<div dir="ltr">Hi Louis,<br><br><div><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div><div>
Does ParaView read data in parallel regardless of whether the file is decomposed in space and/or time?</div></div></blockquote><div><br></div><div>Space, yes. Time, not really, at least not without writing a custom reader.<br> <br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div><div style="direction:ltr;font-family:Tahoma;color:rgb(0,0,0);font-size:10pt">Would it be faster to read decomposed files vs. reading one large file?<br></div></div></blockquote><div><br></div><div>This is something that will be dependent on the file format yuou're using. It will most certainly be faster to read the data in parallel, spatially decomposed, and most of the parallel readers support an N -> M IO mapping, that is, using a different number of readers than there are spatial partitions. As to using one big file or not, well, some parallel file formats support it, some dont. Just make sure you use a file format that supports the spatial decomposition, whether thats as one file per partition-timestep, one file per-timestep with multiple partitions per file, or everything in one file with multiple partitions adn timesteps per file. Your bottlenext in IO will likely be the write time anyways and as long as the file format your using supports parallel reads then how that's laid out, whether in a single file or multiple files, will probably not have a significant impact.<br></div><div><br><br clear="all"><div><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr">----------<br>Chuck Atkins<br>Staff R&D Engineer, Scientific Computing<br>Kitware, Inc.<br><br></div></div></div></div></div></div></div></div></div></div></div></div>