You are not logged in. Please login or register.

Forum updated

We have recently updated our forums system, and we have cleared all spam topics and users. In case we accidentally deleted your account, please register again. If you miss a topic you have posted before, please let us know.

Post new reply

Post new reply

Compose and post your new reply

You may use: BBCode Smilies

All fields with bold label must be completed before the form is submitted.

Required information for guests


Required information

Topic review (newest first)

3

Hi,

Thanks for the reply. I have read through the FAQ page, but I was hoping you may have some testing data using a SSD for comparison. My understanding is that the access speeds are typically significantly  faster for SSDs, and fragmentation is not an issue. However, if you are suggesting RAM memory access is the 'weak link', the case may be that the addition of a SSD would only significantly impact on overall performance of ATENA if the HDD was fragmented and bottlenecking the performance of the system as a whole.

2

Hello, the main advantage of SSDs is much reduced sensitivity to mechanical shocks and vibrations compared to traditional rotating HDDs. A few months ago there was a speed advantage in reading SSDs over HDDs, but writing them was slower - I guess this is changing, too, but we have conducted no comparisons. The concrete bottleneck during analysis depends on many factors, including the concrete model and mesh. According to our observations, RAM memory access is typically the weakest link. Saving results can also significantly affect the performance, if the disk is very fragmented and/or very many results are stored (e.g., after each step instead of only every 10th step).

I assume you have already read the article "I plan to buy a new PC to run ATENA on it, what do you recommend?" from out FAQ page at http://www.cervenka.cz/faq

1

Hi,

Just wondering if there is any benefit in running ATENA using a solid state drive that might justify the use of one. Is there a significant performance increase or is the analysis process bottlenecked elsewhere? For reference, the system I am using has a NVIDIA Quadro 2000 video card and an Intel Xeon W3565 CPU with 12GB of RAM. Thanks.