CCMS

Center for Computational Materials Science
Institute for Materials Research,
Tohoku University

Supercomputing system trial usage

1. Outline

"Can I run a program that I used on my PC with the supercomputer?"
"Can applications available at the Center for Computational Materials Science be used for my research?"
There is a demand for trying these and others.

With this usage frame, you can try out the supercomputing system for up to two weeks. Currently, it takes time to apply for the supercomputing system because it is necessary to apply for the research project, to examination and to adopt it.
Therefore, we will provide "Supercomputing System Trial ". Applicants can use the supercomputing system for up to two weeks before applying for joint use issues. We hope to improve convenience for researchers and promote research.

2. Qualification for use

Those who fall under any of the following and do research on materials science field.

  1. Those who belong to Institute for Materials Science, Tohoku University
  2. Researchers belonging to national, public, and private universities and national and public research institutes

3. Available computing resources

Supercomputing system of Center for Computational Materials Science, Institute for Materials Research, Tohoku University (Cray XC50-LC and Cray CS-Storm 500GT)

System Name Supercomputer Parallel Computing &
Informatics Server
Model Cray XC50-LC Cray CS-Storm 500GT HPE ProLiant DL360 Gen10
total nodes

computing node:
 293 nodes
I/O node, etc:
 27 nodes

29 nodes

29 nodes

CPU

Intel Xeon Gold 6150

  1. frequency:
     2.7 GHz
  2. number of cores:
     18 cores/CPU
  3. number of CPUs:
     2 CPUs/node

Intel Xeon Gold 6150

  1. frequency:
     2.7 GHz
  2. number of cores:
     18 cores/CPU
  3. number of CPUs:
     2 CPUs/node

Intel Xeon Gold 6154

  1. frequency:
     3.0 GHz
  2. number of cores:
     18 cores/CPU
  3. number of CPUs:
     2 CPUs/node
Accelerator -

NVIDIA Tesla V100 for PCIe

  1. performance:
     7.0 TFLOPS
  2. number of GPU cores:
     5,120 cores/GPU
  3. number of GPUs:
     10 GPUs/node
-
memory size 768 GiB/node 768 GiB/node 576 GiB/node
Theoretical peak performance 3.03 PFLOPS
(CPU: 1.00 PFLOPS, GPU: 2.03 PFLOPS)
100.22 TFLOPS
total number of CPU cores 11,592 cores 1,044 cores
total number of GPU cores 1,484,800 cores (290 GPUs) -
total memory size 241.6 TiB 16.3 TiB

4. Node hour and usage fee

4.1 Available node hour

*The supercomputer's node time is up to 50 hours.
When using the application for PC, use the computer installed in Supercomputer building development room 1.
Trial availability time: from 9:00 to 17:00 except Saturdays, Sundays, and holidays

4.2 Usage fee

Usage fee would not be collected.

5. Rules of trial usage

  1. The maximum trial period is two weeks
  2. Applications are limited to once per year, so applicants can only try
  3. As for the result obtained in the trial period, it can not be announced at the paper, the conference etc. If it is to be announced, please apply for collaborative research at the CCMS
  4. You can not copy, modify, redistribute applications
  5. No report submission is required for the work done during the trial period
  6. We will not assume any responsibility for any loss or damage caused by trial of this system
  7. If you wish to use the supercomputing system after the expiration of the expiration date, you will need to apply for collaborative research on CCMS, IMR
  8. Travel expenses etc are not paid to users

6. How to apply

Click on the "Application for trial" for the flow on the previous page.