Half precision floats are 16-bit floating-point numbers, which are half the size of traditional 32-bit single precision floats, and have lower precision and smaller range.
Threading Intel® Integrated Performance Primitives Image Resize with Intel® Threading Building BlocksThreading Intel® IPP Image Resize with Intel® TBB.pdf (157.18 KB) :
This is the first article in a series of articles about High Performance Computing with the Intel® Xeon Phi™ coprocessor.
One of the big new features introduced in the Intel® Math Kernel Library (Intel® MKL) 11.2 is the greatly improved performance for small problem sizes.
The code samples for the webinar "Further Vectorization Features of the Intel® Compiler" given on 4/7/2015 are attached below.