCL并行编程模型的仿真器

最新推荐文章于 2025-07-04 00:13:13 发布

原创最新推荐文章于 2025-07-04 00:13:13 发布 · 2.3k 阅读

1 ·

CC 4.0 BY-SA版权

SoC设计空间探索专栏收录该内容

11 篇文章

订阅专栏

GPGPU-Sim是一款详细的GPU模拟器，支持NVIDIA的Fermi及GT200架构，并能运行CUDA和OpenCL工作负载。它包含了一个集成的能量模型GPUWattch，可在UBC由Tor Aamodt及其研究生团队进行开发。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

GPGPU-Sim

Welcome to the GPGPU-Sim webpage. GPGPU-Sim provides a detailed simulation model of a contemporary GPU (such as NVIDIA's Fermi and GT200 architectures) running CUDA and/or OpenCL workloads and now includes an integrated (and validated) energy model, GPUWattch.

GPGPU-Sim is available on github here.

You can download our fully setup virtual machine here.

A manual can be found here. If you wish to report a bug, go here. Note that use of GPGPU-Sim does not imply support. However, if you have questions, you may want to sign up to the GPGPU-Sim Google Group. The google group is moderated which means it may take some time to see your question posted.

Slides from our most recent tutorial at MICRO 2012 can be found here.

GPGPU-Sim is developed at UBC by Tor Aamodt along with his graduate students.