P4 150% FASTER THAN A T-BIRD!!!

AmdMELTDOWN

Distinguished
Dec 31, 2007
1,998
0
19,780
Newly released <A HREF="http://www.mersenne.org/bench.htm" target="_new">benchmarks</A>(prime95 v21) have the P4 with one arm tied behind the back and one leg in a cast and while wearing a blindfold-smoking the T-bird! Amen.

also here's a link to an AMD paid <A HREF="http://www.jc-news.com/index.cgi" target="_new">website</A> and read their little article about the it.



"AMD/VIA...you <i>still</i> are the weakest link, good bye!"
 
Wow that's is incredible the p4 is much better than I expected when properly optimized. Cool getting better all the time soon ill have my dual P4 then its play time. Who's gonna go dual palimino?

SPUDMUFFIN

<font color=red>Being Evil Is Good. Cause I Can Be A Prick And Get Away With It.</font color=red> :lol:
 
Those are some nice benchmarks. Http://www.distributed.net has a client listed as beta as well. One of the additions mentioned in the changes.txt file is P4 optimized code. I'd be interested in seeing some benchmarks on that one as well.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =
 
If all you do with you computer is chasing prime numbers then you have reason to be impressed...

I mainly use mine for games, so the figures aren't very interesting...


/J

AMD TBIRD 1.33
Asus A7M266
Vapochill
nVida Geoforce3
Apacer 256MB DDR266
Seagate X15
 
:smile: if all you do is games then I guess you do deserve a Athlon cooled with the vapochill no less, just how much did you have to fork over for that rig? rotflmao!!! just to play games??? ha! are you a professional cyberathlete? LOL,



"AMD/VIA...you <i>still</i> are the weakest link, good bye!"
 
wow. you gave us another link to an another article.

how exciting.

I think I'll go throw my tbird away now that I read that article.

not.


:tongue: <font color=green> I LOVE INTEL. It tastes like chicken </font color=green>
 
That is about the most pointless article I have ever seen. WHO THE HELL CARES?! I own a T-Bird but if you show me something that says P4 outperforms it in real world apps and is more affrodable, I'm open-minded. Since that hasn't happened yet, I guess I'll stick with my proc...

Are we there yet?
 
Th funny thing I see is that without SSE2, the P4 at 1500 mHz performs about equal to a TBird 900 or 1000. But, it does show that power of SSE2, and that it does show how well performance can improve. The only problem I have with this test as a guide for real world performance is that this test is extrmeley narrow, meaning it only does one thing. I find it extremely doubtful that in real world complicated and wide-ranging programming, SSE2 will show such huge performance gains. That would be great if it did, as SSE2 will be with both AMD and Intel, but it is unlikely it will be so great.

The "AMD paid" website link you provide is actually very upbeat to the results and depict them in a positive light. What was your point of that post?

"Trying is the first step towards failure."
 
That indicates a 'potential' which may or may not be utilized.
For more closer to 'real' life benchmarks, see this review:


http://www.tomshardware.com/cpu/01q2/010423/index.html

P4 does perform better in some applications, as well as in Q3...but really, you do not buy P4 or AMD 1.33 to play Q3 at 640 x 480 resolution ??

I didn't think so.

Cheers,

hell out
 
AMD TBIRD 1.33
Asus A7M266
Vapochill
nVida Geoforce3
Apacer 256MB DDR266
Seagate X15

??? I'm going to agree with meltdown here, why in the world would you get a vapochill just to play ames? AND who would buy a vapochill and NOT OVERCLOCK!?!? I don't understand.
 
Umm... In real world uses, and since mostly gamers buy the high end fastest systems, an Athlon @1.33 or HIGHER can whoop a P4 at 1.7ghz. Now since you are talking optimized code here FOR the P4, why not throw in an alpha CPu WITH optimized code? Exactly.. It is NOT the same playing field. The ALPHA with it's huge cashe and differences will WHOOP both CPU's but we are not comparing the same real world test here.. Static benchmarks such as this with their optimised codes are BS. Who cares.
It's the frame rate that most people are interested in.

MrNuke
 
Big question what happens when AMD gets to where Intel got for speed stepping??? When they redesign the core to do what Intel is doing then what??? Oh I forgot AMD doesn't have to do any real R&D they just licensee all the technology from Intel.

SPUDMUFFIN

<font color=red>Being Evil Is Good. Cause I Can Be A Prick And Get Away With It.</font color=red> :lol:
 
From your URL: "The Pentium 4 does not however have a hardware rotate instruction."

Where do they get the idea that the Pentium 4 has less instructions than the Pentium 3? The Pentium 4 supports all the same instructions, including all of IA32, MMX, SSE, and SSE2. It definately has a hardware rotate instruction, as did the 80386, 80486, Pentium, Pentium Pro, Pentium II, and Pentium III. To drop support for standard instructions would be paramount to suicide. You would no longer be able to run 99.999% of the software out there. The information on that page is just wrong.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =
 
You need a link for this? This is common sense. Removal of standard IA32 instructions from a processor would make it no longer an IA32 CPU. IT would not longer run any of the software as it would throw exceptions whenever it hit the unsupported instructions.

Simply look through the technical documentation on Intel's website for the Pentium 4. It will tell you exactly what instructions/instruction sets it supports.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =
 
"Big question what happens when AMD gets to where Intel got for speed stepping??? When they redesign the core to do what Intel is doing then what??? Oh I forgot AMD doesn't have to do any real R&D they just licensee all the technology from Intel."

Are you talking about Speedstep vs. PowerNow! technology? If so Amd is already far beyond Intel. Speedstep has only 2 settings (high and low). PowerNow! has a total of 32 possible speed settings and automatically adjusts itself on-the-fly when the power is needed and slows back down when its not to conserve battery power.
 
I did. No hardware rotate instruction....

Also I believe the hardware rotate instruction is part of IA32, not IA32 itself.

---------
I am the first and only one with a 16MB GeForce2 GTS graphics card! :smile:
 
IA32 is the list of all instructions present in the 80386. This was the first IA32 processor and defined the standard. The hardware rotate instruction is a part of IA32, and hence is present in all CPUs that are 100% IA32 compatible, including the Pentium 4.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =
 
IA64 is the standard 64-bit instruction set that the Itanium will be pioneering. I do not expect AMD to use IA64 until they have sufficiently explored x86-64. AMD is targetting x86-64 only at machines that require more memory. Their whole 64-bit platform is based on 64-bit meaning only more memory, while stating that most applications should not bother to be written to take advantage of a 64-bit CPU. In my opinion this is not 64-bit innovation, but 32-bit complacency similar to the old DOS extenders in the 16-bit days that gave you access to more than 1 megabyte (16 bit's limit) of memory.

AMD's strategy in going this route is twofold. First, it does not have the capital, nor the time, to do a complete optimized redesign for 64-bit. Intel started on this long ago, as was necessary for such a new design, and has a huge head start. They needed something simpler that they could finish much more quickly to attempt to be competitive. Second, they calculated that there would be a time after the introduction of the 64-bit CPU where it would not be a great performer on current software, most of which is still 32-bit. This was not a great discovery as it always happens with large paradigm shifts. It happened when we moved from 16 to 32 bits. It will happen when we move from 32 to 64 bits. They intend to take advantage of this 'twilight', if you will, before the dawn of massive amounts of 64-bit applications by pounding on Intel for having lackluster performance on 32-bit applications. Because during the transition there will still be more 32-bit applications available than 64-bit applications, this could have some kind of a marketing benefit for AMD.

Do not mistake any of these strategies as any kind of technological benefit. You did not want to be the owner of a 286 (16-bit CPU) when Windows 95 (requires a 32-bit CPU) was introduced. Even today we still have people claiming DOS is better than Windows. These are the leftovers of those who chose to stick with older hardware because it ran the applications they were using at the time (DOS apps) more quickly. It might have made a bit of sense at the time to stick with an older CPU, because 32-bit applications had not yet proliferated as they have today. That, however, would have completely left us out of the 'new technology' loop. What fun is it to always be the last person on the block who gets to play with the new toys? Not much fun at all. How profitable is it to be the last company to develop software for new technology? Not very profitable at all. Everyone else has already beaten you to the customers.

I do expect AMD to eventually go with an IA64 processor, but not until they have soaked Intel for all they can with the "Itanium is slow at 32-bit IA32 software" marketing line. The first 386 was slower at 16-bit code than the fastest 286. I don't know about all of you, but I'd rather have the 386.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =
 
Raystonn your staying after a couple years when IA64 is welcome to the Desktop, server, Mobile market then AMD will move to IA64. Or AMD will never use IA64.

:redface: 😎 😱 :frown: :lol: 😡 :smile: :tongue: :wink:
The only nice Intel guy.
 
Eventually they will have to use IA64. This is probably less than 10 years off. AMD will milk the x86-64 as much as they can, but it simply does not perform anywhere near IA64. Their critical time period is when 32-bit software is still very popular. That is where x86-64 actually shines, not on 64-bit software.

-Raystonn

= The views stated herein are my personal views, and not necessarily the views of my employer. =