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:
In this video we will talk about running your distributed MPI calculation, and later about file I/O functionality available on Intel Xeon Phi coprocessors.
In this episode 3.8 we will be talking about using multiple coprocessors in a cluster environment.
Next in this episode 3.7 we will look at how to overlap communication of data with computation on the coprocessor and CPU at the same time in the explicit offload model.
In this video we will cover the basics of offload using shared virtual memory. It can be used for sharing complex pointer-based data structures.
In this video we will continue talking about explicit offload programming model, and will cover function offloads, memory re-usage and data retention, as well as asynchronous offload to multiple co
- 1 de 9