Industry Update - Q4-2004: AMD adds SSE3 Support, Intel's 925/915 not selling and more
by Anand Lal Shimpi on November 3, 2004 1:00 AM EST- Posted in
- Motherboards
AMD Athlon 64 Revision E adds SSE3 Support
As we discovered most recently, AMD's 90nm CPUs are of a brand new revision that featured a number of bug fixes and performance improvements. Internally AMD refers to this CPU revision as Revision D. However we noticed something very interesting when looking at the latest AMD roadmaps while in Taiwan: the 90nm chips listed as San Diego and Venice (Athlon 64 FX and Athlon 64 respectively) claimed SSE3 support as a feature, but the current 90nm chips do not have SSE3 support.
We went around to quite a few manufacturers asking what the difference was between the 90nm chips shipping today and the 90nm chips that supposedly feature SSE3 support, and unfortunately we were left with very little information - until we learned to ask for the right thing.
Internally, AMD's San Diego and Venice CPUs are referred to as nothing more than Athlon 64 Revision E chips. Revision E includes even more bug fixes and performance improvements over those we found in Revision D, including support for the 13 new instructions that were added with Prescott, more commonly known as SSE3.
The performance enhancements that go along with Revision E chips include some optimizations to the Athlon 64's memory controller. The more optimized memory controller improves bandwidth efficiency with regards to unified graphics memory accesses; given that the only type of graphics that uses system memory (and thus the on-die memory controller) is integrated graphics, it's safe to say that the Rev E chips will offer better integrated graphics performance.
The first Revision E CPUs will begin shipping in early 2005. AMD also has plans to introduce an Athlon 64 4200+ towards the middle of 2005; they are not listing whether the part will feature a 512KB or 1MB L2 cache, but it will most likely run at 2.6GHz. The Athlon 64 FX-57 is also listed on the roadmap as a 2H-05 part, it's specifications are also unclear but we'd expect it to be a 2.8GHz part with a 1MB L2 cache. Both the Athlon 64 FX-57 and Athlon 64 4200+ appear to be 90nm parts built on the San Diego and Venice cores, respectively.
AMD's 2005 roadmap did not specifically list anything faster than the 4200+, although the classic "> 4200+" was present on the roadmap to indicate potentially faster parts.
On the Intel side of things we heard the name Cedar Mill thrown around a bit more. In the past some have referred to Intel's dual core Pentium 4 as Cedar Mill, but we now know that is Smithfield. This time we heard Cedar Mill referred to as the first 1066MHz FSB Pentium 4s that aren't Extreme Edition chips. Cedar Mill is supposed to be out in the 2nd half of 2005, which supports a claim we made in our recent review of the Pentium 4 3.46EE: "the 3.46EE will be followed up by the 3.73EE as the only two chips to support the faster FSB for almost a year."
So what does having no mainstream 1066MHz FSB chips until the end of next year mean? It means that Intel is holding out for Glenwood and Lakeport and that Sunday's launch of the 1066MHz FSB was merely a gimmick. The 925XE will be buried as the chipset that offered support for two CPUs that no one bought, while Glenwood and Lakeport will be the knights in shining armor that brought 1066MHz FSB support to all.
Intel seems to have learned from their 925X and 915 chipset launches - multiple fundamental technology changes without performance gains don't go over well. Glenwood and Lakeport will be able to support faster DDR2 (DDR2-667), 1066MHz FSB and dual core support upon their release, not to mention that lower latency DDR2 should be available by then (mid next year) and PCI Express graphics should be much more prevalent as well.
Facebook
Twitter
RSS
61 Comments
View All Comments
ThePlagiarmaster - Thursday, November 4, 2004 - link
Would definitely like more of these articles.I'd have to disagree with the statements on the Pentium M beating an athlon64 though (in any benchmark). You're forgetting that it was running against a SINGLE channel system that had it's memory running on a 266mhz bus if memory serves. It should get soundly trounced by a REAL desktop A64/FX. A faster FSB (800mhz?) won't help the Pentium M much either (It's not bandwidth starved like a P4), so unless they can ratchet up the clock quite a bit it won't be a top performer (which it's not designed to do BTW. It was meant to use low power not ramp up in mhz).
Great chip for low power laptops but you just can't shove it into a desktop and expect it to change it's spots. This is akin to Intel trying to shove the P4 into a dualcore. Which of course, it wasn't designed for. Can you say shared bandwidth? Moral of the story is, don't expect anything special from a desktop Pentium M except a decent SFF system.
I'd also have to wonder about the FX57 in 2H05. One chip in 8-9 months or more? I know there is no need for more, but I'd hope AMD would release an FX59 and just stack the price on top of the current chip at that time (the 57). Even if Intel isn't keeping up. Who cares, just charge more, some of us would want it anyway. Why stop at domination? Why not completely obliterate Intel and gain the all important MINDSHARE along the way? We saw just a feature or two of strained silicon make 2.9 on air do-able on OLD .13 tech (fx55). Clearly this process on .09 with SOI should easily do 3.2ghz or so. I hope they release some and just jack up the price. Vendors like voodoo/falcon would surely like to sell them. Hope the roadmaps you guys saw were OLD :)
jonp - Thursday, November 4, 2004 - link
Anand. Yes, it was a great article. Well written and packed with valuable information. I, for one, would vote for more trips and more reports. Thanks for going and writing so well. Jonnewfc12 - Thursday, November 4, 2004 - link
Very intersesting article, its very hard to find this kind on info through the normal media channels.Keep up the good work.KrazyDawg - Thursday, November 4, 2004 - link
#31I forgot to add one more thing. You might not have the need for 4+ USB ports but other people might. I personally have 6 USB ports in use. I can have 7 with my MP3 player. They're not used 24/7 but I rather not deal with swapping devices and purchasing a USB hub.
KrazyDawg - Thursday, November 4, 2004 - link
#31"To answer the MB maker's question about what would make me get off the dime and purshase a new motherboard...
One that has 5.1 digital out in either Dolby or DTS so I could set it up with other audio equipment. Without that feature they can put most anything they want on a board and I won't upgrade.
A digital out that just does stereo PCM does not cut it.
And any more than 4 USB ports is overkill. Firewire IS required."
If you're idea of upgrading to a new motherboard is based solely on sound you can always purchase a soundcard such as the SoundBlaster Audigy2. I don't think it's reasonable for companies and consumers to pay a "premium" cost for "better" sound. The integrated sound on most motherboards are fine for most users and if you want better you can always install a card. Integrated anything is for cutting down costs which means it won't be offering the best performance most of the time.
#44
"What competes with Microsoft's Windows XP? Linux?? pfft....have u ever tried using that crap? You need a doctorate in 'command line' editing just to get the bloody thing to install."
I hope you're not that ignorant and your comment was an attempt at a joke because these type of comments seem to be everywhere. I've successfully installed Mandrake Linux and RedHat Linux without any problems at all. In fact, it uses a GUI based installation. There's an option for using the command line but there's one for GUI as well. I hope more people do their research instead of basing all their research on one person's opinons. That's one reason everyone is "misinformed" about a product nowadays.
Pete - Thursday, November 4, 2004 - link
Fantastic article, Anand. More, please. :)GeekGee - Thursday, November 4, 2004 - link
Great article... keep 'em coming.Wesleyrpg - Thursday, November 4, 2004 - link
You'd think intel would of learnt from their mistakes (aka the i850 fiasco), and not try to shove SO much 'new' technology down our throats at the same time.DDR2 has no real performance gains, well not yet anyway and plus it's a hell of a lot more expensive, and do be honest why do we need PCI express when AGP cards are just as fast.
Maybe they should of released a 'migration' chipset first where it supported both DDR, DDR2, and both AGP and PCI Express. You just can't release a chipset these days where you HAVE to replace RAM, CPU, motherboard AND video card in one hit.
Intel the Microsoft of hardware? yeah right, with so many other good chipsets out there, i don't think that they have the monopoly that you guys think they have, (well maybe for the intel platform) At least there are other chipsets out there competing. What competes with Microsoft's Windows XP? Linux?? pfft....have u ever tried using that crap? You need a doctorate in 'command line' editing just to get the bloody thing to install.
Whoops i have gotten off the track here.....great article by the way!
K money - Wednesday, November 3, 2004 - link
I, like #40, registered just to comment on this wonderful article (and I'll probably be visiting the forums now often). Anand - you are very informative and insightful, keep up the good work even if that means flying out to Taiwan every other week!AussieGamer - Wednesday, November 3, 2004 - link
#4 "Intel thinks they are the microsoft of the chipset market... "They are.