Application of Heterogeneous Computing Techniques for the Development of an Image-Based Hot Spot Detection System Using MTCA

Image-based diagnostics are key for fusion experiments. The operating conditions at ITER and the future machines require changing role of such systems from monitoring archiving offline postprocessing to real-time processing. One roles is machine protection. A relevant application vision wall divertor temperature hot spot detection. However, algorithms detection computationally costly. To achieve performance required time resolution all these experiments, evaluating validating newest technologies vital. This work applies heterogeneous computing techniques based on OpenCL standard problem obtains values in a Micro Telecommunications Computer Architecture (MTCA) platform. reduces development time, improves portability, simplifies evaluation validation each part algorithm find best-suited device system. proposed solution enables balancing computational load between field-programmable gate array (FPGA) graphical processing unit (GPU). has been adapted optimized, taking profit particularities