Applications Performance on GPGPUs with the Fermi Architecture
The University of Edinburgh
The University of Edinburgh, 2011
@article{abdalla2011applications,
title={Applications Performance on GPGPUs with the Fermi Architecture},
author={Abdalla, A.M.H.},
year={2011}
}
The latest GPU architecture released by Nvidia, code-named "Fermi", is the most advanced computing GPU architecture ever built. Radical changes took place on the GPU computing architecture compared to Fermi’s predecessors such as the GT200 series and the G80s. In this dissertation the Fermi architecture is analysed, addressing the most prominent upgrades, by running extensive benchmark tests. These benchmarks included Nvidia’s own SDK package, the Scalable Heterogeneous Computing benchmark suite and the NAS Parallel Benchmark suit. All the benchmarks are described in detail and their results are analysed, and verify Fermi’s expected performance results.
November 29, 2011 by hgpu
