Parallelizing TriScatteredInterp() on ANSYS Fluent output data

Howdy. I am trying to generate contour/vector plots for about 15 thousand time steps of a transient computational fluid dynamics solution. I've successfully used TriScatteredInterp to interpolate scattered nodal data onto the output of meshgrid/ndgrid, but the operation is time consuming (I start with about 52 thousand nodes, and that's just on the plane I am generating plots for -- if I was doing this in 3D there would be millions). By "time consuming" I mean it is taking on the order of several seconds (maybe ten?) for a single time step. I have twelve cores to play with, so I can cut it down by an order of magnitude if I use parfor (does anyone have any experience with this?). But I was really hoping that I could use the GPU (Quadro FX 3800, 192 processors) to do this. However, it appears that this is not supported ( http://www.mathworks.com/help/toolbox/distcomp/bsic4n4-1.html ). Does anyone have any suggestions as to how I can significantly cut down the time required for my post-processing? Thanks!

[Walter Roberson]

I wonder if Accelereyes' Jacket could be of assistance in this?