An interesting use of HPC technologies is in the area of understanding the propagation of radio frequency energy in an outdoor environment. The RF energy propagates partially in a line-of-sight manner but also interacts with the environment. Simulations of how the waves travel must also take into account refraction and reflection of items in the environment.
Taking direction and experience from a computer graphics in which rays are traced to determine the color of a pixel, the same techniques can be applied to tracing RF waves. In many instances, the number of rays that would need to be traced are in the 100’s of millions. Applications of this type need to be completed in seconds to minutes to be useful. Since the tracing of each ray is independent of another ray, this type of application can be distributed easily among the many cores of the Intel Xeon Phi coprocessor.
Various optimization techniques can be used to take advantage of the Intel Xeon CPU and the Intel Xeon Phi coprocessor. Using OpenMP, many threads can be created and the assigned computation can be sent to the Intel Xeon Phi coprocessor cores. However, since each thread may take different amounts of time due to the nature of ray tracing, performance can suffer if the workloads are not distributed properly. Task level parallelism can be used to take better advantage of the Intel Xeon Phi coprocessor. Overall, the computation, measured in terms of seconds per frame improves by about a factor of two.
Source: Survice Engineering, USA
New Tools, New Rules Create faster code—faster—with the new Intel® Parallel Studio XE. Try it today.
