Performance of GTX Titan X GPUs and Code Optimization

TL;DR

This paper evaluates the performance improvements of the GTX Titan X GPU over its predecessor using specific scientific codes, revealing greater-than-expected gains in precision calculations.

Contribution

It provides an empirical performance comparison between GTX Titan X and GTX Titan Black using real scientific codes, highlighting unexpected efficiency gains.

Findings

Significant performance gains in single and double precision calculations

Performance improvements exceed theoretical expectations

Empirical data on GPU performance for scientific computing

Abstract

Recently Nvidia has released a new GPU model: GTX Titan X (TX) in a linage of the Maxwell architecture. We use our conjugate gradient code and non-perturbative renormalization code to measure the performance of TX. The results are compared with those of GTX Titan Black (TB) in a lineage of the Kepler architecture. We observe a significant gain in the single and double precision calculations much greater than the theoretical expectation.