2019/05/10 by Connor Kenyon, Kenyon, Connor, Glenn Volkema +3
Computer Science · Physics and Astronomy · #Advanced Data Storage Technologies #Computational Physics (physics.comp-ph) #Distributed #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #FOS: Physical sciences #Parallel #Parallel Computing and Optimization Techniques #and Cluster Computing (cs.DC) #cs.DC #physics.comp-ph
paper · pdf · doi:10.48550/arxiv.1905.05175
9 pages, 10 figures
arxiv created 2019/05/10 · openalex publication_date 2019/05/10 · arxiv updated 2019/05/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The performance of discrete general purpose graphics processing units (GPGPUs) has been improving at a rapid pace. The PCIe interconnect that controls the communication of data between the system host memory and the GPU has not improved as quickly, leaving a gap in performance due to GPU downtime while waiting for PCIe data transfer. In this article, we explore two alternatives to the limited PCIe bandwidth, NVIDIA NVLink interconnect, and zero-copy algorithms for shared memory Heterogeneous System Architecture (HSA) devices. The OpenCL SHOC benchmark suite is used to measure the performance of each device on various scientific application kernels.