What is useful is to have several demos that have varying degrees of parallelism (or more properly, more degrees of embarrassing).
For instance, if you¹re doing a render farm for frames, and you farm out frame 1,11,21, etc to node 1, 2,12,22 to node 2, etc. Parallel POVray is similar: each processor makes a piece of the image. But then there are things where there¹s more processor:processor interaction. At a next step, you might have a finite element gridded thing, where there are interactions at the boundaries where you divided the grid onto nodes, but not for elements in the middle of the grid segment. For each time step, you calculate the new grid values based on the old ones (including those that you received from other nodes). Finally, there are ones where essentially every element interacts with every other one. Gravity simulations with large numbers of bodies are an example: to calculate the next step, you need to do a pairwise evaluation between all O(N^2) pairs. This would nicely demonstrate that interconnect speed has more effect on some problems than others. On 2/1/16, 7:57 AM, "Beowulf on behalf of Olli-Pekka Lehto" <beowulf-boun...@beowulf.org on behalf of olli-pekka.le...@csc.fi> wrote: >We're in the process of developing a demo Beowulf cluster in the spirit >of Tiny Titan (http://tinytitan.github.io/). However, the one we are >working on is based on 10 Intel i7 small-form-factor boards with a fairly >good per-core compute capability. > >I'd be interested to hear if you have some ideas (or even pointers to >code!) for demonstrating HPC concepts to the general public. Especially >having an element of interactivity would be nice. > >Couple of low-hanging fruits that we are already looking at are >Blender/povray-rendering and porting the existing Tiny Titan codes. > >Best regards, >Olli-Pekka >-- >Olli-Pekka Lehto >Development Manager >Computing Platforms >CSC - IT Center for Science Ltd. >E-Mail: olli-pekka.le...@csc.fi >Tel: +358 50 381 8604 >skype: oplehto // twitter: ople >_______________________________________________ >Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing >To change your subscription (digest mode or unsubscribe) visit >http://www.beowulf.org/mailman/listinfo/beowulf _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
