Profiling code and improving GPU performance

This chapter presents two advanced topics for better utilization of GPUs on computationally intensive applications: (i) profiling a code running on GPUs, and (ii) improving GPU performance. Didactical examples are given in this chapter for the reader to understand these topics. Moreover, best practices that you should follow to improve GPU performance are discussed in detail. After reading this chapter, you should be able to: • Utilize the MATLAB profiler to find the bottlenecks in files running on the CPU.