The Consequence of Waking Up a Sleeping Giant: Intel Roadmaps Inside
by Kristopher Kubicki on January 25, 2005 7:44 PM EST- Posted in
- CPUs
Dual Core on the Horizon
So we lied originally - we have even better news. Dual core Smithfield processors, which are really nothing more than two Prescotts slapped together with independent caches, are scheduled to launch a little earlier than we originally claimed in previous roadmap articles. In fact, part of the push to launch so early seems to be to coincide with the 945/955 launch as those chipsets are the only ones to support the multiple core processors. Recall AMD's dual core launch strategy is to enable existing hardware (nForce4, K8T890, 8xxx) to run multiple cores. So while you can't plug a Smithfield into your existing 925X motherboard, it may be for the better. DDR2 has plenty of bandwidth to offer, but as we have seen in server benchmarks, multiple Pentium 4's competing on the memory bus can be quite slow. Dual core Pentium 4's might be horribly inefficient without DDR2-667, however that is another theory we can put to the test on launch day. If you look carefully, you'll see the Smithfields launching only at 800FSB. We find it slightly unusual that the entire 945/955 platform supports a front side bus speed that two $1000 SKUs utilize.
| Intel Dual Core PerformanceDesktop Lineup LGA775 | ||||
| Processor | Speed | L2 Cache | FSB | Launch |
| Pentium 4 840 | 3.20GHz | 2x1MB | 800MHz | Q2'05 |
| Pentium 4 830 | 3.00GHz | 2x1MB | 800MHz | Q2'05 |
| Pentium 4 820 | 2.80GHz | 2x1MB | 800MHz | Q2'05 |
Also note that the dual core processors on the desktop do not support HyperThreading. The server implementation of Smithfield, "Dempsey," has HyperThreading enabled. For database applications, this makes sense - although we have known for a long time that single threaded applications take a performance hit when a HyperThreading processor exclusively runs that program. Interestingly enough the Smithfield lineup has some very competitive price points according to the launch data. The 820, 830 and 840 models will launch at $241, $316 and $530 respectively - compare that to the Pentium 4 lineup today [RTPE: Pentium 4 775]. At today's prices that's only an $80 premium on the second core.
Facebook
Twitter
RSS
74 Comments
View All Comments
jiulemoigt - Friday, January 28, 2005 - link
#42 the problem with Rambus was the company tried to make the entire industry pay them for DDR2 because of tech they suggested to the Industry standards comision without telling them they patented it already when the Standards comminty was tring to find open standards. That and it is like P4 a long pipe when forced to branch wastes clock cycles{way to often}.Zebo - Friday, January 28, 2005 - link
Unless they get 2-2-2 DDR2 out AMD is wasting it's time (and performance) with DDR2. Negitivty twards Intel? Probably because they keep pimping that marketing gimmick called netburst. And heaters called prescott, but worse this time with two. EVERY, I mean every CPU in history has worked twards more effecientcy. Not intel.You can read about it all here.
http://arstechnica.com/articles/paedia/cpu/pentium...
That article includes the excellent Dothan too, which they should have done in the first place instead of raising our power bills and room temps.
JarredWalton - Thursday, January 27, 2005 - link
#34 and #35 - Why all the negativity towards Intel? I certainly don't think this is all the greatest thing ever, but it's a welcome change from the last 3 months of Intel roadmaps where chips were canceled and release dates were postponed. AMD is still way back in terms of revenue, and that isn't going to change over night. I hope they continue to make improvements in their design, but anyone that thinks Intel is just sitting still is loco, plain and simple.As for the technologies you "poo-poo" above, DDR2 is an industry standard. AMD is avoiding it initially because they don't really need it yet, so when they do need it they can just join the club. That's fine, but at the same time it's good to have one company pushing things forward. AMD pushed 64-bit and forced Intel to join them, and Intel is pushing DDR2 and FB-DIMM technologies, which will benefit everyone in the long run.
In retrospect, do you REALLY think Rambus memory was that bad? It wasn't necessary on the Pentium 3, and it was more expensive than DDR at the time, but economies of scale come into play. If the public had not had a huge backlash against RDRAM, it would probably still outperform equivalent DDR on Intel platforms. The only real problem with RDRAM was that it was a closed standard, so you had to pay royalties.
If you look at the big picture, none of these companies are really out there trying to make the world a better place just for altruistic purposes. They all want to make money. If AMD gets bigger, it will be because they're making more money, and generally speaking that means that they'll be acting more like Intel. To #39, I would say that it *IS* a competition, and we want it to stay that way. If it just becomes another ho hum update each year, we'll end up just like the car industry.
danidentity - Thursday, January 27, 2005 - link
One more question, is there any confirmation to the rumors that the 6xx series of P4's will have downward unlocked multipliers because of EIST?Anemone - Thursday, January 27, 2005 - link
From what I"ve seen a 600 series @ 3.6-3.8ghz should keep up with the FX55 in a lot more games than you'd think. That's based partly on results of EE's clocked @ 3.7-3.8... Of course we will see soon, but of course AMD might easily find another 200 speed bump somewhere too.If you all remember the performance bump from the 845 to the 875, I think you might want to give some thought as to just what "could" be provided by the 955.
I'm also rather sad the 925XE 'may' not accept the dual core. Oh well. If they'd get rid of that idiotic oc lock, I'd spring for the 955. Would be nice to get back to 875 days or better imo.
I'm mostly glad the two are so tightly in competition. I bet that doesn't make Intel happy but it is sure doing nice things for customers. Again, with the exception of the OC lock which was a stupid mistake...
Quanticles - Thursday, January 27, 2005 - link
#8, AMD partners with IBM for their fabricationAll of this is the same old inefficient core slapped together with a little bit more cache, a faster FSB, blah blah blah. Their dual-core setup with have an amazing 10% performance increase I'm sure, maybe that extra cache will make up the last 5%. Now if only this stuff wasnt being released a year from now, cause I'm sure AMD will have better than this in the next 6 months - they just keep their cards to themselves.
Anandtech - tnx for hyping this for Intel. Every page had even "better" news, although I'm not sure who the news was better for. You make it sound almost like a competition.
KristopherKubicki - Thursday, January 27, 2005 - link
Peter: Surely you jest. The predecessor to PowerNow! technology showed up in spring 2000. The first real production processor with PowerNow was the mobile Athlon4 line in May 2001 - which had 5 frequency stages and 6 core voltage stages.Not to split hairs or anything, but the first P3 to show up with speedstep was the 600MHz variant which showed up 3 months before K6-2+ in Jan 2000. In Q2'01 SpeedStep improved and which allowed dynamic clocking, but also allowed voltage adjustment with deepsleep.
Concerning latency: EIST today requires a 30microsecond delay to transition frequency, 100microseconds for voltage. Last I checked the AMD driver for CNQ had a 0.03 second hard delay on frequency/voltage adjustment.
OK fine - things are even up until 2003. Then something called Pentium M showed up in Q1 with EIST. EIST goes beyond changing the clock speed and voltage and will actually switch processor logic on and off when it isnt needed. On the Yonah processor EIST will actually disable portions of the cache it isnt using.
CNQ just isn't doing this yet, but Intel already has 2 years of experience doing that with Banias/Dothan. If we want to talk about innovation, what has AMD been doing for the last 2 years with PowerNow other than renaming it to Cool N Quiet for the K8?
Kristopher
KristopherKubicki - Thursday, January 27, 2005 - link
Live: there are two launches - one of the 6xx line, another a little bit later for 945/955. I dont know if the dual core launch falls at the same time as the 945/955 launch but there will be more data available then at least.Kristopher
Live - Thursday, January 27, 2005 - link
O I whish we could edit our comments. CeBIT is of course in February not March. My whole guessing game kind of falls a part if it would be in March.“So launch in February it is, which coincides with CeBIT Hanover 10-16 February.”
miketheidiot - Thursday, January 27, 2005 - link
First of all I see nothing on here that will allow intel to take back the performance crown. Of course I already see that intel probably will win the dual core publicity/prestige/etc, even though I think their design will probably be garbage.#8, amd has had 90nm out for 3 months and it has worked much better than intel's 90 IMHO. Second they are well into the construction of another fab, so I highly doubt they will go fabless any time soon. On top of that intel was, and still is, getting its ass handed to it by AMD 130nm
#34 there was some news about AMD unfortunately going to ddr2 in '06. This will require a new socket, so if there is to be a Hypertranport2, which I do remember hearing, it probably accompany that change.
I do hope that Intels accelerated dualcore will get AMD to start moving a bit quicker. They demoed dual core quite a while ago, I would suspect that it could go into production very soon if they really needed it to.