PDA

View Full Version : Intel vs. AMD - The Road Ahead



Acid
04-22-2002, 02:25 PM
Feel free to post any concerns or questions you have regarding this article here.

http://www.tweaktown.com/document.php?dType=review&dId=236

Typedef Enum
04-22-2002, 04:01 PM
The thing we, the consumers, have to always bear in mind is that, despite what we want (be it higher bus freq. for the Athlon, eDRAM for 3D chips, etc), the business side of things will always be factored into the equation.

As I'm looking at the current pricing scheme's for the AthlonXP/Pentium4, it's pretty obvious which one is logical choice...despite the shortcomings of the platform. So, even if Intel were to bring a quad-pumped 133 MHz FSB to the market today, you can also imagine that they would price those chips higher than the current P4 lineup.

The current price ratio between their respective high-end chips is basically 2:1...By the time Intel releases their next major chip, it might be slightly higher (I would expect it to be higher)...At the end of the day, will it really prove to be a difference maker for consumers? Perhaps...

But by that time, there's no telling how AMD's products will fare in comparison, again, despite their shortcomings. Personally, nothing is going to excite me at all until the Hammer is released. I have held onto my 1 GHz. Athlon (clocked to 1.33 GHz) since early 2001, and don't have any real need to upgrade, *despite* the fact that I use this system for doing reviews.

Anyhow, I expect the advances that Hammer bring to the table will more than makeup for these things...

Darksword
04-22-2002, 05:19 PM
I agree with you on the pricing. Regardless of how cool Intel's chips run I doubt most people are going to spend $550.00 for a top of the line Pentium 4. One could always just spend about $200.00 for a 1.8Ghz P4, but since it will perform slower than a 1.733Ghz Athlon XP you might as well just get the latter.

Performace-wise, DDR above RDRAM and it is quite a bit cheaper to build a DDR-based AMD system than a DDR-based P4 rig. AMD does need to ramp up speeds with the Thoroughbred, but I don't think they are in too much trouble yet of just being delegated to the low-end value segment.

As always, only time will tell though.

Anonymous
04-22-2002, 07:50 PM
What I find interesting is the fact that no where in the article was there mention of an RDRAM based system. DDR400 was thrown around quite a bit, but in analyzing the performance over the next year or so, I do think that it is important to consider RDRAM for the P4. As old as it is, the i850 still outperforms most competitors(arguable all). With the i850E coupled with PC1066 or even PC1200 RDRAM, I think that RDRAM deserves serious consideration. In terms of performance, there is a good chance that the P4 with 533FSB and PC1066 RDRAM will be the leader. So, why was it not mentioned in the article?

Mr.Tweak
04-22-2002, 07:59 PM
The article was based around DDR and not other memory techniques, at the moment. Chances are we will keep this article updated on an on-going basis and include things like RDRAM. Things like RAMBUS 2 we'll talk about later.

Molman
04-22-2002, 09:54 PM
With Intel arguably moving away from RAMBUS memory (see: http://www.ebnews.com/story/OEG20020226S0040 ) it will be interesting to see what happens in terms of future pricing/and acceptance. As it stands the P4 was designed for the high bandwidth that only RDRAM can provide, so this is where the best performance can be had (at a price).

As mentioned the price verse performance ratio of AMD cpu's leaves allot in AMD's favour that I think will bear AMD well until Hammer makes it appearance (possibly 2002 Q4 unlike the 2003 mentioned in the article). The ability for AMD to produce CPU's with a very small footprint has allot to do with this, basically allowing AMD to get more per sheet of silicon. This interview here with Jerry Sanders is quiet a good overview of AMD past, present and future (See:http://www.upside.com/texis/mvm/news/story?id=3c98da541)

What Hammer brings isn't just a new CPU, but an entirely new platform and selection of technologies - SOI (See:http://www.deviantpc.com/articles/SOI/index.shtml), integrated memory controller (lower memory latency) and HyperTransport interface to name some (See:http://www.aceshardware.com/read_news.jsp?id=55000382). The design of Hammer further allows for simpler motherboard layouts (4 layers) which hopefully will translate in to cheaper AMD motherboards in comparision to P4 parts (See:http://www.aceshardware.com/read.jsp?id=45000313).

Final key point I'd like to raise is upgrade ability. By sticking with the current 266(133mhz) FSB AMD until Hammer creates an upgrade path for current socket A owners, something that Intel owners haven't had of late. Obviously AMD have the option for more to a 333(166mhz) FSB but from all reports with the current architecture - EV6 bus - this results in marginal (if not no) real world performance increase. (See: http://www.anandtech.com/cpu/showdoc.html?i=1595&p=12).

So do I see the AMD being left behind with only value processors . . .no, most certianly not. From the first Slot A Athlon AMD has gone from strength to strength slowly eating market share from Intel. I don't see this good execution failing soon, where as Intel has struggled with competition in the market stumbling along the way only now really finding their footing again recently. I predict Hammer will, if brought to bear as promised, require something special from Intel in retaliation. At the end of the day it's us, the consumer who will always benefit from this market competitiveness, and that's what should really matter wether it be AMD or Intel.

Soverign
04-22-2002, 11:28 PM
I agree with most of you in this reguards

While AMD do have a strong platform at the moment i fear it will loose some groung very shortly with 533FSB, DDR 400 (RDRAM at this point is not worth mentioning as Intel are moving away from RDRAM) will make shorter work of the AMD CPU now.

On the Value side AMD will either have to increase the Duron's bus as it can kill a P3 core Celeron but P4 core will leave it dead now with its lower FSB and lower cache

You won't see RDRAM for P4 533FSB last long as its even more expensive than currant RDRAM (which is almost non-existant today). Intel has already developed its chipsets for the P4 533FSB and they are moving towards DDR-SDRAM rather than RDRAM as the I850 is the last of the line or RDRAM chipsets and even in high end server RDRAM is being shoved aside in place of DDR and Dual Channel DDR SDRAM sollutions

RDRAM at PC1066 and PC2100 will not last long against 5.3GB/s Dual Channel DDR-333 and Dual channel DDR-400 at 6.4gb/s. more than enough for bandwidth for P4's new bus.

As Tweak said we will be updating this article (most likely every end of quater) to reflect on our speculations and make future speculations

That my rant for this evening

Anonymous
04-23-2002, 12:20 AM
I have a few problems with the article...

While it addresses memory issues quite well, it tends to quickly gloss over (or not mention) many of the others...

1. Along with deeper pipelines (and their associated problems of higher latency which was mentioned...), the P-IV suffers from a very poorly designed FPU. The only apparent solution Intel has for this is SSE2 (if your software has it...most don't)

2. Duron is due to be discontinued by the end of this year (according to the Conference Call by AMD last week). This means that the AthlonXP will actually be the low-end part, and the Clawhammer will replace it as the flagship.

3. The Hammer chips are a full generation ahead of the P-IV. Molman has some excellent points, but allow me to expand...
a. Memory controller on die - allows for the increased memory bus speed as system bus increases
b. MUCH lower latency (because of "a") which allows for longer pipelines and increased clock speed with no net decrease in IPC (instructions per clock)
c. It will be able to address >4 Gig of Ram (I know that seems ridiculous today, but how long ago did HDDs top out at 500 Meg and processors at 90MHz?)
d. It should be priced along the lines of today's P-IV, with 64 bit ability to rival the Itanium and simultaneous 32-bit ability of a 3.4 GHz P-IV (quite possibly in stores by Xmas...)
e. Hypertransport connections to all points
f. Motherboards shouldn't require much of a Northbridge (if any) because most of this function is built into the processor (much cheaper chipsets/motherboards...), not to mention Molman's point of 4-layer boards.

One last point...I see it was mentioned that if Nvidia were to base their Nforce on the P-IV it would show far more significant gains than on the present Athlon. While this seems plausible, I would be stunned if it ever happened...
1. Intel won't license Nvidia with the P-IV's bus as this would be a major and superior competitor to their own chipsets (unlike SIS who are strictly bargain chipsets...)
2. NForce uses Hypertransport (owned by AMD...)

Just my .02 worth...

Cheers,
Charles

Anonymous
04-23-2002, 02:56 AM
ahmen to that Charles! hit that right on the head.

pAc

Anonymous
04-23-2002, 03:22 AM
Well, I was going to reply to this article in regards to AMD's updated roadmap, which does phase out the Duron and moves the Hammer in, possibly as early as even late October!!! This is speculation as well, but some rumors are floating around that AMD will be making additional architectural changes to the Barton core. So there will be 512Kb L2 cache and possibly some other things though AMD hasn't said what. To me, it looks like Intel better step it up while it can cause I think AMD has something big planned for the entire computer market. (IE Hammer)

Typedef Enum
04-23-2002, 06:42 AM
I think the other thing that wasn't accounted for in the article is the rumour (and it's more than a rumour...) that Intel dispatched a team to slap together *something* that's very similar to the Hammer...

If that doesn't smell of deparation, I don't know what is...In the field of engineering (of which I'm one...Computer Engineer to be precise), you don't just put together a team of engineers and instruct them to "do whatever you can to take some existing architecture, and change it to model/compete with the-other-guys offering...just in case"....If you catch my drift.

Even when Intel moves to .13u, look at how it will compare to Athlon's Thoroughbred...and then analyze the price/performance issue again.

It's just like with nVidia GPU's...Could nVidia produce some killer-ass 3D chip with gobs of eDRAM, 512-bit memory interface, multiple-chips, etc ? Of course they could...In the end, does the cost justify such a product? No way...Not yet.

With every successive generation of chips, people keep insisting that they move towards higher bandwidth architectures (don't get me wrong...I'm all for it)....As it now stands, the GF4 is approaching 70 M trans....Do you realize how much larger the chip size would be if/should nVidia do that right now? Or 2-3 generations ago? What about yields? What about profit? Until such time that they can pull it off from a technology standpoint AND a business one, they're not going to commit to such features...and the same goes for AMD.

If anything, if you forget about the P4 for just a second, and concentrate on the true next generation platforms...It's pretty darn clear to me that AMD is right where they want to be, and Intel is trying to figure out how to contend with AMD.

As was mentioned, the _very_ kool architectural changes that Hammer will bring about certainly add a lot of credibility to that assessment, not to mention the fact that they're going to beat Intel to the 64-bit Consumer platform game....

If you thought AMD was being a little bit creative/deceptive/etc with their XP marketing, wait until Intel does the same with respect to the Hammer.

Oldbugger
04-23-2002, 07:36 AM
I tend to agree with Charles in his comments....

we know the PIV produces less per clock cycle (about 2/3) what the current Tbird/Palamino core can produce because of its horrendous 20 stage pipe....and thats the only way it keeps up is by increased frequency...purely viable because of its lower work rate per cycle..... How long can the clock speed be scaled to cover poor core design????

We know the hammer will have 512K L2 cache (on their roadmap...later this year)

The bus speed is not really a product of the CPU....its the chipset that carries the weight.....thats how I can run my 1200 tbird at 12*100 or 8*133. There are some timing issues but these are minor.....Intel has put a lot into its chipsets to support the quad fsb....AMD and its chip make

rs will do the same....and as the Nforce shows it is achievable sooner rather than later.

I think we will see much of the same....a bit of a blip for AMD with Hammer but that is all dependent of OSs and apps which will use the 64 bits anyway.......it is very nice having a car that can doo 500kph....useless if the roads only let you actually do 100kph....

What is interesting is that they have a version of Hammer already running on a 64bit version of Wiondows...see here
http://www.theinquirer.net/23040208.htm

Looks good for all of us....if Intel and AMD keep at each other and stay about even then WE ARE THE WINNERS.....as soon as one or the other gets too far ahead then that company can start dictating the game (just like M$ do) and we would all be losers.....

Just hope for our own sakes that they stay about even

PS Here's another interesting article discounting the fsb fears http://www.theinquirer.net/19040202.htm

Acid
04-23-2002, 08:50 AM
Charles, firstly the article was directed at the high-end market, not the value market which is why I focused totally on the AthlonXP and the P4.

Secondly, I didn't comment on the Hammer because as you said, it IS a whole new architecture and it is impossible to speculate on how it will perform, especially against Intel's 64-bit processor. What I did say is that, if the only change AMD will be making to their AthlonXP before the Hammer is upgraded cache and a shrinked die, Intel have a very good chance to pull far ahead as far as performance is concerned.

Think about it. If the 2.4GHz P4 outperforms the 2100+ now, how much better do you think it will go with a 533MHz bus, DDR400 and dual-channel DDR memory?

When I was talking about the nForce, I wasn't saying that nVidia should go out and make a chipset for the Pentium 4. I was merely trying to give an example of Dual-channel DDR and show how it could benefit the P4.

Anonymous
04-23-2002, 09:47 AM
If you check the excellent review of Pentium 4 vs AMD Athlon XP on www.aceshardware.com, a dual Athlon MP 2000 system is still faster than a 2.4 GHz Intel Northwood. Results on database transactions per second are 151,919 transactions per second for an Intel P4 2.4 GHz system, and the dual AMD Athlon MP 2000 system does 231,333 transactions per second. Also the AMD 760MPX chipset has two slots at 533 Mb/sec, and it's not vaporware! I have one of these ASUS duallie systems running and was pleasantly surprised at how stable it is, how cool it runs CPU temperature 109 degrees F after running days on end, and how quiet it is. Based on data presented in the aceshardware.com review, the AMD MP2000 system even outperforms a dual Xeon 1700 system, and the Pentium 4 2.4 GHz system wins only one of the dozens of tests.

For my part, I will stay with AMD systems, because they offer a better combination of high performance and low price.

Acid
04-23-2002, 09:50 AM
If you check the excellent review of Pentium 4 vs AMD Athlon XP on www.aceshardware.com, a dual Athlon MP 2000 system is still faster than a 2.4 GHz Intel Northwood. Results on database transactions per second are 151,919 transactions per second for an Intel P4 2.4 GHz system, and the dual AMD Athlon MP 2000 system does 231,333 transactions per second. Also the AMD 760MPX chipset has two slots at 533 Mb/sec, and it's not vaporware! I have one of these ASUS duallie systems running and was pleasantly surprised at how stable it is, how cool it runs CPU temperature 109 degrees F after running days on end, and how quiet it is. Based on data presented in the aceshardware.com review, the AMD MP2000 system even outperforms a dual Xeon 1700 system, and the Pentium 4 2.4 GHz system wins only one of the dozens of tests.

For my part, I will stay with AMD systems, because they offer a better combination of high performance and low price.

Thanks for that unrelated post, now tell me where in the article I was talking about the Server/Workstation Market? To quote myself:

I am only going to be talking about their desktop processors as that is the only concern we have in this article. The server/workstation and mobile segments are totally different issues altogether.

Molman
04-23-2002, 10:11 AM
Thanks for that unrelated post, now tell me where in the article I was talking about the Server/Workstation Market? To quote myself:

I am only going to be talking about their desktop processors as that is the only concern we have in this article. The server/workstation and mobile segments are totally different issues altogether.

Don't be too hard, I think his post is quiet relevant in that the Multiprocessor market 'is' slowly moving to the desktop. Anyhow I thought I'd make this little post of what the current roadmaps, rumors and releases show for the Athlon and P4 this year. I've only looked at the top desktop CPU's coming out and ignored the other segments.

Current
AMD - AMD Athlon XP (Palomino) 2100+
Intel - Intel Pentium 4 (Northwood A) 2.2Ghz

Q2
AMD - AMD Athlon XP 2000+, 2200+ & 2400+ (Thoroughbred)
Intel - Intel Pentium 4 (Northwood B) 2.26 & 2.4Ghz

Q3
AMD - AMD Athlon (Barton) 2600+
Intel - Intel Pentium 4 2.5Ghz, 2.6Ghz (Northwood A), Intel Pentium 4 2.53Ghz, 2.66Ghz (Northwood B)

Q4
AMD - AMD Clawhammer (Hammer) 3400+
Intel - Intel Pentium 4 2.8Ghz (Northwood B)

AMD
Palomino - 0.18u, 266mhz FSB
Thoroughbred - 0.13u, 266mhz FSB
Barton - 0.13u, 266mhz FSB, 512 KB L2 cache
Hammer - Totally new. See links and discussion above

Intel
Northwood A - 0.13u, 400mhz FSB
Northwood B - 0.13u, 533mhz FSB

I don't know about about everyone else, but at no point do I really see AMD falling far behind Intel (if at all).

Acid
04-23-2002, 10:30 AM
In the end it's all a matter of waiting for the benchmarks. Some people will agree with the article and some won't, but until we see some evidence, everything is just speculation. At this point, arguing is pointless.

viditor
04-23-2002, 10:33 AM
"Charles, firstly the article was directed at the high-end market, not the value market which is why I focused totally on the AthlonXP and the P4"

Fair enough Asher, I was referring to your comment on page 5
"In the value segment, AMD plan to keep the Duron on the Palomino core till Quarter 3 of 2002 , when they will be releasing their Appaloosa core that not only shrinks the die to 0.13, but also bumps the FSB up to 133MHz (266MHz DDR)."
My point was that by the end of this year (about the time Intel's 533 MHz parts come out) the Athlon XP will BE the value market, and the Clawhammer will be what the P4 is competing against.

"Secondly, I didn't comment on the Hammer because as you said, it IS a whole new architecture and it is impossible to speculate on how it will perform, especially against Intel's 64-bit processor"

Again, fair enough...my point is that this is a common mistake today (IMHO) because while the Clawhammer will indeed be 64-bit capable, it's market is the high-end desktop. Itanium won't be it's major competitor (that's Sledgehammer's domain), the P4 will be...and while a bus and clock speed increase will help the P4 enourmously (as you pointed out), it shouldn't come close to what the Clawhammer's new architecture can achieve.
As an aside, Clawhammer is already sampling and being demonstrated. We should be seeing reviews as soon as the NDA's run out (a little birdie told me...<grin>).

Cheers,
Charles

Anonymous
04-23-2002, 11:12 AM
Hammer should have to start off a 533mhz bus, which was reported a long time agoto make Intel's 400 look dated. dual channel ddr for the sledge hammer, not clawhammer.

Anonymous
04-23-2002, 12:02 PM
Hammer should have to start off a 533mhz bus, which was reported a long time agoto make Intel's 400 look dated. dual channel ddr for the sledge hammer, not clawhammer.

. . .arrrh I don't believe Hammers bus has be specified (feel free to point me to something that says otherwise) and 533mhz P4's are due out soonish.

Molman
04-23-2002, 12:09 PM
. . .arrrh I don't believe Hammers bus has be specified (feel free to point me to something that says otherwise) and 533mhz P4's are due out soonish.

. . .oops forgot to log in :cantfocus

Anonymous
04-23-2002, 12:51 PM
true, 533 is not as big as a deal now, it's now even with the p4

where I read it was from long ago, but AMD is not using the old DEC bus anymore with hammer, but Hypertransport. Ok I agree that it doesn't mean a 533fsb, but it will be easier without it.

Anonymous
04-23-2002, 01:27 PM
What would AMD have to do to make the Athlon run at a higher FSB frequency? What is involved engineering-wise? Is it possible to do something like the quad pumped bus of the P4?

Oldbugger
04-23-2002, 03:41 PM
How can the article purport to look ahead and ignore Hammer......which is a highend desktop chip as much as a server....the Intel Itanium is relegated to servers cause of the cost and and its very architecture......but the Hammer will compete directly with the PIV.....thats what needs to be looked at if you are indeed looking forward......

Mr.Tweak
04-23-2002, 03:44 PM
. . .oops forgot to log in :cantfocus

Just a matter of days now before the 533MHz FSB P4 is released... ;)

Mr.Tweak
04-23-2002, 03:45 PM
What would AMD have to do to make the Athlon run at a higher FSB frequency? What is involved engineering-wise? Is it possible to do something like the quad pumped bus of the P4?

An entire new architecture I'd say.

Oldbugger
04-23-2002, 04:07 PM
I certainly hope that AMD and Intel keep as close as they are....I would hate to see AMD jump ahead as much as I would hate to see Intel jump ahead too.....look at the benefits we have gotten over the last 2 years.....and our current crop of processors has a heap of application redundancy in them....they will last and do the job WE want for quite a while...and all this is because Intel and AMD have been competing.........

I hope it continues to a close contest.......up to the Athlon Tbirds there was a real convergence of technologies...all heading in the same direction and using the same technology.....

With the Athlon Tbirds/XPs and the PIVs the paths have diverged a little making that bit harder to get an apples to apples comparison......but who the F%$# cares.....my Tbirds will do JUST AS GOOD A JOB as a PIV.....labels don't matter...whether it is a PR 990000 ..or a bloody squillion gigahetz .......we NEED AMD and Intel to remain close in the "comparitive" performance stakes but we need an INDEPENDENT assessment of processor capabilities for that....

At the moment Intel is boasting about the revs it does while AMD says it can pull more weight.....true both of them....but its like the speeding driver who has to tell the judge by how much he broke the law.....you can't rely on either......

I was a little disappointed with Asher's article claiming to look forward but focussing on one aspect of processor performance....indeed the article reflect more the support the processor gets from the mobo and chipset that was the tone.....especially when you consider simple little things like the OS and drivers can make more difference to a machines' performance probably than raw grunt.......without much being evident.....

What we need is to look at how the differing architectures will enhance the processing capacities of the chips....like the long pipeline of the PIVs is good for graphics type stuff..especially with SSE2.... and how the onboard memory controller of the Hammer will boost the performance....I think the architectures are too different for a direct comparison without that comparison being on specific aspects of the processors capabilities....and how do you get an overall winner?????who knows..it depends on what you want to do with the processors as to which is most suitable......it really is that different already.......I just hope Intel and AMD don't wake up to that fact and keep trying to outdo each other....I'm gunna luv getting a XP 2gig+ chip for next to nothing.......

Anonymous
04-23-2002, 05:16 PM
I think the article is flawed because it doesn't really mention Hammer, it just says that by the end of the year AMD will have 256 KB L2/266 MHZ fsb machines against dual channel DDR 533 MHz fsb P4's. Clawhammer is launching in Q4 and Sledgehammer is launching first half 2003. Clawhammer launches at 3400 +, so I'd say that by the end of the year AMD will be positioned at the front of the desktop market, unless Hammer misses its release (and current indications point to anything but).
In the low end segment AMD will have a cheap but high performance 512KB L2 Barton core getting pumped out at UMC vs. a crippled P4 Celeron. It's easy to see what will be the best in that segment.
In the high-end desktop market AMD should have a 3400+ Clawhammer produced on a 0.13 micron SOI process (with 3 more speed grades getting released within 1 quarter of its introduction) vs something like a 3GHz P4. I don't think anyone can deny that AMD's flagship will at least be competitive.
AMD will be untouchable in the server market. Sledgehammer will provide dual-channel DDR bandwidth for each CPU in configurations of up to 8, with high speed hypertransport connections between the CPUs. AMD will have full compatibility with all x86 software, will support 64 bit for addressing more than 4GB of memory, and should handily outperform Itanium. I'd take a guess that AMD will probably be significantly cheaper also, even if this isn't that important in this market.

viditor
04-23-2002, 07:51 PM
"Just a matter of days now before the 533MHz FSB P4 is released... "

Huh? Did I miss a meeting? All news articles and reviews I've seen (including rumours...) put the release at September-ish (if nothing bad happens...). And if the launches of the past 2 years are any indication, Intel seems far more prone to "paper launches". This is why I don't expect to see any 533 MHz FSB parts until Xmas time (though I may be thinking a bit too cynical here...).
From THG, 25/2/02:
"We have tested the processors that Intel won't be bringing you until Fall of this year at the earliest. Most of all, we look at the Pentium 4/2666 and Pentium 4/2533, which are the first CPUs to offer support for 533 MHz Rambus"
That's why I was comparing it to the Clawhammer instead of the Athlon as they will probably both be on the shelves within a few months of one another. One last tidbit (educated guessing...), it is appearing more and more as if Microsoft will be supporting the Hammer series in both 32 and 64 bit modes...

From Amdmb.com
"Microsoft is going to announce on Wednesday a new Windows XP version for 64-bit operating systems and that it will have support for the AMD Hammer line of processors"
This is speculation on their part, but I tend to believe that MS will be making that announcement soon none the less...
http://www.amdmb.com/index.php#News-4284

Cheers,
Charles

Mr.Tweak
04-23-2002, 07:54 PM
We've also been testing a P4 533MHz FSB processor, I can't say anymore though due to an NDA agreement. I may be wrong about the release date, time will tell.

Molman
04-23-2002, 09:14 PM
We've also been testing a P4 533MHz FSB processor, I can't say anymore though due to an NDA agreement. I may be wrong about the release date, time will tell.

NDA's aside all reports/indicators point to a Intel Pentium 4 (Northwood B) 2.26 & 2.4Ghz out this Quarter - Quarter 2 (actually May 6th I believe?). Along with the Intel i845E chipset (Brookdale-E), Intel i845G chipset (Brookdale-G), Intel i845GL chipset (Brookdale-GL), Intel i850E chipset (Tehama-E) & Intel ICH4 south bridge.

i845E - 200/266/(no 333)DDR memory, 533FSB
i845G - as above but Intergrated GFX ~ GF4MX level using TileBase (ala. KyroII) Tech.
i845GL - a above minus the 533mhz FSB - 400mhz for Celly P4's coming out.
Intel i850E - RAMBUS platform - PC1066 or RIMM4200 with AGP 8x etc . . .

so yeh, there is going to be a little bit of a bump ahead for Intel until AMD gets their parts out, but at the high cost the parts will most likely be introduced at I'd be holding out for AMD's solutions before I made a buying decision (or at least late May when Intel is due to drop prices again).

Mr.Tweak
04-23-2002, 09:48 PM
Pretty much spot on there from what I've seen and heard.

viditor
04-23-2002, 10:56 PM
"NDA's aside all reports/indicators point to a Intel Pentium 4 (Northwood B) 2.26 & 2.4Ghz out this Quarter - Quarter 2 (actually May 6th I believe?). "

I don't disbelieve you guys, it's just that I've been scouring the news and the web for just that and I still can't find anything sooner than August (except for some old roadmaps from late last year...). If you have any link I would appreciate it. If not, but you're rock solid on the time frame PLEASE post that too!
I make my income through my investments (mostly tech) in the US, and this might affect things in the short-term for me...
Many Thanks!

Cheers,
Charles

Mr.Tweak
04-23-2002, 11:05 PM
I'm restricted to what I can say, expect something soon though.

viditor
04-24-2002, 12:53 AM
Thanks Cam...NDAs can sure be painful! :-)
As an additional note, it's looking like Microsoft is indeed backing the Hammer... Word is the announcement hits tommorrow night (Sydney time) along with JS3's retirement as CEO of AMD.
http://biz.yahoo.com/bw/020423/230097_1.html
http://www.theinquirer.net/a_23040205.htm

This is probably a bigger boost to AMD than any memory or FSB change could ever be! They will be the ONLY chip made to run both 32 and 64 bit software natively (until/unless Intel develops Yamhill)...just bought more shares 10 minutes ago! :-)

Cheers,
Charles

Anonymous
04-24-2002, 02:46 AM
For those that say the article is 'lacking' because it does not address hammer are also missing the point that the article does not address future intel chips.

The article is taking an analytical look at the here/now and the next 6-9 months.

Though we cannot say what hammer will bring, we equally cannot claim on what Intel's Prescott (.09 micron P4) will bring. This is due out sometime early next year, and rumors are abound on this chip...

Rumors now...
- 1 meg L2
- 800MHz FSB
- And more die changes in terms of functions...

A lot of you seem to assume that while AMD comes out with Hammer Intel is going to go along with their current Northwood line like nothing's changed...thats far from...

Anonymous
04-24-2002, 04:40 AM
Asher,

“The Pentium 4 will be able to benefit from faster memory while AMD's Athlon range will still be bottlenecked by its slow front side bus.”

You are aware that when the Athlon XP-64 comes out, that memory bottle neck is gone due to the memory controller on die?? The platform actually won’t have a FSB…

Also, the T-Bred should have 512k cache and I’m hoping the data pathways are larger as well…

The Athlon XP-64 will usher in a new age of computers for the simple fact that mobo manufacturers won’t have the subsystem as a bottleneck anymore…

The P4 will be using a FSB while the Hammer communicates directly with memory at CORE speed…

The Athlon will be out in your 6-9 month vision, so the basic aspects of the Hammer core should be included… I’m interested in knowing where the Hammer FSB information is at because the Hammer will communicate with the subsystem via HT and with memory via its integrated memory controller, so where is the FSB at?? This is where Intel will miss the beat!!


Richard

Anonymous
04-24-2002, 05:01 AM
Unrelated?

Riiiiigggghhhht..

You are beautiful, but I think your good looks might have caused you to become a bit too arrogant.

Since your article is so speculative, you should not state predictions so matter-of-factly.

That review is relevant, too. Have you read it? I have.

Anonymous
04-24-2002, 05:37 AM
Some arguments about the article:

-the author did mention that the Barton will have 512k l2 cache and missed completely on the fact the new AMD roadmap says that the Barton will have 333Mhz FSB, and that the Hammer is speculated to have 800 MHz or so.

-now correct me if I'm wrong, but wasn't RDRAM running to take full use of the P4 FSB and so there weren't any memory bottlenecks and if the you compared an Athlon to a P4 using RDRAM at the same clock the Athlon would win hands down.

-now since the P4 has such a deep pipeline and it has to do more to process anything, I think that any increase in the FSB will be a bit useless since you are getting the data in there fast but the deep pipelines are stalling everything up.

-my comment: did Intel have anything to do with the article? Because I have doubt that your article wasn't paid. ;)

Oldbugger
04-24-2002, 06:47 AM
I am finding it more than a little perplexing that Asher/Mr Tweak could have put such a shallow article on the site...it really does detract from the site's credibility.....I am also more than a little perplexed that they can discuss "impending" Intel technology but discount and ignore the AMD equivalent.....I am not the paranoid type but ????? Intel are running scarred of Hammer .... Overclockers.com seems to think so...and they put a bit more depth and background in their articles .... http://www.overclockers.com/

Molman
04-24-2002, 09:11 AM
Pretty much spot on there from what I've seen and heard.

*nudge* . . you can tell us. ;)

Molman
04-24-2002, 09:46 AM
Some arguments about the article:

-the author did mention that the Barton will have 512k l2 cache and missed completely on the fact the new AMD roadmap says that the Barton will have 333Mhz FSB, and that the Hammer is speculated to have 800 MHz or so.


Ummm both those points are not confirmed, and at this point in time alot of rumours/speculation is pointing to the Barton being a 266mhz FSB part and dropping SOI as it originally was ment to have.


[B]
-now correct me if I'm wrong, but wasn't RDRAM running to take full use of the P4 FSB and so there weren't any memory bottlenecks and if the you compared an Athlon to a P4 using RDRAM at the same clock the Athlon would win hands down.


Actually a RDRAM platform coupled with a P4 is pretty much to best platform (for desktop) you can get to date. Obviously the constraint has always been the high cost due to RDRAM. If you look at reviews such as Toms P4 2.4Ghz vs AXP 2100+ you'll see he uses a RAMBUS platform as this shows the P4 in the best light (See: http://www6.tomshardware.com/cpu/02q2/020402/p4_2400-06.html)


[B]
-now since the P4 has such a deep pipeline and it has to do more to process anything, I think that any increase in the FSB will be a bit useless since you are getting the data in there fast but the deep pipelines are stalling everything up.


Arrrrh, if you refer to the review above I posted you'll actually see Tom tests systems running at 533mhz FSB and that it does have a noticable performance increase over the 400mhz FSB systems (~10% increase from what I can tell). One thing to point out is the DDR systems for these new chipsets are still going to constraint the performance in my view. They are only able to supply a Max Mem bandwidth of 2.1 GB/S as rather than the 4.2 GB/s the RAMBUS chipset can supply (See: http://www.aceshardware.com/read.jsp?id=45000318). Ultimately I feel Asher has the inside scoop on things and this is reason as to why he raised the Dual Channel DDR issue (which Intel should be releasing a part for by the end of the year from all reports)


[B]
-my comment: did Intel have anything to do with the article? Because I have doubt that your article wasn't paid. ;)

I doubt it very much, more likely Asher has some more data on the parts coming out soon than we do, Tom's review that I've referred to confirms much of what Asher said. While I don't have the same sediments as the Article (feeling it too short sighted for my liking) it is just one persons view based on the current situation - keep this in mind.

Anonymous
04-24-2002, 01:36 PM
Ever see TV channels beat up a story before the actual show is aired. I think this is a beat up by TT for an article on the Intel proc. The trouble is, because of the "lite" biased nature of the original article, either by design or incompetence, how could you rely on another one? Anyway, playing the political game, the original article, flawed as it is, will stay, and no matter what is said here, Mr Tweak will ignore it. The damage or plug has been made, second doesn't count.

This site has just lost me as a client, I couldn't trust another article to be unbiased or without favour.

Mr.Tweak
04-24-2002, 02:31 PM
Firstly I won't be ignoring it as you say, I've been keeping an active eye on this thread.

The article was based purely on facts, if you have a hard time dealing with that due to your possible alliances with AMD or maybe you are just an AMD fan that's really something you are going to have to deal with.

The fact remains, this article was based on facts. Not mentioning that much about the Hammer does not mean this article is biased, it just means there is little information about it to report on.

Beefy
04-24-2002, 04:16 PM
This site has just lost me as a client, I couldn't trust another article to be unbiased or without favour.

Just lost you as a client? Couldn't have been much of one to begin with.... You haven't registered, and if you'd been a regular you would have appreciated the other articles from here and not be turned off by one you disagree with...

viditor
04-24-2002, 06:05 PM
"The article was based purely on facts, if you have a hard time dealing with that due to your possible alliances with AMD or maybe you are just an AMD fan that's really something you are going to have to deal with"

Ummm...not to pick nits here Cam, but the article was based on "Roadmaps", not really facts...I think the problem most are having is that you are accepting Intel's roadmap as a given, and AMD's as more speculative (just the impression I have). I assume this is because you have the 533 FSB parts in hand, but you haven't personally seen the Hammers (I have, they ROCK!). I am also assuming that Intel is putting out that they are "releasing" this in May (thanks for the date Molman!), but (as we all know) there is a BIG difference between a "release" and finding them for sale (I'm thinking of the 1 GHz and 1.13 GHz Coppermine paper launches, not to mention RDRAM boards and the like...).

"Ummm both those points are not confirmed, and at this point in time alot of rumours/speculation is pointing to the Barton being a 266mhz FSB part and dropping SOI as it originally was ment to have"

Au contraire Monsieur Molman! :-)
http://www.amd.com/us-en/Corporate/VirtualPressRoom/0,,51_104_608,00.html

"Actually a RDRAM platform coupled with a P4 is pretty much to best platform (for desktop) you can get to date"

Ummm... a slight modification here RDRAM+a P4 2.4 GHz...below that speed and it starts at a draw and sways heavily towards AMD as speeds decline.

"For those that say the article is 'lacking' because it does not address hammer are also missing the point that the article does not address future intel chips"

I thought it did! Which chips are you referring to?

Cheers,
Charles

viditor
04-24-2002, 06:11 PM
Woops...didn't read Molman's post correctly... They have indeed dropped SOI for Barton. It will be 512k L2 .13u Athlon. The "word" is that they needed all the SOI wafers they could get for Hammer (which is why most speculate a VERY early launch for Clawhammer...possibly as early as September).
Sorry Molman...

Cheers,
Charles

Molman
04-24-2002, 06:26 PM
Woops...didn't read Molman's post correctly... They have indeed dropped SOI for Barton. It will be 512k L2 .13u Athlon. The "word" is that they needed all the SOI wafers they could get for Hammer (which is why most speculate a VERY early launch for Clawhammer...possibly as early as September).
Sorry Molman...

Cheers,
Charles

no problem :)

Edit: viditor, may I ask where you got to preview Hammer? . . curious as I live in Syd too. . .

viditor
04-24-2002, 06:45 PM
"viditor, may I ask where you got to preview Hammer?"

In LA...I'm a transplanted Yank from LA. My career is in television (I train production and post-production people on new equipment) but my income is from the US shares market (I semi-retired 3 years ago from TV). I also help a friend out in his computer shop...
One of the perks you get working on cutting edge TV gear is being allowed to see systems during the design phase (I'm under NDA as well, but I believe I can tell you the Hammer Rocks without comprimising myself...grin). I get called in to help guide the designers on what functions are most suitable...(notice I scrupulously avoided the word "Consultant"...shiver)

Cheers,
Charles

Anonymous
04-25-2002, 07:52 AM
quote:
Actually a RDRAM platform coupled with a P4 is pretty much to best platform (for desktop) you can get to date. Obviously the constraint has always been the high cost due to RDRAM. If you look at reviews such as Toms P4 2.4Ghz vs AXP 2100+ you'll see he uses a RAMBUS platform as this shows the P4 in the best light (See: http://www6.tomshardware.com/cpu/02...p4_2400-06.html)

sorry but i think that you didn't understand me. I said clock for clock as in a 1.7Ghz P4 and 1.7Ghz Athlon not a rating like 2100+ and compare it to 2.4Ghz P4. if the Athlon was running at the same clock as a P4 it would make it burn. so I think that what I said is still valid.

Anonymous
04-25-2002, 08:23 AM
Mt Tweak I am not am AMD. I'll ask a question or two.

Don't you think your readers have been misled given the title of the article yet the story body has little to do with the actual processors at all?

If so, you should etiher you should heavily modify the title or the story or pull it altogether.

There was an article recently at HardOCP about this very practice by the less "mature" sites. A lot of people read and trust what appears on TT yet such an article, to the newer users, is actually misleading. (I don't know what recourse there could be if someone actually made a commercial decision of that article).

I look forward to your "highly critical" "review" of the processor; complete with benchmark comparisons (not supplied by Intel of course), with full system specs etc, architectural benefits of the different processors, actual availability of the bits (chip, mobo and the memory) and the comparitive prices of course; wouldn't be objective without those would they?

Given the "forward looking" previous article, it would also be nice if you quiz your "source" as to whether it will be the same socket/power form factor as the impending Yamhill with its cut down 13 stage pipeline or will it be another dead end?

Molman
04-25-2002, 09:51 AM
quote:
Actually a RDRAM platform coupled with a P4 is pretty much to best platform (for desktop) you can get to date. Obviously the constraint has always been the high cost due to RDRAM. If you look at reviews such as Toms P4 2.4Ghz vs AXP 2100+ you'll see he uses a RAMBUS platform as this shows the P4 in the best light (See: http://www6.tomshardware.com/cpu/02...p4_2400-06.html)

sorry but i think that you didn't understand me. I said clock for clock as in a 1.7Ghz P4 and 1.7Ghz Athlon not a rating like 2100+ and compare it to 2.4Ghz P4. if the Athlon was running at the same clock as a P4 it would make it burn. so I think that what I said is still valid.

hmmm, its kind of a silly comparision as Athlons are behind in clock speed compared to P4's. So in the realworld (what you can get today, not tomorrow) you would be comparing one of the top speed Athlons to a low end P4. Even AMD don't feel Mhz for Mhz comparisions should be used any more, which is part of their reasoning behind the numbering scheme 2000+, 2100+ (and obviously marketing :) ), and I must say I agree with them, Mhz mean nothing between platforms.

Anonymous
04-25-2002, 10:55 AM
"Not mentioning that much about the Hammer does not mean this article is biased, it just means there is little information about it to report on."

That's funny.... AnandTech has plenty of information about Hammer, and its been there some time now... You can find all the Hammer information Here (http://www.anandtech.com/cpu/showdoc.html?i=1546&p=1) , but then again Anand is a real tech expert!!

PLUNK

Anonymous
04-25-2002, 12:34 PM
Given that the K7 core is near the end of the road for scalability, and it's incorporated into Hammer, how do you suppose that will affect Hammer's scalability?

viditor
04-25-2002, 01:51 PM
"Given that the K7 core is near the end of the road for scalability, and it's incorporated into Hammer, how do you suppose that will affect Hammer's scalability?"

Well, it is and it isn't...first it will be more (and longer) pipelines to allow for much higher clock speeds. This will be offset by having the Northbridge built into the chip die itself (vastly reducing the latency). Also, because it uses HT (with 3 HT connections built into the die), the bandwidth to and from the processor will be MUCH higher with (again) much lower latency. Third, it will be .13u SOI moving to .09u SOI, allowing for much higher clockspeeds. Fourth, it's not really one K7 core but 2...(at least for sledgehammer/Opteron) which the OS can actually see as 2 seperate CPUs (both on the same die), at least it will be by 2H '03.

Cheers,
Charles

viditor
04-25-2002, 02:42 PM
Hmmm...it appears as if my hope for a Sept launch may be too optimistic (by a month...). I have a friend at AMD who (in response to my constant whinging) told me today to "read the Inquirer" if I needed good data...from the Inquirer:

"SOURCES CLOSE TO AMD's plans continue to tell us that the 28th of October date we're currently projecting appears so far to be spot on.
And we also have projected prices of both processors and motherboards, with CPUs costing $400 and mobos hovering around the high $200 mark, as an initial thrust into the marketplace"

http://www.theinquirer.net/25040202.htm

I hope that it's appropriate that I post this stuff here (in this thread)...if it's not, someone please let me know...

Cheers,
Charles

Anonymous
04-26-2002, 07:23 AM
Hi Asher Moses. I was wondering what you mean by real world benefit. If you were to use 333Mhz memory on a 133bus athlon you could still recieve a minor performance gain over 266Mhz memory. Of course you could get a larger gain running both the cpu and memory at 166Mhz. This seems to be available to everyone. Products that allow this are easy to find. If you are still wondering what the point is of a KT400 chipset, I'll let you know... higher performance. Apart from handling 200Mhz fsb (which apparently some KT333 mb's are doing today) it should come with 8xAgp and an improved NB/SB connecter (2x faster than the previous). Of course, to take advantage of these one would have to "overclock" their babies, sometimes things like that happen in the "real world"!

Do you really believe that AMD will stick w 133fsb for its athlon line till 2003? What reason could there be for such a move? The things to consider (from AMD's perspective) would be quality of product, availabilty and pricing. Although 333Mhz chipsets and memory are new in the market their similarity to 266Mhz products will make their adoption much quicker than the Sdram to DDRam changeover for example. The quality of product and pricing are also helped by the similarity to 266 product. To expect AMD's acceptance of this standard to be delayed till 2003 for the athlon in light of intc's 533bus in addition to all the other improvements to the pIV line that will be introed in this year does not make sense. To those who think that "validating" the athlon for 166Mhz isn't worth it (cough, anand) maybe they should consider where AMD makes most of its money.

As for the Hammer line, it seems as if it could be possible to intro products before 2003. Rumors are all over. How long will it be before it contributes a lot to the bottom line, better make sure the current product is competitive till at least then. AMD says that athlon will be around for all of 2003. I don't think they would last that long with you in charge (joke!) !

Anonymous
04-26-2002, 07:30 AM
quote:



Originally posted by Unregistered
What would AMD have to do to make the Athlon run at a higher FSB frequency? What is involved engineering- wise? Is it possible to do something like the quad pumped bus of the P4?





An entire new architecture I'd say.

__________________
Cameron "Mr.Tweak" Wilmot
Founder and Owner of TweakTown


If one were to have a 166fsb athlon homejob would they be an engineer?

Anonymous
04-27-2002, 07:31 AM
Mr. LSD, do you think that there will be any improvements in the thoroughbred vs palomino? Not considering L2 cache. I think that would be a mistake. I guess you must have already seen pics of the cpu.


Butthead

Anonymous
04-29-2002, 05:24 PM
For those that say the article is 'lacking' because it does not address hammer are also missing the point that the article does not address future intel chips.

The article is taking an analytical look at the here/now and the next 6-9 months.

Though we cannot say what hammer will bring, we equally cannot claim on what Intel's Prescott (.09 micron P4) will bring. This is due out sometime early next year, and rumors are abound on this chip...

Rumors now...
- 1 meg L2
- 800MHz FSB
- And more die changes in terms of functions...

A lot of you seem to assume that while AMD comes out with Hammer Intel is going to go along with their current Northwood line like nothing's changed...thats far from...

I think this is wrong for many reasons:
1)When do you think Hammer is coming out? In just over 6 months it will be November. Clawhammer will almost certainly be out, Barton will have been out for a while, and Prescott will still be way off. Prescott is over a year away, Hammer is not. By the time Prescott comes out an improved Clawhammer will probably be on the way. There will at least have been many more speed grades released (3 speed grades above the initial one will be introduced within a quarter of its release).
2)Imagine that Prescott comes out with 1 MB L2, 800 MHz fsb, and all of the other rumoured improvements it will have. Compare this to a Sledgehammer with 1 MB L2 cache and dual channel DDR (at least dual 333 MHz). You could speculate that AMD's high end part would be at the very most at an equivalent price point to Intel's top end CPUs. AMD states that 20% of the improvement in speed of a Clawhammer over an equivalent clockspeed Athlon is because of the on-die memory controller. I greatly doubt then that Prescott will be able to get any more real-world bandwidth than a dual-channel Sledgehammer if the latency advantage of the on-die controller is so large. Hammer is also designed to scale to much higher clockspeeds than Athlon and doesn't need to scale as high to get the same performance increase. It is hard to believe that Sledgehammer wouldn't be competitive with the next P4, but unless Clawhammer is a bit of a failure so far as clockspeed scaling goes then it should be competitive too.

My take on the article is that it is basically saying AMD will be left behind so far as performance is concerned because not only will Intel be changing to a 533 MHz FSB, they will be introducing their dual-channel DDR chipset. AMD on the other hand will introduce a 0.13 micron Athlon and by the end of the period getting talked about should have an Athlon with 640 KB cache. This gives a warped opinion though, because this Athlon will only be AMD's replacement for the Duron, and it will be getting introduced well within 6 months. In reality, AMD will have a processor that out that scales much better than Athlon, is 25% faster at the same clockspeed, has the potential for another 15% improvement (figure from Ace's Hardware) when compiled with a complier that takes advantage of the extra registers etc afforded by x86-64, supports SSE2 (thus removing what is a major advantage for P4 in programs that support it), and supports 64 bit addressing for > 4GB memory. It is sort of like speculating that ATI will be leading the Geforce 4 easily by the end of the year, and ignoring to mention that nVidia will be introducing new technology too.

viditor
05-03-2002, 11:18 PM
G'day Unregistered (my, my you do post alot! <grin>)

I agree with your post ALMOST completely...but I have just one nit to pick...

"supports SSE2 (thus removing what is a major advantage for P4 in programs that support it)"

SSE2 will help the P4 much more than it will the Hammer or Athlon series. It was designed to make up for P4's rather weak FPU, so we should see a much larger gain in the P4 improvements than in the AMD improvements. That said, please note that WITHOUT SSE2, the P4 would struggle to even keep up with Athlon...even with it, I suspect Clawhammer will be leaps and bounds ahead of the (expected) 3.0 GHz Northwood due out early next year, even at 533 MHz...

JMHO

Cheers,
Charles

flasuvious
05-08-2002, 07:33 AM
Sometime around Sept according to the Inq...

http://www.theinquirer.net/06050211.htm

Well at least we KNOW that AMD won't use it till next year!
:beer:

I think Acid needs a rest. : peace:

flasuvious
05-26-2002, 06:27 PM
Hey viditor I think you misunderstood unregistered's point ( I think there is more than one)

It should have been written like ...

"supports SSE2 thus removing a major (maybe some apps) theoretical disadvantage for the Athlon."

Since p4's always have had SSE2 they will not have any further gains from the Intro of AMD's version of affairs. The gains will only be AMD's.


higher fsb to be intro'd in MP's

from the inq: http://www.theinquirer.net/25050201.htm

I think this has something to do with their desire to attain profitability. Word is, people are willing to pay more money for more performance.

To anyone who thinks that Hammer will be available in large amounts, where is the SI28 gonna come from. I've heard of Isonics finding another manufacturer but no details. I think it will only be on certain layer/s so that would reduce the demand if true.

Maybe time to update the article.

flasuvious
05-26-2002, 07:08 PM
hey acid you should also add that the Duron will not likely ever make it to .13. Production will end soon as Austin is to convert to all flash manufacturing.

I think that Barton will be out around August since AMD has said that they will make it without SOI and the soft market has allowed them to spread their mix more effectively. Those would bring them in $220+ for a whole quarter.