Re: is Vax addressing sane today

Michael S <already5chosen@yahoo.com> writes:

On Sun, 06 Oct 2024 07:18:59 GMT
anton@mips.complang.tuwien.ac.at (Anton Ertl) wrote:

The fact that IBM has not submitted results for Power for SPEC CPU
2017 for (Int or FP) Speed or FP Rate results is an admission that
their numbers there are even less impressive.
 

>
That's most likely explanation, but another one is that it is sort of
internal policy no matter what.
IIRC, they didn't publish non-rate scores for POWER7 either, despite
that according to independent measurement at point of introduction
POWER7 single-threaded performance was in the same ballpark with best
Intel offerings and easily ahead of best AMD.

For our LaTeX benchmark (numbers are in seconds (lower is better), the
years are when the hardware came on the market:

Power7, 3600MHz, CentOS 7 (ppc64) TeX Live 2013           0.81  2010
Athlon 64 3200+, 2000MHz, 1MB L2, Fedora Core 1 (64-bit)  0.76  2003
Xeon X3460 (Lynnfield (Nehalem)) 2800MHz, Deb Lenny 64b   0.484 2009
Xeon 5160, 3000MHz, (2*)4MB L2, Debian Etch (64-bit)      0.48  2006
Phenom II X2 560, 3300MHz, 6MB L3, Debian Jessie (64-bit) 0.452 2010

On whatever applications the performance of Power7 is competetive with
Intel and AMD of its time, it's certainly is not on our LaTeX
benchmark.

In any case, certainly for the stuff I do I see no reason why I would
consider, much less recommend buying a Power machine these days.  My
guess is that the major reasons for buying pSeries machines these days
are legacy software and IBM salesmanship.
 
- anton

>
I think, if you are running Oracle DB Enterprise Edition, where
software license per core is the most expensive part then there could
be an economical reason for preferring POWER9 or 10 over Intel or AMD.
But that's just a guess.

Yes, per-core licensing fees irrespective of the actual hardware might
be a reason, but it would be perverse of Oracle or some other ISV to
pay for porting to Power in order to reduce the licensing fees that
their customers have to pay to them.  But stranger things have
happened.

- anton
--
'Anyone trying for "industrial quality" ISA should avoid undefined behavior.'
  Mitch Alsup, <c17fcd89-f024-40e7-a594-88a85ac10d20o@googlegroups.com>