HackerPapers

arXiv:1005.2581cs.PF

A Performance Comparison of CUDA and OpenCL

Kamran Karimi, Neil G. Dickson, Firas Hamze

Abstract

CUDA and OpenCL are two different frameworks for GPU programming. OpenCL is an open standard that can be used to program CPUs, GPUs, and other devices from different vendors, while CUDA is specific to NVIDIA GPUs. Although OpenCL promises a portable language for GPU programming, its generality may entail a performance penalty. In this paper, we use complex, near-identical kernels from a Quantum Monte Carlo application to compare the performance of CUDA and OpenCL. We show that when using NVIDIA compiler tools, converting a CUDA kernel to an OpenCL kernel involves minimal modifications. Making such a kernel compile with ATI's build tools involves more modifications. Our performance tests measure and compare data transfer times to and from the GPU, kernel execution times, and end-to-end application execution times for both CUDA and OpenCL.

arXiv comments
12 pages, 6 Tables, 5 Figures
Journal reference
DOI
Subjects
cs.PFPerformance cs.DCDistributed, Parallel, and Cluster Computing physics.comp-phComputational Physics

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Aug 2015 to Apr 2016.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. The Nvidia DGX-1 Deep Learning Supercomputer in a Box 1 comment

    • I haven't seen any recent benchmarks, but ones from 2011 all seemed to show CUDA and OpenCL on open footing in terms of performance when optimised properly.[1][2] CUDA simply had better library support, and a more well defined and uniform architecture to target. Whereas OpenCL…

      RobadobView on HNParent context

  2. Deep Learning Courses 1 comment

    • Need to run empirical benchmarks. CUDA is usually faster. I'd like to run my own benchmarks with nd4j though. We have our own benchmark setup that works for every backend. It allows us to do some interesting things. Cuda itself is usually faster with data transfer latency…

      agibsoncccView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.