[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Allegro 4.1 on a Sparc 10



> Howdy -
> 
> I'm sending this as a bug-report as well as to the mailing list
> because I'm hoping to get some information from both Franz and other
> Allegro users.  My basic question is, why isn't my Allegro code very
> much faster on a Sparc 10 than a Sparc 2?
> 
> I'm running Allegro CL 4.1 [SPARC; R1].  The first thing to say is
> that a standard Allegro image cannot run on both a 10 and a non-10
> (something to do with the stack location).  So we installed the
> relevant patches, and now have an image that can run on both.  To my
> vast disappointment, however, my system (a natural language
> understander) runs only marginally faster on the 10 (approximately 1.4
> times faster).
> 
> Now, if I remember right, a 10 is supposed to have approximately 2.5
> to 3 times the cojones of a 2, measured in spec marks.  Some simple,
> purely numeric test code that I wrote does indeed run at least 3 times
> faster.  Even some simple, non-numeric test code (lots of consing,
> calls to MEMBER, EQUAL, etc.) runs about twice as fast.
> 
> But my big, hairy, heavily CLOSified system just isn't that much
> faster.  Just to make sure it wasn't the patched image, I compared the
> unpatched and the patched Allegro (on a Sparc 2), and there was no
> appreciable difference in performance.
> 
> So, do any other users have any experience with 10s yet?  Does Franz
> have any intuitions about this situation?
> 
> I'd greatly appreciate any information.  I imagine the mailing list as
> a whole would be interested as well.
> 
> John Burger
> john@mitre.org
> 
> 

Well, thats what the vendor says!  Of course we all believe that don't
we!

For whatever its worth, your number of 1.4 is about what we got doing
performance benchmarks with ACL 4.1 (actually ICAD).  We ran *lots* of
code thru the compiler and did *long* runtime checks.  The compilation
tests on the Sparc 10 (model 41) were approximately 1.5 - 1.75 times
faster than a Sparc 2.  The runtime tests were a little slower 1.5 -
1.6 times faster than a Sparc 2.  Interesting to note that most of our
runtime tests were CPU limited.  Sun even put a special piece of H/W
on to see what was going on because they didn't believe the numbers
either.  And sure enough the application was CPU limited.  The paging
behavior was quite well behaved.  We ran with 64Mbytes of real memory
and 400Mbytes of swap space.  With 128Mbytes of real memory on the
Sparc 10 the performance numbers did not appreciably change.

Finally, running the Gabriel benchmarks ran a little better - 1.75 -
2.2 times as fast as a Sparc 2.

I wouldn't get too nit picky about the numbers.  Benchmarks are a
black art anyways - there are just too many independent variables.
Its qualitatitive at best.

ba

Brian H. Anderson                     (206) 234-0881
Boeing Commercial Airplane Co.        bha@gumby.boeing.com
Seattle, Wa.