[luau] Re: PPC vs. X86

[LinuxDan]

  NOT

-----Original Message-----
From: luau-admin at videl.ics.hawaii.edu
[mailto:luau-admin at videl.ics.hawaii.edu]On Behalf Of Jimen Ching
Sent: Sunday, December 29, 2002 6:32 PM
To: luau at videl.ics.hawaii.edu
Subject: Re: [luau] Re: PPC vs. X86

On Sat, 28 Dec 2002, Eric Jeschke wrote:
>would probably outperform a 1.3GHz P4 and maybe even a 1.5GHz P4.
>This is same reason that a 1.6 GHz Athlon was outperforming a 2.0GHz
>P4. BUT P4's are currently topping out above 3GHz!!

Deminishing returns...After reading some of the benchmarks that people
have done, each gigahertz increase in clock rate does not give you the
equivalent performance boost.  I.e. a 2GHz Athlon is not twice as fast as
a 1Ghz Athlon.  Of course, this doesn't provide any advantages to Apple.
A PowerMac is still more expensive in terms of performance per dollar.
But this does suggest that clock rate along is not the determining factor.

>instructions/clock) is just not able to keep up.  I saw a recent review
>(sorry don't remember where) of a dual 1GHz PPC against a 3GHz P4 with
>hyperthreading; the Mac lost on every benchmark.

You must mean the benchmarks found here:

        http://www.azillionmonkeys.com/qed/apple.html

I also found a host of other PowerPC vs. Intel/AMD benchmarks.  After
reading all of these benchmarks, I noticed they are always pitting a lower
clock rate PowerPC against a higher clock rate x86.  This is
understandable if they can't find a PowerPC with the equivalent clock
speed.  But do these people realize that they're not comparing apples to
apples (excuse the pun)?

The only thing I learned from these benchmarks is that people pay a
premium on the Apple logo, or a premium on the x86 clock rate and power
consumption.  Seems like people are forced to pay for an inefficient
device in one form or another.  Oh, there is another thing I learned.
There seems to be a lot of bias, in both the PowerPC and x86 worlds.  One
could easily get the wrong impression if one doesn't do a complete search.

>If you are doing I/O bound work rather than CPU bound work then, yes,
>you should save your money and buy a slower processor because it will be
>waiting most of the time anyway...

I guess the trick is to try to match the two.  I.e. don't let one, or the
other, be the bottleneck.

>I don't agree with this.  They are tracking the top of the PPC
>manufacturing pretty closely.  Witness: the dual 1GHz G4 is their
>current top of the line (they have been beating Motorola's door down
>trying to get them to build a faster chip, but Motorola does not have
>the market/fab/capitalization/design/?? to ramp the architecture up as fast
>as Intel and AMD).

When I said Apple is not producing higher clock speed systems, I mean
Motorola is not producing the necessary PPC's for Apple.  Anyone know why
Motorola is slow to produce the higher clock rate processors?

>Even AMD is conceding the 32-bit performance crown to Intel, because
>nothing AMD has now in the 32 bit line is touching the P4's performance.

Do you mean clock speed instead of performance?  I believe you mentioned
earlier that the two aren't always a one-to-one comparison.  AMD sounds
like it got tired of the clock race, just like the consumers.

>One last thing: you mentioned that Firewire was competitive to SCSI (in
>your quoted email).  Not to my understanding or experience.  Firewire
>tops out at 400 Mbps or 50 MBps.  Even IDE has a better transfer rate
>than this.  Firewire is nice in that it is hot-plug; you can also do
>RAID tricks over firewire to increase the performance, but a good
>high-speed SCSI subsystem (or even IDE) will be much superior in terms
>of performance.

Can you elaborate on your experience?  The problem with personal
experience is that everyone has their own.  So one has to understand how
similar the usage patterns are before making conclusions about experience.

--jc
--
Jimen Ching (WH6BRR)      jching at flex.com     wh6brr at uhm.ampr.org


_______________________________________________
LUAU mailing list
LUAU at videl.ics.hawaii.edu
http://videl.ics.hawaii.edu/mailman/listinfo/luau