Intel 3.2E vs. 3.2EE vs. 3.2C: Comparing Baseline Performance
by Wesley Fink on February 12, 2004 2:46 PM EST- Posted in
- CPUs
Workstation Performance
Workstation Performance was a bit of a surprise because processors with the largest on-chip cache are usually the best performers in this benchmark. However, in all the individual tests with SPECviewperf 7.1.1 except UGS, Prescott was the best performer. Apparently, there are aspects of the Prescott design that make it more efficient in SPECviewperf. This same pattern was also seen in Intel CPU comparisons on other chipsets and other motherboards. It is a big surprise that Prescott beats the EE in Workstation Performance benchmarks, even though the EE has 2.5MB of cache compared to the 1MB of the 3.2E.
Facebook
Twitter
RSS
19 Comments
View All Comments
mindless1 - Sunday, April 18, 2004 - link
WOnder of all wonders... we have evolved to supporting INDUSTRY STANDARD image file formats yet the review uses proprietary pics. I (and I suspect others) are "a rock" on this point, won't run flash. Using such pics in an article simply causes readers to go elsewhere, which in an overall elite-snob sort of way may not matter but in the grand scheme of things, losing readers beside of abandonment of industry standards is just a dumb idea.Aervires - Saturday, February 14, 2004 - link
Are you sure you bought both processors retail?The P4EE is $955 AND THE A64FX-51 is $745
The total cost a the P4EE will run you more however both are a waste of money. Also the when socket 939 comes BEWARE.
Aervires - Saturday, February 14, 2004 - link
Pumpkinierre - Saturday, February 14, 2004 - link
#9 Trog, if it was only pipeline related then the p4EE comanche4 results should have the same as the northwood. But clearly it is better because of the extra cache 2Mb L3. The Prescott has 1Mb L2 and 16K L1 so it should have results in between the 3.2EE and 3.2c (if not close to the P4EE) if it had the same core as the n'wood and cache latency. In fact it is markedly down in commanche4 cf. with N'wood. Given that other games benchmarks/demos and tests have the two processors within 10%, I dont think this failure is solely as a result of the 31 stage pipeline and branch predictor etc. (remember intel also improved its efficiency with a lot of tweaks). The main problem is the cache latency has slowed down and this obviously has a marked effect on comanche4 as it would in real time gaming where memory subsystem latency is paramount. See here:http://www.xbitlabs.com/articles/cpu/display/presc...
Quote:
"Yes, unfortunately, we have to state that not only the size of Prescott’s cache-memory has grown bigger, but also its latency. And the latency grew up a lot, I should say: for L1 cache the latency doubled! As a result, Intel will no longer be able to boast the extremely low latency of its L1 data cache. From the temporal point of view, the latency of Pentium 4’s L1 data cache got close to that of Athlon 64 L1 cache, though the latter is four times larger. However, the increase in the L1 cache latency is another forced measure, so that the new Pentium 4 processors on Prescott core could go beyond 4GHz core frequency.
Similar changes were made to the L2 cache, too. In terms of L2 cache latency, the new Prescott processor yields to Northwood, as well as to the competing CPUs from AMD Athlon 64 family."
That, plus poor fpu plus heat- not a good gaming cpu scenario. Intel have blundered big time and they must be rushing to get something out soon to relegate this doozer to the dustbin of history.
truApostle - Friday, February 13, 2004 - link
The P4 extreme is a total waste of money, IMHO. To spend $550 more dollars only to gain 3-5 fps in some of the new(er)games is NOT worth it. OF course if you are still playing Quake III then you will realize some smokin fast frames in which case it's all overkill anywho. In every bench from content creation to encoding to gaming the P4EE was marginally ahead, at best. I guess if your a Rockefeller or a Rothschild then it's okay to build a system based upon that proc.I think the best deal out right now is a 64 3400. Benchmarks are really close to FX-51 and are matched too (content creation, encoding) or better (in gaming benchs) than most Pentium archrivals. Just my humble opinion.
Either way isnt it a great time to be human, with all this technology to play with.
truApostle
-when you aim for perfection, you find that it's a moving target.
sipc660 - Friday, February 13, 2004 - link
we seem to go down the same road as with the previous article.#1 was right you should overclock both 3.2C and 3.2E to show the overclocked performance delta with the measured temperature.
that should give people who are interested in buying either a better comparison since the chips are going to be the same price at launch
what you also should drain out of intel is wether or not it has built in 64 bit circuitry. and can it be unlocked through bios at a later stage.????
right now at the moment it seems 3.2C is a clear winner regardless of the high end workstation performance.
overall i would buy barton before i'd buy any of the intel chips. i don't beleive anyone here would buy any of these chips till they seriously come down in price.
just keep it cool (hehehehe)....
go amd
P.S: cramitpal is a passionate joker, if no one can c that than you are blind. personally i'd give him a nice friendly hug if i met him on the street.
LOL
Superbike - Friday, February 13, 2004 - link
I think I'll pick up a Prescott I need a computer/space heater.edub82 - Friday, February 13, 2004 - link
Well this article clinches it for me...The 3.2EE must be mine, the increased performance over that pathetic 3.2C is well worth the 600 extra dollars I'm going to have to spend.
kmmatney - Thursday, February 12, 2004 - link
Yep...Athlon 3400+ $270
2x512Mb PC3200, Corsair: $155
MSI KT8 NEO $97
Total Price $522.
That's the system we just ordered at work. We do a lot of image processing and image compression, and fpu intensive image manipulations and the Athlon is faster than a P4 - at least with our particular applications.
vedin - Thursday, February 12, 2004 - link
That's true johnsonx but..Athlon 3400+ $404
2x512Mb PC3200, Corsair: $155
MSI KT8 NEO $97
Total Price 656.
And it's like, what? .5% slower than the Athlon FX-51?
I see your point about the FX though, as do most here. It's kinda useless with a much cheaper AMD option right next to it performance-wise. But either way, the system I just described makes BOTH systems look silly for buying, unless you just like spending money.