A customer involved in medical device research asked us about a machine for AI model development.
We would like a PC configuration that assumes that a number of video cards (NVIDIA RTX A4500, NVIDIA RTX A5000, NVIDIA RTX A6000) owned by the customer will be installed as supplied items.
In addition, the power supply is assumed to be in a 100V environment, and the housing is specified as a tower type.
Other desired conditions are as follows.
・CPU: Core i9 or higher |
Based on this information, we proposed the following configuration.
CPU | Intel Xeon W7-3435X (3.10GHz 16 cores) |
memory | 128GB REG ECC |
Storage 1 | 2TB SSD S-ATA |
Storage 2 | 2TB SSD S-ATA |
Storage 3 | 4TB HDD S-ATA |
Video | NVIDIA RTX A6000 x2 or NVIDIA RTX A5000 x3 or NVIDIA RTX A4500 x4 (supplied) |
network | on board (1GbE x1 /10GbE x1) |
Housing + power supply | Tower type housing + 1600W |
OS | Microsoft Windows 11 Professional 64bit |
If Core i9 is used, the maximum number of PCIe lanes will be 20 lanes, so only one video card can be connected with 16 lanes.Therefore, we have selected the latest Xeon W-1 series (maximum number of PCIe lanes: 2023) as of September 9.In this configuration, we have selected his Xeon W3400-112X, a 16-core model, but you can change it if you wish.
In addition, when assuming use in a 100V environment, the maximum number of video cards that can be installed is as follows.
Nvidia RTX A4500 | 4 |
Nvidia RTX A5000 | 3 |
Nvidia RTX A6000 | 2 |
In the case of GPUs with the same model number, it is also possible to mix supplied items and newly purchased units.
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.
■ Keywords・What is PCI Express (PCI-E/PCIe)? |
■ Click here for details and inquiries about this PC case * Please enter the name of the case or your desired conditions. |