🚀 go-pugleaf

In article <1993Jan20.232809.29241@nas.nasa.gov> fineberg@nas.nasa.gov writes:
 > In article <1993Jan20.211032.11929@hubcap.clemson.edu>, richard@meiko.com (Richard Cownie) writes:
 > |> This seems to imply a figure of over 4MFLOPS per T800.  Last time
 > |> I programmed one, it was a real struggle to achieve over 1MFLOPS
 > |> even for inner loops of vector routines.
...
 > Its certainly no less realistic than those for the i860.
 > 
I disagree a bit.  It is possible on the i860 to get sensible routines
running at 50 MFLOPS single precision (although also here it is a real
struggle).  But using published peak can be very misleading.  I know
of one machine where the published peak can only be obtained during the
calculation cycles of the vector instruction.  You must ignore instruction
start-up time.  If you included that the peak would be lowered by 25% (yeah,
right, one quarter).  But than we get at the standard question: what should
you use?
-- 
dik t. winter, cwi, kruislaan 413, 1098 sj  amsterdam, nederland
home: bovenover 215, 1025 jn  amsterdam, nederland; e-mail: dik@cwi.nl