Just a clarification on Kevin Turner's post and a response to David Airey's
question.
David Airey <[email protected]> asked:
> Jobs let loose Apple's new hardware specs. Seems to include multiple
> double precision FPUs. Does this mean Stata can now use the Apple
> velocity engine permute routines?? And 8 gigs of RAM is now possible
> too...
No, we still can't support the Velocity Engine because it does not support
double-precision floating-point. From the PowerPC G5 white paper:
"Each Velocity Engine pipeline speeds up this task by processing up to 128
bits of data, in four 32-bit integers, eight 16-bit integers, sixteen 8-bit
integers, or four 32-bit single-precision floating-point values, all in a
single clock cycle."
Forget the Velocity Engine, what's exciting is in this statement:
"Today's powerful applications demand both precision and performance. That's
why the PowerPC G5 has two double-precision floating-point units, enabling it
to complete at least two 64-bit mathematical calculations per clock cycle. In
fact, each floating-point unit can perform both an add and a multiply with a
single instruction. This dramatically accelerates highly complex computations
that are critical in research simulations and in many of the applications used
to manipulate or render 3D graphics and video content."
So in terms of Stata, there is no need to support the Velocity Engine because
of the high performance FPUs.
We're surprised by the 8 gig memory limitation because a 64-bit processor can
address much more than that but perhaps it's a temporary OS limit that will be
removed once they have a proper 64-bit OS.
Everything else Kevin Turner mentioned still holds true.
Something that surprisingly hasn't been asked is if we're planning on release
an SMP version of Stata for Mac OS X. Currently, no, but only because the
standard we've chosen for SMP is OpenMP which does not currently support OS X.
If and when it does, our plans may change.
-Chinh Nguyen
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
