Case No.PC-10865A customer who viewed our website asked us about a workstation for conducting physical property research using the materials science software ``VASP''.
It is assumed that the electronic state of the surface of a system consisting of a metal such as iron, its oxide film, and a polymer placed at the interface will be calculated using several hundred atoms.
We also plan to perform first-principles molecular dynamics calculations in the future, and would like a workstation suitable for these applications.
The desired conditions are as follows, and we have heard that if it is possible to perform high-speed calculations at a lower cost, we would like to consider calculations using GPUs.
|
・CPU: 12 cores or more (preferably 18 cores or 24 cores) |
Based on the information you provided, we have proposed the following configuration.
| CPU | Intel Xeon W7-2495X (2.50GHz 24 cores) |
| memory | 128GB REG ECC |
| storage | 1TB SSD S-ATA |
| video | NVIDIA T400 4GB |
| network | on board (2.5GbE x1 /10GbE x1) |
| Housing + power supply | Tower type housing + 1000W |
| OS | Ubuntu 22.04 |
This configuration is equipped with the latest 4th generation Xeon Scalable series.
We have selected Intel Xeon W24-7X, a 2495-core product, but you can change it if you wish.
The memory capacity is 200GB, assuming calculations with a maximum of about 128 atoms.
If you plan to calculate more atoms than this, please consider expanding the memory capacity to 256GB.
Storage is equipped with 1TB SSD S-ATA according to your wishes.
Up to two HDDs can be installed, so please let us know if you wish to change the storage configuration.
When comparing the CPU calculation specification and the GPGPU specification, the GPGPU specification has an advantage in high-precision calculation, but the CPU calculation specification has an advantage in terms of price.
In the official document regarding GPGPU support for VASP, when using GPGPU, it is required to use a GPU with high double precision arithmetic (fp64) performance.
In addition, the online manual below clearly states that the GeForce series and RTX series for workstations are not suitable.
reference:OpenACC GPU port of VASP – Vaspwiki ■Jump to external site
NVIDIA's current products include the A64 and H100 as GPUs that take fp100 performance into consideration, but these products are more expensive than the price of the machine in this case alone.Also, due to the specifications of the card's cooling method, it must be used in a dedicated GPGPU chassis.
Based on the above points, in this case study we are introducing CPU calculation specifications that give priority to price.
The configuration of this case study is based on the conditions given by the customer.
We will flexibly propose machines according to your conditions, so please feel free to contact us even if you are considering different conditions than what is listed.
|
■ Click here for details and inquiries about this PC case
* Please enter the name of the case or your desired conditions. |
