English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

In this work we explore the performance of CUDA in quenched lattice SU(2)simulations. CUDA, NVIDIA Compute Unified Device Architecture, is a hardwareand software architecture developed by NVIDIA for computing on the GPU. Wepresent an analysis and performance comparison between the GPU and CPU insingle and double precision. Analyses with multiple GPUs and two differentarchitectures (G200 and Fermi architectures) are also presented. In order toobtain a high performance, the code must be optimized for the GPU architecture,i.e., an implementation that exploits the memory hierarchy of the CUDAprogramming model.  We produce codes for the Monte Carlo generation of SU(2) lattice gaugeconfigurations, for the mean plaquette, for the Polyakov Loop at finite T andfor the Wilson loop. We also present results for the potential using manyconfigurations ($50\ 000$) without smearing and almost $2\ 000$ configurationswith APE smearing. With two Fermi GPUs we have achieved an excellentperformance of $200 \times$ the speed over one CPU, in single precision, around110 Gflops/s. We also find that, using the Fermi architecture, double precisioncomputations for the static quark-antiquark potential are not much slower (lessthan $2 \times$ slower) than single precision computations.

SU(2) Lattice Gauge Theory Simulations on Fermi GPUs