Chapter 13
OpenCL Profiling and Debugging
Introduction
Our motivation for writing programs in OpenCL is not limited to writing isolated high-performance kernels but to speed up parallel applications. Previous chapters discussed how we can optimize kernels running on OpenCL devices by targeting features of the architecture. In this chapter, we discuss how we can study the interaction between the computational kernels on the device and the host. We need to measure the performance and study an application as a whole to understand bottlenecks.
An OpenCL application can include kernels and a large amount of input/output (IO) between the host and device. Profiling such an application can help us to improve performance by answering some of the following ...
Get Heterogeneous Computing with OpenCL, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
