nForce4: PCI Express and SLI for Athlon 64
by Wesley Fink on October 19, 2004 12:01 AM EST- Posted in
- CPUs
Index
In round 2 of the chipset wars, nVidia performed a massive transformation of the nForce3 chipset, moving from the pedestrian nForce3-150 to the leading-edge nForce3-250 family in April. As good as nForce3-250 is, however, users knew that more was on the way from VIA, SiS, and nVidia themselves. The CK8 chipset was first displayed at Computex in June. With the successful launch of the nForce3-250 family, it was clear that nVidia had every intention of upping the ante in the Athlon 64 market with both PCI Express and Dual Video cards on the single-chip CK8.
In the four months since we first saw CK8, a lot has happened in the computer industry. Intel launched their new Socket 775 processor and 925X/915 chipset and received a less than enthusiastic reception from enthusiasts. The yawns from the computer community have translated into very poor retail sales for the new Intel platform. Promised performance updates to the new Intel architecture, which were supposed to drive sales of the new 775 platform, have been scaled back, with rumors that mainstream 1066 parts now are not expected until the middle of 2005.
AMD has continued their performance push, with the introduction of the dual-channel 939 on June 1, and today, AMD extends their CPU line at the top with the FX55 and 4000+ processors. Meanwhile, Intel's top 3.6Ghz CPU is finally appearing in the retail channel more than 3 months after introduction. While Intel pioneered the move to 90nm, the transition to 90nm has been anything but smooth for Intel, with concerns about heat and the difficulty of moving the 90nm process to the top performance end of the Intel line. AMD has just introduced their first 90nm Athlon 64, which generally appears to avoid the problems that Intel encountered. However, we will not really know whether or not the shrink is a complete success for AMD until we see the top Athlon 64 processors in 90nm.
All of these developments have quickly changed the landscape of the computer market. In the retail market, AMD has moved from a small percentage of the total retail market to even with Intel in the last couple of months. Computer users who scoffed at the idea of buying an Athlon 64 computer a few months ago are now shopping for Athlon 64 computers. Also VIA, which had problems with the PCI/AGP lock in the initial launch of the K8T800 PRO, has fixed these issues with shipping chipsets. VIA also demonstrated a working K8T890 chipset a few weeks ago that features PCI Express and the promise of Dual Video cards in a future K8T890 Pro chipset. Thus far, there are no retail boards based on the K8T890 that have appeared in the market, but VIA promises that they will be here "soon".
All of these developments have changed the landscape for nVidia. In other words, the stakes for CK8 have changed since June. A winner with CK8 would change nVidia from an AMD chipset maker to one of the major players in the chipset market. nVidia seems keenly aware of what is involved and they have pulled out a whole slew of features to win you over if you're looking for an Athlon 64 motherboard.
Facebook
Twitter
RSS
101 Comments
View All Comments
suave3747 - Wednesday, October 20, 2004 - link
#70According to nVidia's website regarding the nForce 4 SLI, it states that the board will have 20 lanes of PCIe. It also states that there will be 3 PCIe 1x slots. I assume that the SLI board will have the option of using 1 PCIe 16x and 3 PCIe 1x slots, or 2 PCIe 8x slots and 3 PCIe 1x slots. Therefore, there is really no "lack" of PCIe 1x slots on the board. That board pictured was probably just a poor representation of the actual retail board.
The thing I am curious to know is whether there will be a reasonable amount of standard PCI slots available for use until PCIe cards for sound and whatnot become more prevalent.
stelleg151 - Wednesday, October 20, 2004 - link
Wesley, now that your done testing the board, if you need someone to take it off your hands I would be willing to take that burden.ThePlagiarmaster - Tuesday, October 19, 2004 - link
Wesley,I'm wondering why the dvd2avi divx 5.1.1 show such close results here. With basically the same machines on hardocp, they show the athlon64 beating Intel's best by HUGE margins (like 20% faster than the 3.6 and almost the same over the 3.4ee)
http://www.hardocp.com/article.html?art=Njc1LDM=
You guys showed the same thing no too long ago, but I can't find the article now. The paragraph under the graphs of the A64 winning said Intel lost the last thing they used to win in the benches. The article appears gone? What happened here, why so different from dvd2avi results at hardocp? They used the same divx 5.1.1 so it's not the encoder or the frontend. Heck even the 3500+ dominated the 3.6 and 3.4ee (more than 10%).
Whatever it is, I think a bit of research needs to be done on what's best for AMD, and what's best for Intel and pit them against each other. Clearly AMD people would run the way hardocp does (though it looks no different than what's used here). While you state you can show whatever you want, perhaps you should be showing the BEST for each platform. Would people really go home and run in a way that makes their cpu look like crap?
When you're talking about cutting 20% off of encoding, that adds up to a lot of time. I'd argue with the statement about divx 5.1.1 exploiting sse3 and making Intel a usual winner. Hardocp has been using 5.1.1 and A64's kill p4's with it (and have for a long time on their site). Is it AutoGK that throws things out of whack? Does it favor Intel so much that it causes a 20+ percent reversal? If it's truly based on dvd2avi how could it be so far out of whack compared to hardocp's scores? I think your readers would want to know which way to encode the fastest with whichever cpu they choose. Why would people want to know what the middle ground is and lose 20% cpu performance? Maybe Xmpeg for Intel, and pure dvd2avi for AMD?
Wesley Fink - Tuesday, October 19, 2004 - link
#73 -The earlier results are on on different test bed with a different video card. If you check out results on the same setup at http://www.anandtech.com/mb/showdoc.aspx?i=2128&am... you will see that the Asus is performing about the same as the other K8T800 boards. It is true that the nVidia nF3 and nF4 perform best with an nVidia card which we have pointed out many times in the past.
Saist - Tuesday, October 19, 2004 - link
just wanted to make a couple of comments:Nvidia's Soundstorm was a result of it's partnership with Microsoft and the Xbox. Since Nvidia is no longer being funded by Microsoft and is no longer involved with Xbox2, there is little reason from Nvidia's viewpoint to continue researching audio.
I also will state that if you are scared of Creative and you want more powerful audio. Get a freaking Via Envy chip. Those are only $20-$30 with shipping and match the Creative Offerings pretty nicely.
Saist - Tuesday, October 19, 2004 - link
Noli - Tuesday, October 19, 2004 - link
For all those disappointed with old AC97 codec sound chip on nf4, why not wait for via's K8T890 with better envy sound? (ok it's still not as good as soundstorm but it's better than AC97 right?). K8T890 also should have dual vid cards and also NCQ disk support... (but admittedly lacks ntune style bios extras).One thing I want to know is if K8T890 only supports nvidia SLI?? Presume so cause it's branded dual GFX. Would be awesome to be able to double up with less noisy ATI cards though. Also, seem to remember that Alienware's dual card solution was NOT SLI and seemed to produce consistent 90%+ frame rate improvements. Anyone know if/when this is coming out?! If so, 90%+ beats nvidia at their own game (and from a computer 'vendor' - ha!).
Disappointed that dual vid cards might be limited to nvidia - 6800GTs are good but still prefer ATI and 2 nvidia cards would prob be too noisy for me...
Spinne - Tuesday, October 19, 2004 - link
When will the nTune software be avaiable? NVidia's download site has a page for nTune, but the download link at the bottom still points to the old System Utility.Rza79 - Tuesday, October 19, 2004 - link
Correct me if i'm wrong but this how i see it:First check this review:
http://www.anandtech.com/cpuchipsets/showdoc.aspx?...
-------------------
Check the Business Winstone test scores:
nForce3 => 30.1
K8T800 => 28.9
Now this review:
nForce3 => 30.1
K8T800 => 26.9
---------------------
Now Multimedia Winstone:
nForce3 => 37.4
K8T800 => 36.9
In this review:
nForce3 => 36.9
K8T800 => 33.4
---------------------
This can't be right?
If the Asus board really performs this bad, then they should have taken another board.
It's harder to judge about the gaming test since they use a different card. Above that, Geforce cards tend to perform better on a nForce platform. So my guess is to have a fair review they should have used a ATI based card like the X800.
Second thing they always forget to mention is the Serial ATA driver for the Via board. I mean this can be an important factor.
I agree with post nr. 69 & 70.
Lately i'm starting to lose faith in reviews from Anandtech, just like i did with Tomhardware a couple of years ago. Seems like you can't get reliable reviews with the big review sites anymore.
Wesley Fink - Tuesday, October 19, 2004 - link
#70 -We will be rewiewing the K8T890 as soon as we receive a retail board. Thus far none have shipped.
The K8T890 reviews at other sites in September were based on a traveling preview board which VIA did not make available to all of the major review sites.