In this video episode 2.1 we will introduce Intel Xeon Phi coprocessors based on the Intel Many Integrated Core, or MIC, architecture and will cover some of the specifics of hardware implementation
HPC cluster programming model number 1 has been MPI for the past 10 or more years.
In this video we will discuss the general properties of the Intel MIC architecture in detail, and then focus on vector instruction support.
Table of Contents:
We will discuss automatic vectorization feature of the compilers, where it can be used, and how to diagnose it. But this discussion will cover only basic principles of automatic vectorization.
In this episode we will talk about some of the problems you might get while using automatic vectorization feature of Intel compilers.
We will talk about software threads, and particularly multithreading implementation with OpenMP library.
We will introduce private and shared variables, parallel loops and their scheduling.
Let's talk about Fork-Join parallelism.
We will talk about race conditions, synchronization between OpenMP threads, using critical and atomic pragmas.