Programming Guide


Performance Tuning Cycle

The goal of the performance tuning cycle is to improve the time to solution whether that be interactive response time or elapsed time of a batch job. In the case of a heterogeneous platform, there are compute cycles available on the devices that execute independently from the host. Taking advantage of these resources offers a performance boost.
The performance tuning cycle includes the following steps detailed in the next sections:
  1. Establish a baseline
  2. Identify kernels to offload
  3. Offload the kernels
  4. Optimize
  5. Repeat until objectives are met

Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at