Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm quite new to HPC environment. Is there any difference in running a job on a node utilizing 8 cores and running the same job on 8 nodes utilizing I core in terms of performance or walltime used.

PS: I'm working on a project which involves running a script in the cluster which takes around 2-3 days for the output. Hence such a doubt to avoid irrelevant tests.

share|improve this question

closed as too broad by devicenull, Falcon Momot, mdpc, Ward, Tom O'Connor Aug 30 '13 at 7:12

There are either too many possible answers, or good answers would be too long for this format. Please add details to narrow the answer set or to isolate an issue that can be answered in a few paragraphs.If this question can be reworded to fit the rules in the help center, please edit the question.

It mostly depends on how much your processes need to talk to each other. Even Infiniband is going to be slower than a connection purely local to a node. – Michael Hampton Aug 30 '13 at 3:19

Probably, yes. It's hard to tell which will be faster though because there are a lot of factors. If possible, run a smaller version of your program so that you can compare both. Here are some factors that affect performance:

  • Interprocess communication (as Michael mentioned in his comment): Communication between cores on the same node is faster than Infiniband.
  • Resource competition: Processes/threads running on the same node must share resources like I/O (disk and network) and memory.

If this is a CPU-bound application and you have 8 nodes available, you might consider using all 64 cores.

share|improve this answer

Not the answer you're looking for? Browse other questions tagged or ask your own question.