All Products
Search
Document Center

Overview

Last Updated: Oct 13, 2021

This topic provides an overview of the best practices for performing high-performance computing on an Elastic High Performance Computing (E-HPC) cluster in different scenarios.

Scenario

Description

Use the HPL benchmark to test the FLOPS of an E-HPC cluster

High-Performance Linpack (HPL) is a benchmark that is used to test the floating-point operations per second (FLOPS) of high-performance computing clusters. HPL can evaluate the floating-point computing power of high-performance computing clusters. The evaluation is based on a test for solving dense linear unary equations of Nth degree by using Gaussian elimination.

Use STREAM to test the memory bandwidth performance of an E-HPC cluster

STREAM is a benchmark tool that is used to measure the performance of memory bandwidth. It is also a general-purpose tool that you can use to measure the memory performance of servers. STREAM supports four vector kernels: Copy, Scale, Add, and Triad. These vector kernels are used to measure the performance of memory bandwidth.

Use IMB and an MPI library to test the communication performance of an E-HPC cluster

Intel MPI Benchmarks (IMB) is a piece of software that is used to measure the performance of point-to-point and global communication operations in an HPC cluster for various message sizes. Message Passing Interface (MPI) is a communication library for parallel computing. MPI supports multiple programming languages and provides benefits such as high performance, concurrency, portability, and scalability.

Test the performance of an SCC instance

Super Computing Cluster (SCC) instances support low-latency networking by using remote direct memory access (RDMA). This meets the parallel computing requirements of E-HPC clusters. SCC instances have no performance loss in virtualization and can be isolated by virtual private cloud (VPC). You can have direct access to hardware resources.

Use LAMMPS to perform high-performance computing

Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) is a classical molecular dynamics program. It has potentials for solid-state materials (metals, semiconductors), soft matter (biomolecules, polymers), and coarse-grained or mesoscopic systems.

Use GROMACS to perform high-performance computing

GROningen MAchine for Chemical Simulations (GROMACS) is a full software package. It is used to perform molecular dynamics by simulating Newtonian equations of motion for systems that include millions of particles. GROMACS is used for nucleic acid analysis of biochemical molecules such as proteins and lipids that have various complex bonded interactions.

Use OpenFOAM to perform high-performance computing

Open Source Field Operation and Manipulation (OpenFOAM) is a C++ toolbox for the development of customized numerical solvers, and pre-/post-processing utilities for the solution of continuum mechanics problems, including computational fluid dynamics (CFD).

Use WRF to perform high-performance computing

Weather Research and Forecasting Model (WRF) is a next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. WRF can produce simulations based on actual atmospheric conditions or idealized conditions. The model serves a wide range of meteorological applications. It features a software architecture that allows for parallel computation and system extensibility.

Configure auto scaling

If you need to submit jobs at any time, use an E-HPC cluster to perform large-scale computing for several hours, and then release nodes, you can configure different scaling policies for different job types.

Use BWA, GATK, and SAMtools to perform high-performance computing

When you perform DNA sequencing, you can use the Burrows-Wheeler Alignment (BWA) tool to build indexes and generate alignments, use SAMtools to sort the alignments, and then use the Genome Analysis Toolkit (GATK) to remove duplicates, recalibrate base quality scores, and discover variants.