- Descripción general
In Episode 10 of the “Hands-On Workshop (HOW) Series on Parallel Programming and Optimization with Intel® Architectures” we present additional topics on optimization.
We show how to use the performance analysis tool Intel® VTune™ Amplifier XE on the host and on Intel® Xeon Phi™ coprocessors to detect hotspots and diagnose general performance issues.
We also demonstrate the capabilities of the Intel® Math Kernel Library (Intel® MKL), including automatic offload to Intel Xeon Phi coprocessors.
In the hands-on part of the episode, we show the procedure for starting and using Intel VTune Amplifier XE to analyze an application for Intel Xeon Phi coprocessors, and use Intel MKL to scale general matrix-matrix multiplication to multiple coprocessors.