R
roman modic
Hello!
Yep, I know that. But plans regarding 939 future are still
unclear/undefined. BTW, here are some nice links
regarding AMD (and Intel):
http://www.hardwarecentral.com/hardwarecentral/print/6193/
Regards, Roman
NoNoBadDog! said:Roman;
The new crop of AM2 and S1 procs will support Pacifica, which is a better
virtualization than the Intel scheme.
Yep, I know that. But plans regarding 939 future are still
unclear/undefined. BTW, here are some nice links
regarding AMD (and Intel):
http://www.hardwarecentral.com/hardwarecentral/print/6193/
It's difficult to tell if AMD is worried about the new Intel platform;
whether it's based in truth or bravado, there seems to be an air of quiet
confidence from company HQ. Choosing years ago to go with an integrated
memory controller instead of the traditional CPU/chipset layout is
definitely paying dividends in terms of relative performance, as their
processors' lower latencies have allowed AMD to slip right past Intel and
never look back.
This architecture also lets AMD quietly tune memory performance and features
with each new core stepping, whereas Intel needs to release a new chipset to
accomplish the same thing. AMD's method is more seamless, but it also comes
with a few negatives, such as the increased R&D time required to redesign
the integrated controller for DDR-2.
It also means that AMD is in some ways less flexible and more susceptible to
industry change. Intel seems to have dropped DDR support from its current
chipset line, but once AMD finally makes its DDR-2 transition, Intel might
backtrack and offer both options to customers. AMD is also introducing
Socket AM2 to support its DDR-2-enabled processors, which means the end of
the road for the faithful Socket 939 and may let Intel level the playing
field in terms of platform stability and potential longevity. AMD also has
the move from 90- to 65-nanometer-process engineering to look forward to,
which should naturally translate into additional clock speed headroom --
probably over the 3.0GHz threshold. This may scare Intel, as the 65nm
Pentium D 900 chips are already on the market, but the NGMA design at 65nm
might prove to be sensational.
http://www.itjungle.com/breaking/bn030706-story01.html
On that curve, if you normalize for 486 performance and power consumption
(meaning setting them to 1), then the 486 has an "Energy Per Instruction"
(EPI) of 10. The Pentium chip from 1993 had about twice the performance, but
consumed 2.7 times the energy, which raised the EPI to 14. The move to the
Pentium Pro boosted performance relative to the 486 by a factor of 3.6, but
power use went up by a factor of 9, driving the EPI up to 24, and the
"Williamette" Pentium 4 chip had six times the performance, but consumed 23
times as much energy, yielding an EPI of 38. The "Cedarmill" Pentium 4 chip
had 7.9 times the performance, but consumed 38 times as much energy, for an
EPI of 48. The Pentium M may not have had blazing performance, but it sure
did have pretty good power efficiency and decent enough performance for a
laptop, where companies would willingly sacrifice performance for longer
battery life. The second-generation "Dothan" Pentium M chip had about 5.4
times the performance of 486, but only consumed 7 times as much energy,
giving an EPI of 15. And the new dual-core "Yonah" Core Duo chip, which
actually is made using a 65 nanometer process, has 7.7 times the performance
of the 486, but only consumes 8 times the power, which gives it an EPI
rating of 11. Which is only 10 percent higher than for the 486.
That, in a nutshell, is why Intel is excited about the new Core
Architecture. It has been able to turn back the clock on power consumption,
and because of the 65 nanometer process, it can cram more cores onto a chip,
keep the clock speed low, and still boost performance enough to make its
server customers happy.
Regards, Roman