A customer consulted with us about a machine for calculating linear linear equations using MATLAB.
Currently, machines with the following specifications are used.
CPU: Core i5
In the case of this machine, it is possible to calculate about n = 4000, but there is a problem that it cannot be calculated if n = 16000 is exceeded.
Ultimately, I would like to consider a dedicated machine that can calculate up to n = 60000 with a budget of about 100 million yen.
Since memory capacity is important for linear calculations in MATLAB, we considered a configuration that prioritized memory capacity within the budget.
In the interview with the customer, it was speculated that the reason why the calculation of n = 16000 was not possible on your PC was related to the memory capacity overrun of the matrix size, so n = 60000. The large capacity of 256GB is used so that the memory will not run out during the calculation.
The CPU is equipped with a 14-core Xeon W-2275, which has improved performance compared to the Core i5.
However, it is hard to say that "the speed will improve as the number of cores increases" because it depends on how the code is written whether the calculation speed will improve in actual use.It seems that the parallelization on the code side depends on how effective it is.When considering the introduction of a machine based on this configuration, we would appreciate it if you could check the status on the code side as well.
|CPU||Xeon W-2275 (3.30GHz 14 cores)|
|memory||256GB REG ECC|
|storage||1TB SSD M.2|
|network||on board (10/100 / 1000Base-T x1 5G x1)|
|Housing + power supply||Middle tower case + 850W|
|OS||Windows 10 Professional 64bit|
■ Click here for details and inquiries about this PC case
* Please enter the name of the case or your desired conditions.