Roadmap: Introduction to Advanced Cluster Architectures
Advanced clusters for High Performance Computing (HPC), such as the Frontera and Stampede2 supercomputers run by the Texas Advanced Computing Center (TACC), are powered by a large number of multi-core processors, abundant memory and cache, and fast interconnects. The Frontera and Stampede2 supercomputers use processors from the Intel Xeon Scalable Processor (SP) product line: Stampede2 is built in part using Intel Skylake processors, and Frontera leverages Intel Cascade Lake chips.
This topic presents the salient characteristics of these clusters and of both these processors, which represent the first two generations of the Intel Xeon Scalable Processor product line. Stampede2 also contains nodes based on a third-generation SP processor, Ice Lake, which were added in 2022. While we focus on the earlier Intel Xeon Scalable Processors, much of the material in this topic is generally applicable to other advanced cluster architectures built out of a large number of multi-core nodes, providing information on how to effectively use such hardware and scale applications for larger problem sizes.
Objectives
After you complete this roadmap, you should be able to:
- Identify features of Intel Xeon Scalable Processors and their deployment in large clusters such as Stampede2 and Frontera at TACC
- Describe the software elements that a code must possess to produce a scalable application on a large cluster that incorporates multi-core processors
- Name the software tools that are available to help you improve your application's performance on Stampede2 and Frontera
Prerequisites
- Familiarity with High Performance Computing (HPC) concepts. Those who are less conversant with HPC terms and techniques should be prepared to inspect the glossary terms rather frequently. It may also be helpful to review Cornell Virtual Workshop content on Parallel Programming Concepts and High-Performance Computing and either MPI or OpenMP.
- Programming experience in C or Fortran. Introductions to C and Fortran are available, though the reader will need to look elsewhere for a full tutorial on these languages.
- Readers who need an introduction to either Stampede2 or Frontera will find it helpful to first review one of more of the following items: the Stampede3 User Guide, the Stampede2 Environment CVW material, the Frontera User Guide, and the Getting Started on Frontera CVW material.
Requirements
As a goal of this material is to help you use multi-core processors and associated clusters effectively, the presentation is interspersed with short exercises to highlight features as they are discussed. Examples are designed to run on the Skylake (SKX) nodes on TACC's Stampede2 system, with some information about minor modifications needed to run on Frontera instead.
Accordingly, system requirements include:
- A workstation running Windows 10 or above, macOS, or Linux, as these operating systems include the OpenSSH software necessary to connect to an HPC cluster such as Stampede2 or Frontera.
- Access to Stampede2 or Frontera at TACC is recommended; the material, however, is broadly applicable to other clusters built out of Intel Xeon Scalable Processors, and—to a lesser extent—other advanced clusters constructed from large numbers of multi-core processors.