CCL: Computing on graphical processors

As others have noted, wide availability, low cost (driven by the gaming
 market), and existing toolkits have favored using GPUs, which typically have
 several FPUs on board.  Some tinkering is required to get the best performance,
 based on a talk I heard recently.  A current limitation is that most of the FPUs
 are single precision (32-bit f.p.), which is sufficient for graphics rendering.
 Rick Venable    5635FL/T906
 Membrane Biophysics Section
 NIH/NHLBI Lab. of Computational Biology
 Bethesda, MD  20892-9314   U.S.A.
 (301) 496-1905  venabler AT nhlbi*nih*gov
 -----Original Message-----
 > From: John McKelvey jmmckel,, [mailto:owner-chemistry()]
 Sent: Sat 16-Feb-08 8:11 PM
 To: Venable, Richard (NIH/NHLBI) [E]
 Subject: CCL: Computing on graphical processors
 It seems that there is beginning to be significant efforts to do processing
 using video card processors.   Could someone comment on this as to why this
 is being so successful [probably many factors, I suppose], what kinds of
 computations work well on them, and what kinds of work probably do not work
 well on them.... and why?
 John McKelvey