backtop


Print 122 comment(s) - last by murphyslabrat.. on Dec 22 at 1:05 PM

AMD plans to keep "Brisbane" around, releases new chips based on it

Things at AMD may have gone from bad to worse with the lackluster Phenom launch in late November.  Not only did Phenom fail to appeal to professional reviewers, but the company ended up removing one third of its CPU lineup just after the big day.

Last week AMD CEO Hector Ruiz vowed that the company would stop hemorrhaging cash and return to profitability soon.  "That is our number one goal right now," Ruiz said in a conference in Bangalore

Making a profit at AMD apparently means refocusing on its older K8 architecture.  The company will introduce eleven 65nm K8 processors over the next two quarters.  By comparison: AMD launched two quad-core K10 Phenom processors in November with three more scheduled over the next two quarters.  Two tri-core Phenom processors will follow in March 2008.

Essentially, AMD will move any remaining Athlon 64 processors from the 90nm node to the 65nm node, with a few new frequency and TDP variations.

The AMD Athlon 64 X2 5600+ will be the first to jump on the new 65nm K8 bandwagon with a 65W TDP. The previous Windsor-based chip of the same featured an 89-Watt TDP. AMD will also add 100 MHz to the core frequency of the Athlon 64 X2 5600+, now rated at 2.9 GHz. Total L2 cache will be halved in the move to the Brisbane core, and the updated Athlon 64 X2 5600+ chips will feature only 1MB of L2 cache. Availability of these processors is scheduled for Q1 2008.

AMD's higher-end Athlon 64 X2 6400+ and Athlon 64 X2 6000+ will both be discontinued.

AMD will also update its "Energy Efficient" series and will release three new chips, the AMD Athlon 4850e, Athlon 4450e, and Athlon 4050e in Q2 2008. All of the new offerings will be based on AMD's Brisbane core and will feature a 45-Watt thermal envelope. AMD's current energy efficient "BE-2xxx" series will be phased out at that time. Respectively, the new chips will run at 2.5GHz, 2.3GHz and 2.1GHz.

All new Brisbane chips will be based on the Socket AM2 interface.  These processors are compatible with AMD's AM2+ socket designated for Phenom processors.


Comments     Threshold


This article is over a month old, voting and posting comments is disabled

AMD's new Sempron
By nerdye on 12/5/2007 10:52:17 AM , Rating: 2
Does anyone know the future plans AMD has for its Sempron line of CPU's, perhaps these new k8s will serve that role? I think we need to give AMD a little time, perhaps somewhere in 2008 we can determine if k10 will ever reach prominence, clouds of doubt remain unfortunately.




By KristopherKubicki (blog) on 12/5/2007 10:55:27 AM , Rating: 2
Sempron in 2008 is teh LE-1150 to LE-1300 series (that's four CPUs in total). There was supposed to be a speed bump in there but that got canned. Basically we'll see the LE-1100 drop out and the LE-1300 show up in Q1.

That's all for Sempron for the rest of the year.


RE: AMD's new Sempron
By cochy on 12/5/2007 10:58:21 AM , Rating: 1
A little time? I don't think they have much time left. How can Hector Ruiz promise a return to profitability when AMD is going to lose all their markets. Even Opteron, which was once their bread and butter, is looking like a disaster now. If they lose out big in that segment it's curtains for this company. Chapter 11. Good night Irene.


RE: AMD's new Sempron
By StevoLincolnite on 12/5/2007 11:06:43 AM , Rating: 2
AMD won't go under in a hurry, there are people in very high places that will assure that won't happen.

At least they have an Action plan in place.


RE: AMD's new Sempron
By TomZ on 12/5/2007 12:42:21 PM , Rating: 1
quote:
AMD won't go under in a hurry, there are people in very high places that will assure that won't happen.

Who do you mean by that? President Bush? :o)

Seriously though, nobody in "very high places" can make the market accept a sub-par products. The only way AMD can continue to have marketshare is by continuing to lower prices further. This of course harms their revenue and profitability, which further compounds their problems.

The best way out for AMD was to have Phenom be a great success at the right time so that it could effectively compete with Intel with high margins. It seems like that opportunity is missed, however.


RE: AMD's new Sempron
By StevoLincolnite on 12/6/2007 10:20:40 AM , Rating: 2
I'm not American, Bush is the last person to come to mind, and I thought AMD was Canadian based?

And sub-par products? If you go back to the Pentium 2 and earlier days, I don't exactly recall AMD being a market leader at any single time, they survived then and the market had more competitors, I'm not sure how the Stock markets and what not work, but I can imagine they will work something out when the coffers start to run low.

I hope they don't go the way Cyrix did, Personally I think the Athlon X2's are great value for money.
I was disappointed how the latest batch of Radeon's didn't really make Performance headways.
Although the Radeon 2900GT is great value, and I highly recommend it.
Which brings another thing, Back during the Days of the Pre-Radeon ATI survived almost completely on the OEM market, While nVidia, 3dfx, Matrox, S3, Rendition etc. battled it out, so I doubt that part of the company will go either.


RE: AMD's new Sempron
By Silverel on 12/7/2007 2:34:51 PM , Rating: 2
ATI is (was?) Canadian.

Anyway, if they get to the point they have to close the doors, its very likely someone will buy the remains and continue on competing with Intel.

I'm hoping for IBM personally.


RE: AMD's new Sempron
By afkrotch on 12/8/2007 12:08:51 PM , Rating: 2
AMD is American. ATI was Canadian or is Canadian. Not sure what you'd call it now.


RE: AMD's new Sempron
By gmofftarki on 12/5/2007 11:47:29 AM , Rating: 5
Keep in mind that despite AMD/ATi's current lack of superiority in any one section of the marketplace, they've put themselves into an interesting position strategically.

nVidia and Intel aren't getting along that well with regard to intellectual property and proprietary technologies. nVidia and AMD/ATi are direct competitors for a portion of the marketplace, as are Intel and AMD/ATi.

New Intel processors, to benefit from multiple GPUs on the newest chipsets, currently have to use Crossfire, ie. AMD/ATi graphics.

nVidia is being kept out of the loop on the new Intel chipset protocols, so, to continue moving forward, they're going to have to continue designing AMD chipsets.

Granted that neither nVidia or Intel will crash and burn, but the current situation is rather tenuously balanced, and if ATi positions themselves properly with a new product line ready to launch when something hits the fans, they'll be in a better position than now.

Personally, if I were in AMD/ATi's shoes, I'd focus on the GPU for now. 8800GT and G92 8800GTS are going to take all of the attention for about 4-6 weeks, and then there's the post-christmas buying depression. In mid-January to early February, release the 3990 (or whatever designation you prefer) and have it cream the equivalent nVidia, with the marketing being "No proprietary component requirements, but for best performance, use with the full Spider platform".

Has AMD messed up a lot in the very recent past? Sure. But I'm not convinced that they're past the point of no return, at least not yet.


RE: AMD's new Sempron
By StevoLincolnite on 12/6/2007 10:32:04 AM , Rating: 3
quote:
Has AMD messed up a lot in the very recent past? Sure. But I'm not convinced that they're past the point of no return, at least not yet.


Which company hasn't? And you need to define "Flops" some regard the AMD K6 series a flop, when they were serious value for money, Others thing the Athlon 64 was a flop when in all realization pounded Intel for several years, and now they are great value for money, ATI' took awhile to get its drivers upto Gamers standards, and that paid off during the Radeon 9xxx, x8xx, x1xxx etc.
The Radeon x300, x600, x700, x800 series didn't have SM3, Unlike the Geforce 6 series that did, Although the really only notable feature of SM3 is HDR, and that can be performed on SM2b hardware with a few extra passes.

Intel apparently flopped with the Pentium 4/D - But they had an aggressive marketing strategy and still out gunned AMD in-terms of sales.

What I would like to see is the Athlon 64 line available in Single and Dual Core, Die Shrank and Available for Socket 754, 939 and AM2, at much lower prices, I know allot of people with Socket 754 and 939 Sempron's and would literally kill to be able to spend a small amount on upgrading they're processor without upgrading memory and motherboard, and in some cases Graphics cards.

Multi-GPU System are still only an enthusiast thing, its not something that you come across everyday unfortunately, And I personally cannot find a crossfire AMD board at any of my local computer stores, yet have plenty of choices when it comes to nVidia's SLI. - Although I live in a small town in South Australia which could be my issue.

One thing I would like to see in the chipset market is, Via's return to Performance/Enthusiast chipsets, that might heat the market up and lower prices.


RE: AMD's new Sempron
By herrdoktor330 on 12/6/2007 11:14:32 PM , Rating: 2
2 things:

Don't get me wrong, guys. I love AMD and have been a loyal customers of theirs since the K6-2 days. However this Barcelona bug is a serious misstep. Since Intel has started this "tick-tock" practice, AMD is going to have to make some big improvements in the theoretical K11 to even come close to the offerings Intel will have.

Think about this: Nehalem is going to be the Conroe redesign with 4 cores on die that's coming out the end of next year. I'm sure they'll use the same trick they're using now to put 4 + 4 cores communicating through the FSB on one cpu. Plus I hear that they're going to be bringing back hyperthreading technology back on the high end Nehalem chips. So that roughly means 16 listed cores for the Intel powered system to use.

Then what happens if Skulltrail starts selling and they make a version of that chipset for Nehalem. That's a "possible" 32 listed cores on your machine. (This will be 2009's newest Apple Macintosh High End Workstation... you heard it here first. Mac fans will be proud.)

... but AMD can't even get 4 cores working properly. And who's going to bother with 3 cores? And they just killed their enthusiast package.

I know that there isn't a large portion of software that can successfully use more than 4 cores for now. But as more processing cores become available, software developers will find a way to scale to it. Once that happens, Intel's going to be getting all the kudos and AMD is going to have to build up again to try to be competative. Or they finish the bulldozer all-in-one platform they've been talking about and show how great and simple those can be. But no matter how you slice it, AMD is going to have an uphill battle to fight with Intel to win back the performance crown.

2nd thing about Via, I don't believe their angle is EVER going to be performance. They're way outclassed for that. From what I understand the C7 line has all the power of a PIII of equal or lesser clock speed. They make for great e-appliances, web surfers, and eco-friendly open home file servers (assuming you're not worried about raw transfer speed). But I'm going to go out on a limb to say they're never going to be a #1 performer ever as long as Intel and AMD are in the market. I like their philosophy though and would be inclined to buy their product if they could keep the power consumption low while offering more expandability to their boards (more PCIe, 4 or more SATA 3GB connections, and so on). If they could make the next "conroe" sized leap in performance while keeping consumption down (maybe the C8 line will do this), these would be the bomb for laptops.

But that's my opinion.


RE: AMD's new Sempron
By FITCamaro on 12/5/2007 12:36:54 PM , Rating: 2
AMD is still doing quite well in the 4 and 8p server market.


RE: AMD's new Sempron
By cochy on 12/5/2007 12:55:52 PM , Rating: 2
Sure. But for how much longer if CPU innovation and advances are seemingly coming to a crawl? Who's going to need a 4 or 8p server if and when Intel releases Octo-core and greater chips? Which we know they will, they have said that we should see a 32 core chip sooner rather than later. AMD is struggling with quad-core even. Do they have the resources for R&D now that they are a cash black-hole? If so for how much longer? If Intel and AMD continue down their current paths, not much longer.

With the current mounting loses can AMD compete with Intel and Nvidia? They need captial and they aren't going to get it from sales if they continue to have to lower prices. They can't function the way they did back in K6 days because they were a much smaller company then. Now they are AMD/ATI. Very bad timing to start losing quarter after quarter. They are in way bigger trouble then people may realize. They will need outside financing soon.


RE: AMD's new Sempron
By Martimus on 12/5/2007 1:14:52 PM , Rating: 3
You are comparing apples to oranges. AMD is struggling with integrating a memory controller into a die with more than two cores. It kills the yeild in the manufacturing process. Intel doesn't have to worry about that, because they don't have IMC's, but at the same time, that cripples them in the server market. The FSB becomes a huge bottle neck the more processors there are to process the data, which is why the AMD solution is often better in those circumstances. Of course, that is such a small portion of the market that it isn't likely to make much of a difference in either sides bottom lines.


RE: AMD's new Sempron
By cochy on 12/5/2007 1:26:04 PM , Rating: 2
Right. Correct me if I'm wrong. Intel's next gen coming next year will have IMC with QuickPath? So as I said: How much longer?


RE: AMD's new Sempron
By KristopherKubicki (blog) on 12/5/2007 1:38:27 PM , Rating: 2
Late 2008 for Nehalem.


RE: AMD's new Sempron
By cochy on 12/5/2007 1:42:33 PM , Rating: 1
Exactly. So Intel is innovating their designs while AMD is standing still. That's moral of the story here.

Soon Opteron's biggest advantage is no more.


RE: AMD's new Sempron
By Martimus on 12/5/2007 1:58:28 PM , Rating: 2
Who says that Intel won't have yeild problems with their integrated memory controllers? They have working parts, but so did AMD over a year ago. It doesn't mean that the 4 cores on one die and IMC to control how each accesses memory won't cause a production issue that will push back that timeframe. There are manufacturing issues that you aren't taking into account. I would be very surprised if Intel is on time with Nehalem, and if they are I would expect some major error like in the design that they will need to work out. You only have to look at what has happened to AMD with Barcelona to see that Intel should have similar problems with Nehalem. The two are very similar in the architecture portions that gave AMD problems, so you should expect Intel to have similar problems. They may be solved sooner, if Intel learns form AMD's problems, but I doubt that their agressive schedule will allow for anything but a paper launch in late 2008, if there is indeed a launch at all.


RE: AMD's new Sempron
By cochy on 12/5/2007 2:33:50 PM , Rating: 3
Very true. But on that note with recent history in mind, my money is on Intel's ability to innovate chip design and solve said problems easier than AMD. Time will tell.


RE: AMD's new Sempron
By Master Kenobi (blog) on 12/5/2007 5:57:30 PM , Rating: 2
Intel will be using the 45nm Process and High-K materials, AMD is using the SOI process and on 65nm.

In Intel's defense though, their track record for processes and yields has even beat the pants off of IBM. Make no mistake, when it comes to process nodes and ability to produce excellent yields, Intel is bar none, the best.


RE: AMD's new Sempron
By jarthel on 12/5/2007 6:32:02 PM , Rating: 2
Intel may have problems with Nehalem and yields. BUT you have to remember that unlike AMD, Intel has loads of cash for R&D.


RE: AMD's new Sempron
By Calin on 12/6/2007 8:09:13 AM , Rating: 2
Also, Intel is at least a year ahead of AMD on microprocessor front - maybe even more. So, even if Intel lets a year pass by because of problems/issues/whatever, they will still be in the better position.
I really hope from a huge success from AMD's Fusion. I am running at home an integrated graphics platform (AMD/ATI), and a Fusion-like architecture would bring better everything for integrated graphics.


RE: AMD's new Sempron
By maven81 on 12/10/2007 1:21:51 PM , Rating: 2
You could say that AMD is a year behind in performance, and at least 6 months in process technology, but I don't think the same could be said about architecture.
Their 4 core chips are definitely slower then intel's but even if they do nothing but stick two of those on one die they could build an "8 core" chip before intel does. It just wouldn't have hyperthreading. Obviously this won't really be viable until 45nm, but if they can do that, it's an ace up their sleeve.
Their fusion program is also at least a year ahead of Intel and was the whole reason for buying ATI. I'm betting they knew Intel was heading in this direction, and wanted to beat them to the punch. If they can push out actual products based on that design on time, they still have the advantage. However, the "on time" part is what's killing AMD.


RE: AMD's new Sempron
By 91TTZ on 12/6/2007 7:54:06 AM , Rating: 2
quote:
You are comparing apples to oranges. AMD is struggling with integrating a memory controller into a die with more than two cores


I don't think the problem is with integrating a memory controller into a die with more than two cores, I think the problem is just the more general problem of having multiple cores on one die. That's why Intel does it on multiple dies- to increase yield. Intel is known for its yields and increasing yield (and profitability) seems to be a very high priority for them when designing a CPU.

If you notice, AMD announced that it will be selling tri-core CPUs. They're not doing this just because they think a 3 core CPU is a neat idea, they're doing it because they have tons of 4 core dies with a bad core on them.

It was the same reason that Intel made the 486SX years ago- it wasn't that they thought that consumers wanted a 486 without a math coprocessor, it was because they had lots of 486DX dies with a bad coprocessor on them. Instead of scrapping those chips, they disabled part of the die and were still able to sell them, just for a slightly lower price.


RE: AMD's new Sempron
By Martimus on 12/6/2007 12:56:06 PM , Rating: 2
Exactly, but the integrated memory controller keeps AMD from being able to slap two dies on a single chip. Nehalem is a huge change for Intel, as they will be going through the same things AMD is with this problem. I expect them to fix them faster than AMD has (or hasn't I guess), but don't be surprized if the chip gets delayed. The closest chip to Nehalem's architecture is Barcelona/Phenom, and that has had nothing but issues.


RE: AMD's new Sempron
By DM0407 on 12/5/2007 10:58:49 AM , Rating: 2
Was the K9 designation never used or was it a complete failure so they started on k10?


By KristopherKubicki (blog) on 12/5/2007 11:00:31 AM , Rating: 3
There were multiple K8 successor projects. Even at AMD "K10" is not the official name, but since nobody at the company feels like figuring out some kind of specific designation it will have to do.


RE: AMD's new Sempron
By 16nm on 12/5/2007 11:03:17 AM , Rating: 5
quote:
Was the K9 designation never used


Sure, by law enforcement. But they were dogs, which, ironically, K10 also is.


RE: AMD's new Sempron
By StevoLincolnite on 12/5/2007 11:09:07 AM , Rating: 2
We aren't sure about what the future is like for Phenom, give it a few more revisions first, you might be surprised, allot of people thought the same thing about the Pentium 4 Willamatte when it was first released, and once it hit the Northwood, they were ahead of the Athlon XP until the Athlon 64 arrived - Performance wise.


RE: AMD's new Sempron
By DM0407 on 12/5/2007 1:03:10 PM , Rating: 2
quote:
quote:
Was the K9 designation never used

Sure, by law enforcement. But they were dogs, which, ironically, K10 also is.


That made me laugh : )


RE: AMD's new Sempron
By mmntech on 12/5/2007 12:01:54 PM , Rating: 3
Likely the K8 will become the new Sempron. AMD did this with the last K7s when the original Athlon 64s first came out.

AMD has been in business for decades. They won't go under so easily.


Back the sqaure one
By cochy on 12/5/2007 10:49:59 AM , Rating: 5
What does this move indicate? Certainly failures in new chip design, innovation, what else?

Releasing new offerings based on years old architecture? I jumped on the AMD bandwagon the day K7 came out (cause that was serious innovation). Now it looks like the old K6 days for AMD. Bargain basement prices and offerings.




RE: Back the sqaure one
By StevoLincolnite on 12/5/2007 11:02:00 AM , Rating: 2
Yes the K7 was innovative, but it was Beaten by the Pentium 3 Coppermine EB chips, because they featured on Die full speed cache, until AMD moved them on-die also, then the Late Model Pentium 4's were able to beat the K7, So it was more of "Pass the Performance crown" between the Pentium 3 and Pentium 4 and K7 chips.
Really the only time Intel has been completely demolished was when the Athlon 64 and the Pentium 4/D were the only chips in the Arena, and AMD dominated, It was good as well, as Intel raged Price wars with AMD, and that... Made my computing upgrade life so much the sweeter ;)

Now... I wish for more competition, Phenom is good, but is it really what we had hoped for?
I want to go back to the days where we had the IBM 686, Cyrix 686, Pentium 2, Celeron, AMD K6-2/K6-3 those were the days of competition.


RE: Back the sqaure one
By cochy on 12/5/2007 4:24:06 PM , Rating: 2
Athlon (K7) was so important because it signaled from AMD that "Hey guys we can innovate and we aren't satisfied with being 2nd dog in this 2 dog race anymore". K7 was ahead of it's time, architecturally speaking. P3 might have outperformed it (not sure P3 was clock for clock faster though), but those days AMD had huge price/performance advantage over Intel (not so today. Yes they might but it's not as big as it once was).

Now with this announcement from AMD, by continuing with 4 year old tech, it's just the opposite.

"Hey guys, we're satisfied with being 2nd dog."

C'mon guys let's see more than marketing and branding tricks. Fusion can't come fast enough.


RE: Back the sqaure one
By cscpianoman on 12/5/2007 9:26:25 PM , Rating: 2
Actually, second place isn't necessarily bad as long as you play second place well. Take a look at Home Depot and Lowes. Home Depot exceeds Lowes in market share quite a bit, but have you noticed the performance numbers between the two? Lowes makes a killer profit by differentiating and targeting a different market. AMD can also do the same by differentiating enough that people see value in the differences and I suspect that is exactly what they are trying to do at the moment.


RE: Back the sqaure one
By Chaser on 12/5/2007 11:09:12 AM , Rating: 2
Reverting back to a bargain CPU alternative to INTEL compared to a price/performance leader may not be a bad thing. But I would say that it's a lot easier and less costly to build upward and grow rather that downsize back. If that's the case. Is the next step huge layoffs and rollbacks?


RE: Back the sqaure one
By cochy on 12/5/2007 1:02:27 PM , Rating: 1
quote:
Is the next step huge layoffs and rollbacks?


You bet. Because how can they continue to function as the "brand X" while being as big a company as they are now? They grew a lot and invested a lot in new assets back when they were very profitable (K8). Oh ya they also bought ATI. So ya, down-size a lot because your profits are going to sink (that is when they start making a profit again). AMD made horrid timing errors. Upper management dropped the ball. That's why upper management is on the way out.


By someguy743 on 12/5/2007 12:48:07 PM , Rating: 6
I hope AMD and IBM and their other partners have been working as hard on their 45 nm (and beyond) technology as Intel has. Intel has had 100s of PhD engineers and scientists working on their new 45 nm technology. It took a lot of brainpower from a bunch of people over the past few years to get this new Penryn technology to market. I think the whole industry has known about using hafnium for the dialectric for a good while. It's the "metal gates" that are the true "secret sauce" in the new Penryn chips. Intel is keeping that "metal gate" technology a big secret for sure. Gotta have the new metal gates in order for them to work just right with the new hafnium dialectric.

This article by one of the key Intel engineers describes how Intel did it.

http://www.spectrum.ieee.org/oct07/5553

The guy who wrote it is named Mark Bohr. I wonder if he's related to the famous quantum physicist genius Neils Bohr. If so, he probably has the good genes for doing the kind of stuff that AMD and Intel do. The stuff these engineers do these days is true Einstein level stuff. Way over my head, I know that.

Check out this article also.

http://www.eetimes.com/news/semi/showArticle.jhtml...

"But was Intel first to 45 nm? Perhaps Matsusheta/Panasonic's newest process deserved an earlier mention, but I think it has, or will, become accustomed to occupying Intel's 45-nm shadow. In terms of size and transistor density, Panasonic's UniPhier IC achieved a true 45-nm technology and put it into the market earlier than Intel. Panasonic Blu-Ray players with the technology appeared on the market in early November. By implementing immersion lithography, Matsusheta/Panasonic has achieved the smallest minimum metal patterning that we have seen to date, at 67-nm M4 half-pitch. However, the gate stack technology is traditional and well behind Intel's. The 36-nm poly gates are not designed for best performance but rather for squeezing two parallel H.264 decoders onto a single piece of silicon.

Perhaps surprisingly, Panasonic achieves tighter metal pitches than Intel. While Intel might be proud of extending dry litho to 45 nm, it cannot match the dimensions from Panasonic's fab, which is running immersion tools now. For example, the UniPhier device displays a minimum pitch of 138 nm up to metal four. Compare that with Penryn's metal-two pitch of 158 nm."

Maybe AMD should have been partnering with Panasonic instead of IBM. Panasonic actually beat Intel to 45nm, but their gate stacking technology isn't as good as Intel's. Maybe AMD has mastered their immersion tools by now and they're getting close to matching Intel on their gate stacking technology. Let's hope so. I want to continue buying high quality/high performing AMD products in the years ahead ... hopefully a LONG TIME. Customers all over the world want the competition. Better products sooner at better prices.

AMD and IBM better find an answer for Intel's tri-gate technology. Intel is really piling on the pressure for AMD these days. It's starting to look like Intel is the schoolyard bully for the whole semiconductor industry ... stealing the smaller kids' lunch money. AMD and IBM need to hire more geniuses to invent their way out of this nightmare of competing with Intel.

Intel is just getting rolling with Penryn's new dialectric and metal gates. In 2010, they'll have this tri-gate technology out that is supposed to be better than IBM's FinFET technology ... which I assume AMD will probably use. AMD better invent something better than tri-gate or the nightmare of competing against Intel might continue for another decade.

http://www.pcworld.com/article/id,126044-page,1/ar...

http://www.intel.com/technology/silicon/tri-gate-d...




By thartist on 12/5/2007 3:01:01 PM , Rating: 2
Why don't you send it to them? They have been showing that they are not quite capable of a clear thinking by themselves these days, so they might surprise you and the rest of the world (i pray!) and actually do something that doesn't turn out a flop or a disaster.

Maybe too wet but, what do you lose?


By StevoLincolnite on 12/6/2007 10:39:09 AM , Rating: 2
Who brought the Encyclopedia in here?

Seriously a great and informative post, worth +6 and beyond.


By Clauzii on 12/6/2007 3:11:18 PM , Rating: 2
XXXelent post! 6+!

Here is Mark Bohr on the 45nm:

http://www.youtube.com/watch?v=IA4ilK2xKWs


It's only fair....
By RussianSensation on 12/5/2007 11:08:49 AM , Rating: 2
When the design of the Opteron/A64 architecture was completed in early 2003, AMD has had more than 4 years now to release something much faster. Phenom is about 15-20% faster than A64 per clock now?

When the management and engineering departments sat down 4 years ago, what did they aim to achieve in terms of performance? I don't think Ruiz is the only one to blame here. Personally, the head engineers in charge of the design are at least as responsible for this.

Although you won't know the exact performance of the part you design but you can logically extrapolate. It doesn't take a genius to look at the bottlenecks of K8, look at the evolution of software coding and ask yourself where you can increase performance. IF their engineers couldn't achieve performance above 20% from the start AMD should have hired smarter people to do the job.

In the end the value of your human capital is invaluable. If Intel designed Core 2 Duo so can AMD if they hired the right people. Intel is just a name, not some magical mysterious company that can do "wonders." If AMD didn't feel at the time they could afford the brightest people then they shouldn't have spent all that $ buying ATI...




RE: It's only fair....
By bull2760 on 12/5/2007 11:15:18 AM , Rating: 2
When a company posts as many losses as AMD has over the past couple of years you need to step back and look at the leaders. GM did it Crysler did it, it's time for Ruiz to step down. Yes others will have to go But you need to start at the top and right now Ruiz is the man.


RE: It's only fair....
By retrospooty on 12/5/2007 11:43:46 AM , Rating: 2
I agree with you there. Granted, Ruiz in not in engineering and doesn't directly effect die's and yields, the fact of the matter is that since Ruiz took over AMD hasn't executed anything well at all. That may or may not be Ruiz's fault, it may just have been bad luck, but the fact remains, he does not seem to be able to motivate people. AMD needs to be motivated.

Intel had the same issues a few years back. They were missing deadlines, changing specs at the last minute to accomodate for flaws, etc etc... Then they reorganized and recomitted to becoming #1 again, and started to execute perfectly again. AMD needs to do the same thing, and they can... given the right leadership.


RE: It's only fair....
By cochy on 12/5/2007 1:05:16 PM , Rating: 2
quote:
Is the next step huge layoffs and rollbacks?


Well no. Intel may be just a name, but they also have an order of magnitude more capital to spend on that all-important R&D you're mentioning.


RE: It's only fair....
By cochy on 12/5/2007 1:06:00 PM , Rating: 2
Quoted the wrong post there. Quote should read:

quote:
Intel is just a name, not some magical mysterious company that can do "wonders."


Since they're still working on the K8...
By joemoedee on 12/5/2007 12:05:54 PM , Rating: 2
Having a better lineup of 939 chips on the market certainly wouldn't hurt them. Or maybe just one or two "high-end" chips that would be affordable upgrades for those with still rather recent PCs.

I'm unsure what the fab difficulties would be, but I know there's a ton of 939 system owners that would jump at the chance to upgrade the cpu in their machine.

As far as the business side goes, it does seem that they're all over the place with what they're doing. I've enjoyed their products, and hope that they can figure it out before its too late.




By RamarC on 12/5/2007 12:28:59 PM , Rating: 2
i completely agree. a lineup of 939 based x2s would sell quite well. a 939 based x2 6000+ could certainly keep some amd old schoolers who are in need of an upgrade from abandoning ship.


RE: Since they're still working on the K8...
By Kazairl2 on 12/5/2007 8:38:34 PM , Rating: 2
If you want to keep with Socket 939, NewEgg still has the Opteron 185 (2.6 GHz, dual-core with 1 MB L2/core) around. Mine just arrived today. The chip is more expensive than the equivalent AM2 chip, but it lets you keep your mainboard and memory. If you have a lower-end 939 CPU, doubling the cores AND increasing the clock frequency isn't a bad upgrade.



By joemoedee on 12/6/2007 8:06:00 AM , Rating: 2
quote:
If you want to keep with Socket 939, NewEgg still has the Opteron 185 (2.6 GHz, dual-core with 1 MB L2/core) around.


Yeah, I saw that. 169.99 for the Opteron 180, 235.00 for the Opteron 185. However for 99.99, you can get into a 4800+ X2 Brisbane core on the AM2 platform. They need similar 939 products available at similar price points, and I believe that would increase their sales quite a good bit. But again, I'm unsure of the fabrication issues that may entail.

Up until mid 2006, I know I saw still about a 50/50 split on the AM2 vs 939 sales where I worked. Most system sales were AM2, but most CPU sales were 939. The majority of 939 systems out there are PCI-e and SATA, and a lot of folks dropped a good amount of DDR Ram in when it was inexpensive.

A nice affordable dual core upgrade from their single core, and they're set for at least a year if not more. (Depending on their usage)

For me personally, I'm in a 754 still. (Talk about a lack of CPU upgrades available there!) So my next upgrade will be a full one, and it's hard to consider AMD this time around when Intel is offering such good bang for the buck. I sincerely hope they figure all this out, as I've been a strong supporter of their products since the 5x86/133 CPU.


Compete with Penryn ?
By 2ManyOptions on 12/5/2007 11:26:13 AM , Rating: 2
If the Phenom/K10 line of processors were not able to match the C2Ds and the Penryns, how will an existing/old architecture ensure good competition?




RE: Compete with Penryn ?
By Vanilla Thunder on 12/5/2007 12:15:19 PM , Rating: 3
Have you seen what AMD sells these chips for? Your average user/consumer would not notice the difference between C2D or K8 chips in their daily routine. And if they can save themselves $100 on a PC that suits their needs, I'd be willing to bet they'd go that route. I'm still running a 4800 X2 in my machine OC'd to 2.7 ghz, and to be perfectly honest, I'm not ready to drop all that cash on a new Mobo, ram, and CPU just to have the "best" out there. Not everyone needs the best, just something that works well.

Vanilla


AMD is quite stupid lately...
By Captain Orgazmo on 12/5/2007 12:15:15 PM , Rating: 2
I know 3 people personally who have socket 939 systems with old Athlon 64 3200+'s. They all have PCI express boards, meaning they can upgrade video cards and whatever else they want, but not processors. If AMD had any brains, and wanted to make a spot of cash in the next year, they would release a couple of these "new" K8s in a socket 939 version. All of these three people, and many more like them, will be forced to buy a new system, and they will all buy intel.




RE: AMD is quite stupid lately...
By 1s0ul on 12/6/2007 4:34:42 AM , Rating: 2
Yup, that's exactly like me. I'm still running 939 3200+'s at the moment and have been saving up for a while for my next upgrade / system. I'll probably have to build a new system anyways and it looks like I'll have to go with Intel this round...


By kilkennycat on 12/5/2007 2:57:08 PM , Rating: 2
Seems like an appropriate fix for all of AMDs current Barcelona and Phenom woes. Certainly better yields and none of this tri-core nonsense. Take a leaf out of the Intel play-book, just as Intel took a leaf out of the AMD playbook when they finally dumped Netburst . And with the K8/Opteron architecture it seems like a pretty trivial design exercise.




By StevoLincolnite on 12/6/2007 10:52:25 AM , Rating: 2
Nonsense? If Tri-Cores had a Performance Improvement at a cheaper price than a similar dual-core I don't think anyone would complain.


Don't look back...
By iFX on 12/5/2007 3:08:49 PM , Rating: 2
AMD needs to stop trying to compete with Intel and start competing with the consumer, because Intel isn’t buying their microprocessors, the consumer is.

What do I mean by compete with the consumer? Simple, AMD has a ton of negative press and when compared with Intel’s offering they look like they are “losing” in their market. AMD needs to battle with consumers with marketing to show that AMD, in its own market is the right choice for their dollars. How do we accomplish that? By pitting AMD products against each other and reinventing the entire product line.

So how do we win with the consumer? Simple., establish a base performance level that you can market to the consumer, this level will be your cheapest product. Now everything above that product which already has a great performance level will be even better. Right now AMD has a very confusing product lineup. The K8 microprocessors have been renamed and rebadged so many times I quit trying to understand it. AMD can win back their lost market share with competitive pricing, smaller product lines and a clear purpose for each line. If AMD would market each product line better they would be in good shape.

AMD needs three principle product lines: Every day computing, performance computing and high end computing. Each product line should utilize a unified naming scheme, pricing scheme and should follow a logical progression of increased performance and price per model. Make it easy for the consumer to see what they are buying, and emphasize that the cheapest product is very good at its intended purpose. Right now the consensus from consumers is that all AMD products are poor at any purpose – AMD must change that perception ASAP, and again, competing with Intel is the wrong way to do it.

To accomplish effective marketing the product line must shrink considerably from its current state. All confusing tags must be removed, different variations of the same model must be removed, confusing pricing models must be removed and finally products need to fall into one of three distinct product lines. Here is the lineup:

Every day computing (all dual core, K8, 65nm):
AMD Athlon X2 2400+ @ 2.4 GHz - $75
AMD Athlon X2 2800+ @ 2.8 GHz - $100
AMD Athlon X2 3000+ @ 3.0 GHz - $125
AMD Athlon X2 3400+ @ 3.4 GHz - $150

Performance computing (K10, all quad core):
AMD Phenom X4 2400+ @ 2.4 GHz - $175
AMD Phenom X4 2800+ @ 2.8 GHz - $200
AMD Phenom X4 3000+ @ 3.0 GHz - $225
AMD Phenom X4 3400+ @ 3.4 GHz - $250

High End computing (K10, all quad core):
AMD FX 3600+ @ 3.6 GHz - $325
AMD FX 3800+ @ 3.8 GHz - $375

Now, I realize that K10 isn’t able to hit these speeds currently – but it will in time. In the meantime relaunches can start ASAP of current offerings with new, simplified product lines, naming models and pricing models. AMD needs to go on TV, radio, the web, bill boards, and McDonald’s cups, literally everywhere to blast their new and improved family of processors.

And finally – the biggest thing AMD has to do is leave the lineup alone for at least 12 months. No renames, no relaunches, no special editions, no nothing. Give the consumer time to grow into your product line. People will buy what they can now and upgrade in the future – if they commit their future upgrade to memory and then in six months that product is gone or under a new name then all of your marketing efforts are for nothing. People need to be able to keep their next purchase in vue, see it for sale, see it in stores, so that when they do upgrade it’s there waiting. Otherwise – they have to start their learning over, and may include a competitor in their research. One last thing – leave the prices alone. Set a price and leave it alone.

I wish AMD all the best. They have the technology, they just need the leadership. Fire Hector and fire all the marketing people before it’s too late. And while they are at it, fire the entire line of project executives as well. I can’t believe the share holders aren’t demanding Hector’s head on a pike at this point.




RE: Don't look back...
By mindless1 on 12/6/2007 12:29:49 AM , Rating: 2
Actually, AMD doesn't have negative press with the typical consumer, the typical consumer barely ever sees any press at all about AMD which is part of why they didn't gain momentum when they had comparable product in the early K7 era.


Resurrection...
By Proteusza on 12/5/2007 11:08:47 AM , Rating: 2
It lives.... again!




FINALLY
By anubis44 on 12/5/2007 11:58:10 AM , Rating: 2
This is the first really promising CPU news out of AMD since the release of the A64 X2 core. F I N A L L Y. There's nothing wrong with a company recognizing that one of their engineering teams has made a miscalculation. Same thing happened to Intel with the Pentium D. The way forward for Intel was not to build on the Pentium IV core, but to go BACK to the Pentium III core (which their Israeli team did with the Tulatin and subsequent excellent Pentium M chips), which led to successor Core and Core 2 chips.

AMD should go back to the A64 core and work on ways of improving it in much the same fashion. The K8 core was and still is incredibly elegant. I'm not a chip designer, but I'm pretty sure a rethink of the K8 core is the way forward, at least for the desktop and lower end server chips. The K10 core is awesome conceptually, but it is starved for Lvl2 cache, and Lvl 3 cache has too much latency. AMD needs to go to .45u in order to realize the full potential of the K10 core by giving it the kind of cache Intel is able to give it's Penryn processors, which are .45u.




By nofumble62 on 12/9/2007 7:44:24 PM , Rating: 2
Does AMD have any answer on the mobile front?




Tic-Tac Model???
By gd4u on 12/5/2007 7:39:33 PM , Rating: 1
Why Intel`s Tic-Tac Model is not followed? Penryn is Core 2 duo architechture on 45nm Tech. Where is K8 on 65nm?




Goodbye AMD
By Ihmemies on 12/5/07, Rating: -1
RE: Goodbye AMD
By StevoLincolnite on 12/5/2007 10:55:27 AM , Rating: 3
You make it sound as if AMD is a Failure, the K6-2 and K6-3 were great value Chips in they're time, And the K8 was a great chip against the Pentium 4, And in-fact I still think the K8 is a still a great processor, As far as I last checked any AMD K8 Athlon 64 X2 is capable of still running anything demanding, and the K7 was just a solid chip with a very long life, Especially those Socket A boards...


RE: Goodbye AMD
By 16nm on 12/5/2007 11:00:51 AM , Rating: 4
The smartest thing for AMD to do now would be to keep working on K8 by refining it and getting more megahertz/efficiency out of it. I would not see anything wrong with them introducing a two-die quad-core K8 chip if it is reasonably feasable.


RE: Goodbye AMD
By cochy on 12/5/2007 11:03:31 AM , Rating: 3
There's only so far that you can push a CPU design.


RE: Goodbye AMD
By 16nm on 12/5/2007 11:16:48 AM , Rating: 2
Well, I think AMD are doing a pretty good job with K8 90nm, but they have a long way to go with 65nm. There is a lot of room for improvement there.

Conroe and K8, more or less, are the same design. Intel had great expertise with the 65nm process going into Conroe because of how hard they had to push it on the Netburst design. AMD have a lot more room for improvement with regards to their 65nm process. Fully expect them to introduce better, efficient steppings on 65nm. K8 is top technology and does not need to be retired. Updated - yes, retired - no. For example, SSE4 would not be a bad addition.


RE: Goodbye AMD
By Proteusza on 12/5/2007 12:04:43 PM , Rating: 3
K8 and Core 2 are similar but different. Like a Corvette compared to a Viper. Similar philosophies, different execution.

The Core 2 is superior in integer performance especially.


RE: Goodbye AMD
By MandrakeQ on 12/5/2007 1:32:56 PM , Rating: 2
Core 2 is optimized for high ILP, and it doesn't look like AMD is pursuing that route as aggressively anymore.

AMD appears to be spending their transistors on server features lately, and this means the desktop market gets neglected. I don't really blame them for this decision given the razor thin margins they have to deal with in desktop procs.

Sun has taken a similar path with their Niagara processors by focusing on thread level parallelism, and this appears to be working out well for them.


RE: Goodbye AMD
By Andrwken on 12/5/2007 6:45:35 PM , Rating: 3
The margins are razor thin by not having a competitive product. Are you saying they shifted design philosophy 2-3 years ago when k10 design started because they thought the margins would be bad on the desktop? I thought they were doing quite well in the desktop space back then, and it would seem odd to neglect it on the current design, unless, you didn't expect your vastly larger rival to come back swinging after you started takin pop shots and marketshare.

It's called don't kick the 800 lb. gorilla until your are at least an 800 lb gorilla and can deal with the consequences of waking the sleeping giant. ;)

They just don't have the resources, or capital to play with the big boy at this point, and purchasing ati gave them enough marketshare for intel to pummel them even more without having to worry about the monopoly talk for a while.


RE: Goodbye AMD
By MandrakeQ on 12/5/2007 7:41:03 PM , Rating: 3
Whenever AMD and Intel have had roughly equal performance, margins are smaller for both sides. When one pulls ahead of the other though, the leader can charge more for the performance premium, and they make more money. When you're on the losing side of the battle, then your margins become 0 or negative (AMD is in that situation right now).

K8 was AMD's first processor to successfully compete in the server space (development started back in late 90's I believe). The design philosophy of the architecture is clear when you take a look at its two most defining features, x86-64 and the IMC (neither of which are particularly useful for desktop users). AMD took advantage that Intel wanted to force Itanium down everyones throat, as well as the fact that P4 was so inefficient that it took massive amounts of power just to get it competitive. Not to mention that Intel had at that point considered AMD a bottom feeder and left it completely unchecked.

K10 is an extension to K8 (still with a focus on servers) and it is going to do well in the 8+ core server space. Everywhere else it will lag behind, since there's no way a 4MB cache shared across 4 cores will perform as well as the 12MB cache the Penryn Xeons have (Unless of course you're bottleneck is bus traffic and memory latency, which is the case for the market previously mentioned).


RE: Goodbye AMD
By myocardia on 12/6/2007 1:38:39 PM , Rating: 2
quote:
K10 is an extension to K8 (still with a focus on servers) and it is going to do well in the 8+ core server space. Everywhere else it will lag behind, since there's no way a 4MB cache shared across 4 cores will perform as well as the 12MB cache the Penryn Xeons have (Unless of course you're bottleneck is bus traffic and memory latency, which is the case for the market previously mentioned).


Umm, two things to be noted here. First is that all Barcelona's (the K10 server chip) have been recalled. The second is that 100% of Intel's current quad-core CPU's have 2x4 MB of L2 cache, not 1x4 MB.


RE: Goodbye AMD
By MandrakeQ on 12/6/2007 3:34:42 PM , Rating: 2
I thought Penryn based Xeon 5400's had 12 MB L2 cache? Are these not available yet? As for the recall, its a bummer for AMD, but if they can get the problem fixed soon (hopefully by early next quarter), they should be able to sell a healthy number of them at least until Nehalem comes out.


RE: Goodbye AMD
By joemoedee on 12/6/2007 8:09:40 AM , Rating: 2
quote:
There's only so far that you can push a CPU design.


True, but then you have to consider that the current Intel CPUs that are wiping the floor with AMD performance wise trace their routes back to the P3 which was launched back in 1999.

There's a lot to be said for refinement and enhancement on CPUs. One great thing AMD has going for their K8 CPUS is Hypertransport, and I think they could still ring some good performance gains from their existing design.


RE: Goodbye AMD
By StevoLincolnite on 12/5/2007 11:05:31 AM , Rating: 4
I actually thought they would release a quad core K8, And if some of Quad's weren't functional could have sold them off as single and dual cores.
I Personally Have a Pentium M laptop, Pentium 3 Tualatin 1.4ghz machines and an Athlon 64 X2 4000+ - All solid machines in they're own right.

And considering the Price of the Athlon 64 X2's they are seriously great Performance for you're dollar in budget machines.


RE: Goodbye AMD
By murphyslabrat on 12/5/2007 11:07:47 AM , Rating: 3
Yeah, like imagine if Intel had've stuck with re-iterating the original Pentium instead of giving us the next generation of computing with Netburst...</sarcasm>

Not quite an acurate parallel, but it stands.


RE: Goodbye AMD
By iFX on 12/5/2007 11:52:20 AM , Rating: 1
No it doesn't stand. Netburth was a flaming POS, and K8 is a revolutionary, highly efficient CPU design that until mid 2006 was top dog. It has a long life left if AMD is smart.


RE: Goodbye AMD
By TomZ on 12/5/2007 12:33:25 PM , Rating: 2
Nah, the only future K8 has is if AMD sells 'em cheap. It doesn't compare to Core 2 either performance wise or in terms of energy efficiency. The only other possible angle is to make them cheap enough so that performance/dollar competes with Intel at this point. And in the meantime, Intel is not standing still either...


RE: Goodbye AMD
By mindless1 on 12/5/2007 11:16:56 PM , Rating: 2
They already were, beating Intel in by far the most popular price segment, the under $140 and more recently under $85 category.

Their future depends on lowering manufacturing costs and securing more OEM contracts, because AMD was in 2nd place, is in 2nd place, and will continue to be in 2nd place to Intel. It's not a competition with Intel for performance or efficiency, it's a competition to provide a cost effective solution to OEMs.


RE: Goodbye AMD
By murphyslabrat on 12/6/2007 1:22:13 PM , Rating: 2
The only problem with that is that a consumer will read stuff like, "Intel CPU's overclock like crazy", and "AMD just can't beat Intel when it comes to ultra-high performance"; and they'll go with an Intel CPU, assuming that these reports have a bearing on SOHO.

So, in other words, the "more educated" consumers that we have nowadays, as a result of Intel's Netburst, will go with an Intel CPU. Short of that, we have the domnodies that have absolutely no clue, and will probably end up buying a Netburst Celeron/Pentium D.


RE: Goodbye AMD
By 16nm on 12/5/2007 1:06:24 PM , Rating: 1
K8 and Conroe are just evoluntionary Pentium Pro/P2/P3 designs. There's nothing Revolutionary about K8. Netburst was just a weird design to wow the buyer with great megahertz numbers. Intel thought they could design the long pipeline to be very intelligent wrt instruction ordering and achieve great performance but that never happened. The ultra long pipelined Prescott was supposed to be the pinnacle of this effort but it was a total flop, but boy did Intel ever learn a lot about manufacturing processes with it. It catapolted them to where they are today. Their manufacturing processes are the absolute best. Wait till they fine tune their high k metal gate 45nm process (something AMD do not even have in the works). It will be something to behold, I'm sure.

AMD need to get some of the Intel Mojo in their 65nm process. I suspect it's mostly a question of dinero standing in the way of their success right now. And that's too bad, because it doesn't seem as though they'll be earning a whole lot any time soon.


RE: Goodbye AMD
By weskurtz0081 on 12/5/2007 1:29:54 PM , Rating: 2
AMD and IBM are working on HKMG's actually, and we MIGHT see them by the end of next year.


RE: Goodbye AMD
By 16nm on 12/5/2007 2:14:55 PM , Rating: 2
That's good news. I've only heard that IBM had high k 45nm but that AMD were not interested (in paying for it, probably). I do know with certainty that AMD's current 45nm effort is of the low k gate variety.

It's very good to hear that IBM and AMD are working on high k together. I hope AMD lessen their focus on a single die quad and concentrate their efforts on dual core and dual die quad core chips. From a manufacturing standpoint, this seems to make sense, and performance does not appear to be a huge issue (Kentsfield > Phenom).


RE: Goodbye AMD
By weskurtz0081 on 12/5/2007 4:50:10 PM , Rating: 2
good post. The first round of AMD 45nm will indeed be SOI, and they are supposed to switch over to HK after they release and get the 45nm process working fairly well. It probably will not be until 09 until we see it, but they are working on it.


RE: Goodbye AMD
By murphyslabrat on 12/5/2007 2:17:32 PM , Rating: 2
The comparison I am making is to the negative step away from a very capable little brother. Netburst was an all-new design, while Barcelona is an evolutionary step; however, neither were any better than their precursor. Netburst, as you said, was a flaming POS, and Barcelona is so much more costly (money, R&D, and transister/silicon-wise) for similar performance compared to K-8. Amd would probably have done better by sticking to pathway optimization, silicon and transistor innovation, and, possibly, channeling it directly into die-shrink R&D. As is, we have something, that at present, was a catastrophic waste.

Maybe we just aren't seeing the full fruition of the technologies that debuted with Barcelona, but the suspicious absence is akin to the massive performance increases promised with Netburst.

BTW, few things make me as angry as Netburst. Do you realize that, barring available platform-specific considerations--memory-speed, FSB-bandwidth, etc--the Tualatin revision of the Pentium III not only performed much better than the Pentium 4, but had a die-size of approximately half of a same-node Pentium 4. The only shortcoming is in FLOPS, where the Pentium III and Pentium 4 were about even, clock-for-clock.

At least AMD hasn't pulled that one on us...yet. And I sure as hell hope we never see anything like the Pentium III-to-Netburst again.


RE: Goodbye AMD
By StevoLincolnite on 12/6/2007 10:49:03 AM , Rating: 2
The Tualatin was actually very poor at clock speed ramping, it was more of a test of the new process node that would eventually be used for the Pentium 4 Northwood, the Willamatte still used the same fabrication nodes as the Pentium 3 coppermine, the other notable thing is, that the Celeron Tualatin actually performed about the same as the Coppermine clock for clock (Even while it had a 33% advantage in bandwidth).

Besides the Pentim 4 wasn't all that bad, think of it like this.
Intel Used the Pentium 3 Tualatin, Retrofitted it with the Pentium 4's Front side bus, Advanced tree predictor, Doubled/Quadrupled the cache and made it more energy efficient, and extended/improved the pipeline and called it a Pentium M, which is what our new beloved Core 2 Duo's are all based on, which clock for clock slaughtered the Pentium 4.


RE: Goodbye AMD
By murphyslabrat on 12/22/2007 1:05:03 PM , Rating: 2
quote:
the Celeron Tualatin actually performed about the same as the Coppermine clock for clock

Yes, while it had one half to one quarter of the L2 cache. If anything, that's a testament to the versatility of the P6 core.

And why couldn't Intel have done all of that whithout the Pentium 4?


RE: Goodbye AMD
By gusc3669 on 12/5/2007 12:13:15 PM , Rating: 2
I am not an IT person, but I agree that while playing "one-ups" by producing a chip that is faster (clockwise) than the competitor's chip is not the way to go (eventually), it did sell chips back in the Pentium era, along with bragging rights, until AMD took a next step and produced their Athlon (Socket A) chips. I still own a Socket A computer and remember that it was not the fastest when I purchased it, but it was more efficient and could perform operations on par or better than the faster, more expensive, Pentiums.

AMD needs this "next step" in innovation if it is to remain competitive and get back to its desired profitability. Yes, you could compete in the "budget" arena but not if the competition is providing equal or better offerings at relatively the same price point. AMD would also need to ramp up the volume sold if it wants to go this route which does not seem to be occurring as the majority of new the Dell/HP/Corporate mainstream purchases are Intel based (at least in the various companies I've been associated with). Making their products on the 65nm die, increasing the clock rate, and possibly lowering the price is fine if they want to remain competitive and sell some chips, but don't cut the other items which add to the chips overall performance.


RE: Goodbye AMD
By 91TTZ on 12/6/2007 7:58:08 AM , Rating: 2
quote:
Yeah, like imagine if Intel had've stuck with re-iterating the original Pentium instead of giving us the next generation of computing with Netburst...</sarcasm>


That's sort of what they ended up doing. They scrapped the Netburst idea and went back to reworking the Pentium Pro design.


RE: Goodbye AMD
By caqde on 12/5/2007 11:26:22 AM , Rating: 3
Unfortunately that is impossible because of the design of the K8. The on-board memory controller makes doing such a task impossible without major changes to the core one way or another. Hence the Barcelona core's design... A design like Bulldozer/Fusion will get rid of such issues though.


RE: Goodbye AMD
By Amiga500 on 12/5/07, Rating: 0
RE: Goodbye AMD
By Martimus on 12/5/2007 12:36:17 PM , Rating: 2
I don't know if they could introduce two-die quad-cores with the integrated memory controller. But maybe they can, considering they had two chip solutions with the Quad-FX setup.


RE: Goodbye AMD
By 16nm on 12/5/2007 12:45:06 PM , Rating: 2
I'm sure it is possible, but is it reasonable? They've surely thought about it, and I hope the reason we don't see any discussion of it is NOT because they have been making fun of the Intel dual-die quad. Ego should not get in the way of rational decision making...


RE: Goodbye AMD
By Master Kenobi (blog) on 12/5/2007 12:50:19 PM , Rating: 2
With Quad-FX, each controller had explicit control of one bank of memory, not both. So basically it was "separate but equal". This is where Intel is getting benefit by having the memory controller on the north bridge. They can glue two dice together and get away with it, just tweak the controller to compensate. AMD has to stick with the unified design because it's integrated, at least until they can do something very creative so that the two don't fight each other for fetches.


RE: Goodbye AMD
By Martimus on 12/5/2007 1:07:12 PM , Rating: 2
That is kind of what I had thought, thank you for answering. I am glad that I posted that here, as I have been wondering about that issue for a while and it would have been difficult to look it up an my own.


RE: Goodbye AMD
By 16nm on 12/5/2007 1:15:21 PM , Rating: 2
Yes, they could try to do something very creative, or, simply copy Intel's design. It doesn't seem to matter much where the memory controller is placed judging from the performance of Conroe. At least, we don't hear much about the superiority of the IMC since Conroe debuted. That bullet has pretty much been shutdown. AMD must do something to get back in the game. K10 is not going well at all. That L3 cache design flaw is really absurd. They totally dropped the ball on that one. It seems everything hinges on K10 right now. If they can keep K8 going then they can relax and work on getting K10 right.


RE: Goodbye AMD
By Master Kenobi (blog) on 12/5/2007 5:50:47 PM , Rating: 2
Yes and No. Conroe gets away with kicking butt and having the Controller on the North Bridge because Intel's engineers worked some magic. AMD's IMC and HT bus can feed their processor faster than Intel can (Theoretically). Intel compensates for this by increasing the L2 cache into the 2-12MB range and using extremely slick algorithms to do intelligent pre-fetching. Allowing it to feed data into the chip at a rate the chip can use without a performance hit where the CPU is idling on cycles because it can't get information quickly enough.

To go with Intel's north bridge method, AMD would not only have to come up with a better prefetch method, but also increase the L2 and possibly L3 (Jury is still out on how effective L3 cache really is, Barcelona/Phenom was not the best of implementations based on the theories I've read about) into the megabyte range much as Intel has.

With Intel's move to Nehalem, they will be sporting the Native Quad Core design much like Barceona/Phenom, they will also be sporting the Integraged Memory Controller, and the new Intel QuickPath (Faster and more bandwidth than Hyper-Transport 3.0 supposedly). Now Intel is also adding Hyper-Threading back in so it will show up as 8 Processors to Windows (Should be pretty slick). If Intel can find a way to glue 2 of those together and not have the memory controllers fighting, AMD could copy that (If they haven't figured out how to do it by then). Right now they would have to re-engineer their chips and chipsets to a point that would make them both incompatable with current boards and chipsets, as well as force them to redesign the CPU's and a lot of the logic built into it that is based around being linked to the IMC. Sounds like too much cost and headache to get around it. Best bet would be to develop a way to not have the IMC's fight with each other.

In Summary.... Intel played their cards right and played their strengths and milked every last bit out of the North Bridge, Legacy BUS, and their processes. They were able to take a cheap route based on existing architecture and glue two dice together and make out like bandits.

AMD Ran with new tech like IMC, and Hyper-Transport and while it has worked well for them (K7/K8) it seems to have closed that door for them, up until such time as they can figure out how to get 2 IMC's to play nicely. That's really the only thing stopping them from doing exactly what Intel is doing.


RE: Goodbye AMD
By JumpingJack on 12/7/2007 2:37:30 AM , Rating: 1
Well done.... the argument boils down to cache really.

Fast bus + small cache or slow bus + large cache, the design choice of either combination is balanced to hit certain performance goals.

Cache hit/miss rate goes as a power law in terms of overall capability, the larger the cache the lower the miss rate (a miss being a situation where the processor needs data but does not find it in cache).

Small caches have high miss rates, to mitigate the penalty for going to DRAM, simply design a bus to get it there faster (high BW, low latency), so if you miss say 5 times out of 20 attempts, you may pay only 8 cycles penalty waiting.

Large caches have low miss rates, so you may only miss 2 times out of 20, but you must pay 12 cycles penalty waiting on the slow bus.... just an example.

It is completely possible with the 'archaic' FSB to out perform the novel and slick IMC implementation so long as the caching technology is par excellent (which C2D has), consequently high quality memory is not nearly as impactive on a well cached CPU as opposed to a cache lean CPU.

Where the FSB becomes more problematic are in large throughput, large working set situations where even a larger cache becomes overwhelmed ... hence SPECFP_rates (large data sets, high through put) really shine on the high BW busses.


RE: Goodbye AMD
By Omega215D on 12/5/2007 2:16:36 PM , Rating: 1
Refining K8 and bringing some of that to the Socket 939 iteration... ok I know it's a pipe dream but hey, I'm sticking with my 939 and DDR until it's absolutely necessary (gaming wise) to ditch my current setup.


RE: Goodbye AMD
By qwertyz on 12/5/07, Rating: 0
RE: Goodbye AMD
By NullSubroutine on 12/5/2007 11:26:44 AM , Rating: 5
I hope you realize that most of the consumers don't buy CPUs because of benchmarks. Most people would assume the Pentium 4 at 1.7 Ghz is faster than Pentium 3 at 1.7 Ghz simply because 4 is better than 3.

Except for Vista, any CPU sold today in the Core or X2 series is more than capable for 95% of all consumers out there.

What is more important to them is having more hard drive space for their music and videos and having morre ram so their computer runs faster/better.

Even they typically just call everything "memory". Gaming, video professionals, or enthusiast only make up so much of the market.


RE: Goodbye AMD
By iFX on 12/5/2007 11:54:24 AM , Rating: 1
This is correct, which is why AMD chips at lower price points are selling quite well.


RE: Goodbye AMD
By FITCamaro on 12/5/2007 12:34:33 PM , Rating: 2
Name a Core or X2 processor not capable of running Vista? They've got it running on 1GHz Core 2 chips in small form factor PCs. RAM is far more important with Vista.


RE: Goodbye AMD
By mindless1 on 12/5/2007 11:28:14 PM , Rating: 2
Except for Vista, a Celeron 800 is enough for 90% of users out there. Actually, most people do not have a system as fast as any latter generation P4 or K8 based system, and this doesn't even count the dinosaurs some businesses use.

There are a vast number of users out there that have a primary goal to just keep using their present system until it breaks and when it does, to repair or replace it, whichever as cheaply as possible being the main factor without particular concern for performance increases.


RE: Goodbye AMD
By StevoLincolnite on 12/6/2007 10:58:17 AM , Rating: 2
Indeed, Most people who only write letters etc, don't need anything faster than a Pentium 3/Celeron/Athlon/K6-2/K6-3 faster than 500mhz and 256mb of ram and a TNT2 or maybe a Geforce 2 and Windows XP for that matter.

I wouldn't mind someone like Via or AMD perhaps to make Sub 1ghz processors especially for this market in mass quantities.
Maybe Kmart and Coles, Myers and woolies could start selling systems based around these processors then for extremely low prices and those who can't afford anything else and just want to browse the internet and write letters etc.


RE: Goodbye AMD
By Adsski on 12/5/2007 11:46:26 AM , Rating: 3
We need AMD!

And if they have to resurrect K8 to help then survive then thats great.

I'm still running the venerable K8 90nm myself.
X2 4200 manchester, S939, DFI, DDR450, x1800xt to be precise.

The point is whilst i'm really tempted to crash the cash on a quad core system i have to ask the question, do i need it! Or will that 8800GTX / HD3870 be the only upgrade i need to run crysilis?

For the average joe buying an off the shelf unit at PC world the old X2 K8's will be fine, yeah conroes quicker but lets be honest only the users wanting to game at high res or do some serious video processing are gonna notice the difference. For those doing MS Office, Photos & Web
I think 2GB of some good DDR2 800 would make more of an impact.

And of course ditch Vista, XP SP3 looks the way forward!


RE: Goodbye AMD
By Noya on 12/5/2007 1:27:54 PM , Rating: 2
K8 was what stomped all over Intel, not K7.


RE: Goodbye AMD
By Omega215D on 12/5/2007 2:14:20 PM , Rating: 2
There was the Slot A Athlons that stomp over Intel up until the AMD released the 1GHz Ahtlon. Then Intel pulled ahead slightly after that with the P3 1GHz.


RE: Goodbye AMD
By Brockway on 12/5/2007 4:47:42 PM , Rating: 1
The P3 1ghz was a buggy unstable piece of crap that was never widely released.


RE: Goodbye AMD
By Omega215D on 12/5/2007 4:55:24 PM , Rating: 2
I thought the regular 1GHz that was fine and the 1.13GHz version was the one that was unstable and buggy.


RE: Goodbye AMD
By mindless1 on 12/5/2007 11:49:36 PM , Rating: 2
Yes, the first release of 1.13GHz Coppermine was instable. They fixed it and also came up with the P3 Tualatins to 1.4 (or maybe it was 1.5) GHz.

By cC0 stepping, even some of their Celeron 600s would run stabily at 1.2GHz with a bit of a voltage increase.


RE: Goodbye AMD
By mindless1 on 12/5/2007 11:32:57 PM , Rating: 2
Nope, Athlon and P3 were reasonably competitive in the slot A era. Later in that era around the 1GHz point, it wasn't even the processor that mattered as much as the chipset, as at that point Intel platform chipsets were better.


Ugh
By MrBungle123 on 12/5/07, Rating: -1
RE: Ugh
By murphyslabrat on 12/5/2007 11:04:35 AM , Rating: 3
Hey, look at the "rebadging" done on the PIII. The tualatin core was the die-shrink/slight enhancement of the coppermine, and look how that turned out. If Intel had stuck with it's k6 architecture...well, we wouldn't have AMD as we know it, that's for sure.

Product refreshes aren't always worthless. If AMD can re-use an existing product, great...as long as they don't go calling it stuff like "innovation", "the next generation", or other crap like that.


RE: Ugh
By StevoLincolnite on 12/5/2007 11:14:48 AM , Rating: 2
You mean P6*
Well it Started off with the Pentium pro then the Pentium 2, Pentium 3, Pentium M and now the core series, all dating back to a... 15 year old processor design? (Although its a rather huge evolution).
The Netburst just happened to sit between the Pentium 3 and M, Unfortunately it didn't ramp up in clockspeeds to 10ghz like Intel wanted it to, And the other notable thing is that the Pentium 4 went under design Stages near the End of the Pentium 2's life time and was going to be the Pentium 2's Successor.
But the competition at the time, made Intel release the Pentium 3 Katmai and Coppermine, the Tualatin was a Dieshrink test for the Pentium 4 Northwood series.


RE: Ugh
By murphyslabrat on 12/5/2007 2:41:31 PM , Rating: 2
Heh, yes, I did mean P6.

quote:
But the competition at the time, made Intel release the Pentium 3 Katmai...

Which, ironically enough, bore much resemblance to the Deschutes core, though it had the (hacked, half-bandwidth) SSE instructions, as well as some core tweaks.
quote:
Tualatin was a Dieshrink test for the Pentium 4 Northwood series.

Yep, and a very successful one too. The only reason why anyone bought Pentium 4's was due to the hype, increased clockspeeds, and the fact that Intel intentionally crippled the Tualatin's sales.

Intel made some inconsequential tweaks to the bus logic and pin-layout that made the new CPU's incompatible with previous platforms. Then, they charged an immense price-premium for the new chipsets and CPU's. If Intel had took it's head out of the marketing departments **s, they would've at least kept the Xeon line based partially on Tualatin revisions.

As is, the only group to recognize the Pentium III's value was a small Israeli lab...the one responsible for Intel's--forsaken--on-die memory controllers. That's where you got the Pentium M and Core, after which Intel saw pure gold...and the rest of the story is in every up-to-date, top-end PC, today.

As I said before, the transition to Netburst is one of the most infuriating things for me, that a corporation would intentionally bank on the consumer's ignorance. And, more frustrating, is that with every product launch, AMD seems to be getting closer and closer to that...


RE: Ugh
By chick0n on 12/5/07, Rating: -1
RE: Ugh
By StevoLincolnite on 12/5/2007 11:18:56 AM , Rating: 1
Intel is not the only company that "Rebadges and enhances" products, nVidia used the Geforce 2, Improced the Memory Controller, Added a few things, and called it a Geforce 4 MX.

ATI Used the Radeon 8500 and did a similar thing, and renamed it the Radeon 9000, 9100, 9200 etc.

The Geforce 7 series is a heavily modified Geforce 6 series GPU.

All these company's do similar things, its how they gain little niche' markets, and improve they're market share.

Then again people didn't complain when they found out that they're Geforce 6200 A's are actually Geforce 6600's although its the same thing, just a superior product turned into a lesser one in order to meet demand, so why act differently in this situation?


Close the doors already
By bull2760 on 12/5/07, Rating: -1
RE: Close the doors already
By DigitalFreak on 12/5/2007 11:17:43 AM , Rating: 3
quote:
AMD I've given you 10 years worth of my money in building computers based off your crap, hoping that one day you might get it right.


Then shame on you for being stupid enough to continue giving them your money.


RE: Close the doors already
By anubis44 on 12/5/2007 12:16:36 PM , Rating: 5
So AMD's only produced '10 Years of crap?'

Let's see here:

1999 - K7 processor released, and puts the smack on the Pentium III (oh yeah, THAT was a crappy chip)
2000 - AMD is first to 1GHz with Thunderbird K7 (Looks like AMD's really misfiring here)
2001 - AMD releases Athlon XP
2003 - AMD releases Barton core Athlon XP (remember those?)
Sept. 23rd, 2003 - AMD A64 - AMD kicks Intel's ass with the first 64 bit x86 process: A64 (Yeah, that one was REAL garbage)
April 21, 2005 - AMD A64 X2 - AMDreleases a BACKWARDS COMPATIBLE dual core A64, which is drop in replacement for the single core A64 (Gee, what a FAILIURE the X2 was.)

I'm only STILL using a toledo A64 X2 4400+ chip clocked without voltage adjustment at 2.53GHz on my 3 year old Gigabyte motherboard, and it's still giving me completely excellent performance.

So, all these processors were just 'crap', eh? Methinks you've got your head stuck in a toilet. The A64 was so formidable, Intel was practically having a seizure when they benchmarked it. Then AMD released a dual-core version which worked in the same socket (939) motherboards we already had. If that's not giving us value for the money, then you need to go and re-evaluate your sense of proportion.


RE: Close the doors already
By StevoLincolnite on 12/5/2007 11:25:47 AM , Rating: 3
quote:
AMD I've given you 10 years worth of my money in building computers based off your crap, hoping that one day you might get it right.


Hang on... You're the idiot for buying it in the first place even if it didn't meet you're needs, Thats not AMD's fault, that is you're own.

And remember, Phenom is still young, give it time to mature like the Intel Pentium 4 did, that chip my friend didn't truly shine until it reached higher clock speeds.

quote:
Intel you now have my money for the next 10 years!


You say that now... But you don't know what the future holds in the Performance/Dollar market and you may change you're mind in 12 months time.

The way I think is: "There is no failed chip, its just the competition is better".


"We don't know how to make a $500 computer that's not a piece of junk." -- Apple CEO Steve Jobs

Did You Partake in "Black Friday/Thursday"?
Did You Partake in "Black Friday/Thursday"? 





0 Comments
Related Articles













botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki