OT, But interesting

[Sean]

Does AMD use IBM's Copper technology? I know Intel licensed the Copper 
Technology with the "coppermine" series, but Its a bit tricky to get it to
work right especially with large chips. IBM is having a hard time getting
it to work correctly with the G-4 series chips which have 2.5  times more
transistors then the G-3 series does. 

The copper technology rocks.  They took the G-3 300 design, shrank the die
from .20 to .18 and lowered the voltage and upped the clock to I believe
400MHZ and basically ended up with a faster chip that used less energy. (I
think it was from 6watts to 3.5watts.) This is why Apple can ship the
_real_ G-3 chip in its portables and not some cut down version like the
"mobile series". Also, its why if you get a desktop box, your more likely
to get a motorola chip (which I believe still uses aluminum) and if you
get a portable your more likely to get an IBM chip. It's also part of the
reason why they are shipping machines without cooling fans(iCube, iMac).

As far as stamping the speeds on the chips, IBM/Motorola looked at the
demand before stamping the chips. If they made a batch with a great yield
of 500MHZ chips, some of those might get stamped as 400MHZ just because
they were out of the 400MHZ chips. Which increases the chances of being
able to overclock them significantly. I dont know if Intel or AMD uses the
same technique or not.
 
Clock chipping (overclocking just the chip) has traditionally been 
unstable and never resulted in major _real_ performance gains. Its a
little different story then overclocking your entire board as far as the
benefits. 

This throws out a couple of questions. 
First MHZ to MHZ do the AMD and Intel chips stack up equally as far as RL
performance? 

If Intel is disabling some unstable code, could this be some of the code
specifically on the chip for the SPEC tests (Intel has a set of
instructions on the chip specifically written for the SPEC tests and
only used for that)?

If the internal clock speed of the Pentium is running at 100MHZ what
is the benefit of clocking the rest of the chip to 1ghz? Your still
processing information internally at 100MHZ.
 
This in my mind throws out the question so what if it the chip is running
at 1GHZ or 1.1GHZ? You are better off with a 1GHZ chip on a 200MHZ board
(or running your 1.1GHZ chip at 1GHZ). This is simply because of the wait
states involved. If you have a 200MHZ board with a 1GHZ chip and your
66MHZ PCI bus. You have an even 1:3 ratio between the PCI and the board
and an even ratio of 5:1 between the chip to the board. This translates
into NO wasted time for parts of a clock cycle. Your chip is running 15x
the PCI bus. 

If your running at 1.1ghz you have the 1:3 ratio between the PCI and the
board, and a 5.5:1 ratio between the chip and the bus. If the buses can
only exchange data when the cycles match, you are actually waiting for the
chip to go around to the 11:2 ratio, the extra wait time involved actually
slows your machine down unless you are performing 11 instructions on
every piece of data. 

Or am I completely offbase?



 On Sun, 6 Aug 2000, Tim Schmidt wrote:

> >From: "Tim Schmidt" <computer_holic@hotmail.com>
> >To: linux-user@egr.msu.edu
> >Subject: Re: OT, But interesting
> >Date: Sun, 06 Aug 2000 17:03:06 GMT
> >
> >>From: Ben Pfaff <pfaffben@msu.edu>
> >>Reply-To: pfaffben@msu.edu
> >>To: "Tim Schmidt" <computer_holic@hotmail.com>
> >>CC: linux-user@egr.msu.edu
> >>Subject: Re: OT, But interesting
> >>Date: 06 Aug 2000 10:15:02 -0400
> >>
> >>"Tim Schmidt" <computer_holic@hotmail.com> writes:
> >>
> >> > http://www.hardocp.com/news_images/2000/aug2k/080500b.html
> >>
> >>I'm unable to read that article with lynx, w3m, or links: all I
> >>get is links to three "IFRAME"s, which just contain ads, no
> >>content.
> >
> >works in Netscape...
> >
> >>
> >> > It appears that Intel is not only factory overclocking their
> >> > CPUs [...]
> >>
> >>Isn't that an oxymoron, or a misnomer?  As I understand it, when
> >>you go to a chip fab, there aren't separate assembly lines
> >>cranking out 60 ns and 70 ns, nor are there separate assembly
> >>lines cranking out 866 MHz and 933 MHz Pentium IIIs, and so on.
> >>Rather, each chip that comes off the line is tested for its
> >>performance, where they crank up the speed until it fails at N
> >>MHz, and then they sell it as an (N - delta) MHz chip.
> >>
> >>On the other hand, overclocking is running a chip at a faster
> >>speed than recommended by the manufacturer.  So the factory
> >>*can't* overclock chips.  They could recommend that you run it
> >>faster than it would actually work, I suppose, but in that case
> >>it's a defective chip and you should be able to exchange for a
> >>working one.
> >
> 
> I was reading over your question again Ben, and realized an even better way 
> to explain why those "questionable tactics" are "factory overclocking."  
> Here it goes.  You're right, whe a chip comes off the line, it's tested to 
> see how fast it can run -- but the testing is done at default settings (in 
> this case, 1.6v, no microcode, stock HSF).  At this point, AMD stamps the 
> speed on them and ships them off.  Intel however, takes the fastest of these 
> chips, ups the voltage (just as any other OC'er is experienced in doing), 
> slaps on a massive HSF, to see how much higher they can get it (in other 
> words, it's being overclocked from it's normal tested rating -- at the 
> factory).  If it doesn't run 100% stable, they write some new microcode to 
> disable whatever part of the processor is giving them problems at that 
> speed.  Of course that's an over-simplification of how microcode works, but 
> you get the point.
> 
> Did this explain it better?  Why it's refered to as factory overclocking?
> 
> 
> >Yes Ben, but PIII-C's run at 1.6v (I think, maybe 1.65), Intel has not only
> >cranked up the voltage (gets a clearer high/low voltage signal through) to
> >increase the speed the chip can reach, they've issued microcode updates for
> >the 850 and up which in effect "turn off" parts of the chip that can hold 
> >it
> >back when reaching higher speeds.  So microcode updates allow the chip to
> >clock higher, but have a performance hit.  Also, Intel has outfitted the
> >PIII 1000, and 1133 (and I think the 850 and up) chips with massive HSF's
> >(Heatsink + fans) to dissipate the massive ammounts of heat produced by the
> >high clock-speed/voltage.
> >
> >In other words, with no tweaking a PIII-C might reach 850Mhz, only with
> >--massive-- ammounts of tweaking and/or questionable tactics can a PIII-C 
> >go
> >any higher.
> >
> >AMD on the other hand, has not used and microcode updates, voltage hikes,
> >die shrinks, or massive heatsinks to get teh Athlon to 1Ghz.  1.1Ghz 
> >athlons
> >have been in the hands of reviewers for several months now also.
> >
> >In short, resorting to all these questionable tactics is what is generally
> >refered to as "factory overclocking"  -- yes, it is technically an 
> >oxymoron.
> >
> >--Tim