High Throughput Low Latency Online Image Processing by GPU/FPGA Coprocessors Using RDMA Techniques
TimeTuesday, 17 November 20208:30am - 5pm EST
DescriptionThe constant evolution of X-ray photon sources associated with the increasing performance of high-end X-ray detectors allows cutting-edge experiments generate large volumes of data that are challenging to manage and store. These data management challenges have still not been addressed in a fully satisfactory way as of today, and in any case, not in a generic manner.
This thesis is part of the ESRF RASHPA project that aims at developing an RDMA-based Acquisition System for High Performance Applications. One of the main characteristics of this framework is the direct data placement, straight from the detector head (data producer) to the processing computing infrastructure (data receiver), at the highest acceptable throughput, using RDMA techniques.
The work carried out in this thesis is a contribution to the RASHPA framework, enabling data transfer directly to the internal memory of accelerator boards. A low-latency synchronisation mechanism is proposed to trigger data processing while keeping pace with the detector. Thus, a comprehensive solution fulfilling the online data analysis challenges is proposed on standard computer and massively parallel coprocessors as well.
Scalability and versatility of the proposed approach is exemplified by detector emulators, leveraging RoCEv2 or PCI-e and RASHPA Processing Units (RPUs) such as GPUs and FPGAs. Real-time data processing on FPGA, seldom adopted in X-ray science, is evaluated and the benefits of high level synthesis are exhibited. The assessment of the proposed data analysis pipeline includes raw data pre-treatment for Jungfrau detector, image rejection using Bragg's peaks counting and data compression to sparse matrix format.