view article
Figure 4
An overview of the maximum throughput in data paths (1, 2.1, 2.2, 3) inside a backend processing computer. Because of the lack of existing RDMA-compatible detectors, such a detector was simulated by a workstation. The processing computer embeds a NVIDIA QUADRO P6000 GPU accelerator. The GPUDirect technology (step 2) allows bypassing the extra copy in the central memory (steps 2.1 and 2.2).

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 27| Part 5| September 2020| Pages 1297-1306
https://doi.org/10.1107/S1600577520008140
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS