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
Degrador - Wednesday, November 3, 2004 - link
More of these articles would be great. Any chance you'd have a more specific idea of when SSE3 A64s would be available? I was thinking of upgrading in Jan, but might wait a bit longer for those, but I'd prefer not to have to wait too long (might get a 3000+ and wait for next upgrade for SSE3).Btw, #3, the forum attendees make up a rather small section of computer buyers. Most people purchase from OEMs, and are more familiar with the Intel label. Hence Intel can be as demanding of mobo makers as they like. 915 and 925X give them more advertising power (all advertisers seem to love techno babble and product code names), so Intel want to make it available as much as possible. Even recently I had a friend - who I thought was pretty cluey as far as computers were concerned - buy an Intel 3.0 instead of A64 simply because he's always had Intel machines (didn't believe or trust me in A64 suggestion).
KHysiek - Wednesday, November 3, 2004 - link
I don't get why all mobo makers are so quick to use nforce4 for all segments and exclusively for high-end market (includint enthusiast). Chipset is still buggy (HT 800 only), and after few years on the market they drivers lack a lot of maturity. It will also probably be the most pricey of all.Except SATA2 there is nothing really interesting and standing out in this chipset (SLI is very minor thing, wanted by >0.001 percent of potential customers).
drifter106 - Wednesday, November 3, 2004 - link
I must say this was a well written and informative article. Your style of writing is very much appreciated!! I strongly urge you to continue providing readers and members of this community with technological information. Its icing on the cake!!Decalores!!!
Jeff7181 - Wednesday, November 3, 2004 - link
Anand, what are you doing next week? Up for another trip to Taiwan? (that means I want more articles like this... but don't forget about reviews... Far Cry 1.3 has been out for a while now and a certain other website has a very extensive review of it)IceWindius - Wednesday, November 3, 2004 - link
Its quit obvious that Intel has overestimated themselves, the market and the simple fact that you can only shove so much stuff down peoples throats before they become annoyed.In this case, they tried to hard and to fast to push and shove new technology that showed little to no increase to not only their previous chipset and CPU generation, but showed worse performance in comparions to AMD's offerings, which are much cheaper in every shape and form.
Just goes to show that no corporation is perfect and the fact that Intel, the mother of all that is CPU related is getting its ass reamed in desktop, server and chipset area's show that over confidence and cheast heaving in the end will leave both you and the customer bitterly dissapointed.
Go AMD go!!!
phaxmohdem - Wednesday, November 3, 2004 - link
AMD rules, Intel sucks big donkey dong.....ermmmm. That said I am extremely interested in the release of "desktop" Pentium M Mobo's. I'd love to see desktop comparisons putting this chip up against intels and AMDs finest desktop procs and chipsets. I'm thinking compact, kick ass cluster? Too bad the chips are so frigging pricey. however the energy savings may pan out to help justify the cost a little. Did I mention intel sucks big donkey dong for pricing so damn high? (Whistles and pretends Athlon FX chips don't exist)
Spacecomber - Wednesday, November 3, 2004 - link
I appreciate this "straight from the horse's mouth" reporting. It takes things a step beyond the usual efforts to "read between the lines" to try and figure out what is going on behind the scenes.Keep up the good work.
jimmy43 - Wednesday, November 3, 2004 - link
Intel thinks they are the microsoft of the chipset market...Beenthere - Wednesday, November 3, 2004 - link
It's amazing that Intel has NOT learned from past mistakes... They still falsely believe they can strong-arm the Asian Mobo makers and get away with it forcing them to buy 915 chipsets to get 865's. Intel is their own worst enemy and their poor sales show that reality has caught up to the huge egos and their arrogance has cost them dearly.I suspect the Mobo makers will warm up to ATI's PCIe RS480 Mobo chipset REAL fast when they see that no one is interested in Intel products and everyone is demanding AMD Mobos with Via890/nF4/ATI RS480 and PCIE. All you need to do is look at the forum activity for proof.
I'm sure with ATI selling their own Mobo as they do graphics cards, some Mobo companies will try to use the nF4 as leverage, but that could be a huge mistake. There is plenty of room for VIA/Nvidia/ATI Mobos for AMD's S754/939/940. Since ATI claims they will ship PCIe Mobos first and that these Mobos will be AMD CPUs with Intel RS480 Mobos coming some time next year, it looks like the Asian Mobo companies are gonna have a lot of 915 chipset Mobos they can't sell while ATI cleans up with AMD PCIe Mobos.
The Times, they are a changin for the better. With AMD owning the desktop market and now making serious inroads in the server segment, and Intel without a clue or a canoe for two more years, consumers are the real winners. Any Mobo company that wants to still be in business in 6 months better be offering the latest and greatest AMD processor Mobos or they'll be suffering the same financial woes as Intel is finally admitting.
Kaji - Wednesday, November 3, 2004 - link
Nice one! Would definately be cool to get more of these... it gives a great insight into the current "state of industry"Maybe you could videoconference instead of flying to taiwan everytime :)