• Welcome to Overclockers Forums! Join us to reply in threads, receive reduced ads, and to customize your site experience!

First 1066FSB Intel CPU Benchmarks surface

Overclockers is supported by our readers. When you click a link to make a purchase, we may earn a commission. Learn More.

nissmo300

Member
Joined
Apr 4, 2004
Anandtech | Hexus | Firingsquad | XBitLabs | HardOCP | PCPer | Tech-Report | Beyond3D | Sudhian

5250.png

5251.png

5261.png

5298.png

5294.png

Anandtech's Conclusion
So there you have it folks - the 1066MHz FSB does absolutely nothing for performance. The 3.46EE does manage to outperform its 3.4GHz/800MHz FSB predecessor, but the margin of improvement is negligible. Intel desperately needs a win here and other than the more affordable price of the Pentium 4 560, there's very little going for the CPU king these days. It will take higher speed Prescott CPUs or dual core in order for the added bandwidth of the 1066MHz FSB to truly be of any use - and it will take lower latency DDR2 memory to finally give the latest Pentium 4 platforms lower latency memory access than the ones they replaced.

The move to the 1066MHz FSB is in sharp contrast to the past two FSB bumps that we've seen from Intel. The introduction of the 533MHz FSB back in 2002 yielded up to a 12% gain in gaming performance, and a 3 - 6% gain in individual applications as it was paired with PC1066 RDRAM. Then came the 800MHz migration that showed a 3 - 9% increase in gaming performance, and just under a 12% increase in professional application performance. But with the move to the 1066MHz FSB we have a platform launch that, in the spirit of the 925X and 915 launches, does virtually nothing for performance.

HotHardware's Conclusion
When we look at the entire spread of benchmark readings we took here for you today, we see the P4 pulling down six wins to the Athlon 64's five wins, with two virtual draws in the 3DMark05 and Lame MP3 tests. These metrics should be contrasted by the fact that the benchmarks that were won by the Athlons were more mainstream desktop and gaming applications that many of our readership finds most important. The P4 definitely excels in audio and video media encoding, as well as mutlithreaded applications like Cinema 4D in our Cinebench benchmarks. The Athlons were the clear and distinct victors everywhere else. Finally, we noted a smallish 1 – 3% advantage for the new 3.46GHz P4 Extreme Edition and i925XE chipset, versus the current standard P4 EE and the i925X.

The new 3.46GHz Pentium 4 Extreme Edition coupled with the i925XE chipset offers a small performance gain for the enthusiast in certain gaming scenarios and the occasional Media Encoding or 3D Rendering workload. Again, the performance gains we observed were in the 1 – 3% range, hardly what we expected frankly. In fact, equal performance gains can be realized just by making the move to lower latency DDR2 DRAM set at CAS 3, 3, 3, 8 timings. With identical system memory timings in our i925X and i925XE systems, the net gain from a high-speed 1066MHz FSB is observable but frankly nothing to write home about, at least in the applications we tested it in.

This is HUGE letdown (atleast for me) I was looking forward to this for the past 6-8 months. :(

Looks like another :thup: for AMD.
 
Wow, kinnda makes me glad i went with an AMD on my latest upgrade.

Something i would like to add to anyone thinking about going to AMD right now, Intel is by far the king when it comes to multitasking. Windows just feels so much more smooth on an Intel. In raw gaming power though, my new FX-55 is the big dawg. Thanks for the info.
 
Im sticking with my [email protected] till late next year and see how the dothan does.
Theres no point in getting another p4 seems like theres hardly any performance gains to warrant all the cash to upgrade
But if a great 939socket motherboard comes out i will probley get a 90nm A64 3000+ and clock it to 2.6ghz still not sure how much of a improvement that will be over my current setup though, i have no experience with a64`s.
 
That's a pretty good point. The P4 architecture is pretty played-out at this juncture. CPU performance hasn't changed much since the Northwood hit 3GHz, and the heat and current ramifications of the Prescott's design limit its clock rates effectively for all but the most determined users.

The other side of this coin is that the P4 can't be improved substantially because there isn't anything wrong with it. i865pe and i875 are fabulous chipsets, and all any of these i9xx things can hope to do is to match them. You can't fix what isn't broken, and those that have tested the assertion before know that 800fsb and DDR400 are not limiting in terms of overall application performance.

It's just a replay of the BX days of past. P3->P4. i440BX->i875, i82x->i9xx, Athlon->A64. And unfortunately Via is still Via. Just like in the P3 days when Intel's cpu choices looked tame, long ago maximized by the perfection that was the i440BX chipset and at the CPU clock speed limits of their design, you were left wishing you could put one of those spiffy new 1.4GHz Tbirds on your BX board as to avoid the amatuerish AMD-supporting chipsets.

In similar fashion today, if you could plop that nice new A64 4000+ on a i875 motherboard no other choice would make a lick of sense. The more things change, the more they stay the same. AMD has been more progressive in their CPU design than Intel for 7-8 years, but blunted the impact of this advantage by a complete lack of similar advancement of the system of core components that facilitate its use. Sure Nvidia chipsets are better than Via, but that's not saying much at all.

What this means is those that are inclined to use AMD processors have little reason to consider the Intel alternatives. Perhaps time to introduce a dog-and-pony show to confuse buyers. PCI Express, anyone? I forgot that in my progression statement above, AGP->PCI Express. Both introduced for primarily marketing impact long before needed, so for a time Intel can say 'if you buy an AMD system you can't get the latest technology'. Nevermind the fact that in this case the latest technology has no impact on application performance and simply drains users' bank accounts in a torrent of unneeded upgrades and influenced hardware choices in the course of necessary new machine purchases.

For those inclined to run Intel systems, they generally already have a very refined and optimized Northwood or Prescott rig--and again little reason to consider the current Intel offerings. And just like the P3 days, they will either have to let just how well their computers actually work in real life satisfy them until truly new products recapture the lead in the numbers race, or buy an AMD. Personally I weathered the last storm and am prepared to weather another, unless AMD should provide the chipset excellence long a hallmark of Intel's efforts.

It's ironic that the most likely salvation for Intel stems from a developement of that same, tapped out, P3 architecture. Intel will have to truly understand that even though they have been able to direct the industry at their whim for a long time, that day is over. Actual performance in the context of purchase price must assume the lead role, rather than the exact details of Intel's latest market manipulation stradegy.
 
Last edited:
DanIdentity said:
larva - fabulous post, bravo. You hit the nail on the head.

Sure did, its what i meant but im a spaz at writing larva is spot on.
 
Last edited:
jenko said:
Im sticking with my [email protected] till late next year and see how the dothan does.
Theres no point in getting another p4 seems like theres hardly any performance gains to warrant all the cash to upgrade
But if a great 939socket motherboard comes out i will probley get a 90nm A64 3000+ and clock it to 2.6ghz still not sure how much of a improvement that will be over my current setup though, i have no experience with a64`s.
you'll tell a difference... my 3000+ is a 754 w/o CG 2.40Ghz and it smacks the crap outta my friends 3.6+ghz machines. but they still ahve better memory and video cards :(
 
jenko said:
Sure did, its what i meant but im a spaz at writing larva is spot on.
You did identify the operative issues correctly and arrive at the correct consumer stradegy. This shows true understanding and that is a rare thing indeed. I likely would not have stopped to comment if you hadn't crystalized the functional issues so clearly.

Writing is a practice-makes-perfect endeavor, and this forum is a world-class opportunity to hone your skills while discussing the things you love. There are two major factors in the quality of your writing: the quality of the things you read and the quantity of the things you write. I'm doing every thing I can on the issue of the former; the latter is entirely up to you :p

Seriously though, do find great writers that tackle subjects of interest to you and devour their works. I read entire libraries stem to stern as a child, and that is why my writing is polished. Understanding what quality writing looks like is (at least) half the battle.
 
Last edited:
Hmm so its another P4 Willie vs Athlon scene. But if they bring out Super Dothan's with all the goodies I can see Intel back in the lead. If they don't... Well how hard is it to cool a single Presscott can you imagine 2 of them under one heatsink.

I think Intel seriously needs to retool their consumer lines and bring out a cpu that can crack down on AMD in a clock for clock race. I wouldn't mind seeing those days again when a slower clocked Intel would crack down on a K6. I also think that Intel started this hole when they decided to stick to SDR instead of DDR with the P3's.

Guess I will be getting an Athlon 64 next summer if things don't turn around over in the blue camp.
 
DanIdenity said:
What all the review sites seem to be forgetting is that mobos based on the 925XE chipset will be much better overclockers than the older 925X based boards.

XbitLabs did a review which compares a p4 3.46 EE chip in both 925XE and 925X motherboards (along with p4 560 LGA775 [3.6 GHz] and various athlon 64s).

Their mb conclusion:

As far as the new i925XE Express chipset is concerned, this solution also doesn’t offer us anything really new. It is just a slightly enhanced version of the i925X core logic, which we are already very well familiar with. Therefore the new chipset boasts the same features and provides the same performance level (which is actually even lower than what we are still able to get from the good old i875P based platform). However, i925XE Express has quite a few promising prospects ahead. Mainboards based on it will become popular among overclocking fans (we will check it out first hand when the mass mainboards on the new i925XE Express appear in our lab). Moreover, the performance of i925XE Express based platforms can also improve when DDR2-533 SDRAM featuring more aggressive timings (for example, 3-3-3-8) comes out.


*** EDIT - apologies to nissmo300. Did not realized before posting this that you linked to this xbitlabs article in your original post.
 
Last edited:
Ouch... well on the bright side I does use a lower multi. However those performance figures are *not* a good sign to investers. Especailly when AMD is hammering away at Intel with the 4000+
 
Back