h5part AT lists.psi.ch

Subject: H5Part development and discussion

List archive

Re: [H5part] Performance

From: John Biddiscombe <biddisco AT cscs.ch>
To: Achim Gsell <Achim.Gsell AT psi.ch>
Cc: h5part AT lists.psi.ch
Subject: Re: [H5part] Performance
Date: Wed, 19 Mar 2008 16:59:03 +0100 (CET)
List-archive: <https://lists.web.psi.ch/pipermail/h5part/>
List-id: H5Part development and discussion <h5part.lists.psi.ch>
Organization: cscs

> or the fact that we write a dataset per scalar
>array? If we put all arrays into one big array, I/O will be of course
>faster ...

And this is what we found. I had not however expected it to make an
order of magnitude difference. I'll post some timings once I have
everything organized.

JB

[H5part] Performance, John Biddiscombe, 03/19/2008
- Re: [H5part] Performance, Andreas Adelmann, 03/19/2008
  - Re: [H5part] Performance, Achim Gsell, 03/19/2008
    - Re: [H5part] Performance, John Biddiscombe, 03/19/2008