9-15 June 2018
Woodlands Conference Center
America/New_York timezone
**** See you at Real Time 2020 ****

FPGA acceleration of Model Predictive Control for ITER Plasma current and shape control

12 Jun 2018, 14:40
1h 30m
Woodlands Conference Center

Woodlands Conference Center

159 Visitor Center Dr, Williamsburg, VA 23185
Poster presentation Control, Monitoring,Test and Real Time Diagnostics Systems Poster 1

Speaker

Dr Samo Gerksic (Jozef Stefan Institute)

Description

A faster implementation of the Quadratic Programming (QP) solver used in the Model Predictive Control scheme for ITER Plasma current and shape control was developed for Xilinx Field-Programmable Gate Array (FPGA) platforms using a high-level synthesis approach. The QP solver is based on the dual Fast Gradient Method (dFGM). The dFGM is essentially an iterative algorithm, where matrix-vector arithmetic operations within the main iteration loop may be parallelized. This type of parallelism is not well-suited to standard multi-core processors because the number of operations to be spread among processing threads is relatively small considering the time-scale of thread scheduling. The FPGA implementation avoids this issue, but it requires specific techniques of code optimization in order to achieve faster solver execution.

Description FPGA control
Speaker Samo Gerksic
Country Slovenia
Institute Jozef Stefan Institute
Minioral Yes

Primary authors

Dr Samo Gerksic (Jozef Stefan Institute) Dr Bostjan Pregelj (Jozef Stefan Institute) Dr Matija Perne (Jozef Stefan Institute)

Presentation Materials