🚀 go-pugleaf

In article <1993Jan22.015827.26653@nas.nasa.gov>, fineberg@wilbur.nas.nasa.gov (Samuel A. Fineberg) writes:
|> In article <1993Jan21.165159.10149@meiko.com>, richard@meiko.com (Richard Cownie) writes:
|> |> fineberg@wilbur.nas.nasa.gov (Samuel A. Fineberg) writes:

|> |> : Its certainly no less realistic than those for the i860.
|> |> 
|> |> I have to disagree with you there.  I know of *some* applications where
|> |> the i860 can achieve a good fraction of claimed peak speed, e.g. on
|> |> a double-precision matrix multiply you can do over 35MFLOPS, against
|> |> a peak rate claimed as 40MFLOPS (or sometimes 60MFLOPS, because you can do
|> |> 2 adds for each multiply).  In any case, it's well over 50% of peak.
|> 
|> I don't know too many people that write assembly code, and that is what you
|> need to do to get 35 MFLOPs.

False.  Using the PGI compilers on C and FORTRAN source code, selected codes can
achieve > 35 MFLOPS.

As you point out, most codes get less.

-- 
Kirk Hays - NRA Life, seventh generation.
"The only thing necessary for the triumph of evil is for good men to
do nothing."  -- Edmund Burke (1729-1797)