You may also refer to the output of the following command to get the most updated information. ‘module avail’ Please refer the table here a rough overview of the available software.
You can connect to HPC by SSH client with the following information. For HPC Coral: SSH (login-0-0): IP: 10.4.1.115 Port: 22 Web (login-0-1): If you need GUI interface, please go to: https://10.4.1.116:4443/nxwebplayer For HPC Jade: IP: 10.4.1.100 Port: 22
GPU accelerated computing offers unprecedented application performance by off-loading compute-intensive portions to the GPU. Each GPU consists of thousands of smaller and more efficient cores for handling multiple tasks. Applications are computed much faster in a parallel computing environment with GPU accelerating. By June 2016, our HPC cluster – Jade supports GPU accelerated computing with 2 NVIDIA K80 […]
Message Passing Interface (MPI) is a standard API for communicating data between distributed processes. It is commonly used in HPC to build applications that can scale to multi-nodes. CUDA-Aware MPI is communicating data between difference GPU processors without staging through system memory. For more detailed information, please refer to the following webpages: An Introduction to CUDA-Aware […]
There are two computing nodes “compute-2-2” and “compute-2-3” installed with one NVIDIA K40m GPU card respectively. You can submit your job to “gpu.q” for using GPU acceleration. Here is an example of submission script for running in a single node: #!/bin/sh #$ -S /bin/bash #$ -cwd #$ -V #$ -N p1 #$ -j y #$ -A username #$ -q […]
Most of the programs, packages and software require re-compilation for supporting GPU acceleration. You can check the list from NVIDIA to see whether your application is supported or not. GPU-ACCELERATED APPLICATIONS: http://www.nvidia.com/content/gpu-applications/PDF/GPU-apps-catalog-mar2015.pdf If you need assistance, please contact email@example.com
You can click here to access the following information. Kindly use the account of HPC to login. The webpage can only be accessed inside campus or by SSL VPN. The overall CPU loading and memory usage of each computing node. The longest waiting time for each user. The expected job finish time for each user. You can also […]