backtop


Print 42 comment(s) - last by boogle.. on Jun 21 at 8:01 AM


  (Source: HEXUS)
AMD has a new chip in the works to tackle the MID/netbook market

Intel and AMD have been fierce rivals for many years. Intel almost always had the upper hand over AMD until the launch of AMD's K8 architecture which saw the Sunnyvale, California-based company basking in the spotlight (and in enthusiast praise). Intel shoved AMD into the backseat with the launch of its Core architecture and AMD has been pretty much stuck in that position ever since.

While AMD may be having problems tackling Intel in the high-end desktop and notebook markets, the company is looking to go toe-to-toe with Intel in the emerging Mobile Internet Device (MID) and netbooks/nettop market. Intel is currently having a lot of success with its Atom processor which will be in short supply until the end of Q3 2008.

AMD is countering with a low-power AMD64-based CPU design of its own according to leaked slides obtained by Eee PC News. The unnamed processor features an integrated memory controller, 16-lane 800MHz HyperTransport link, 256KB of L2 cache, and a 1GHz core clock.

Considering that this new chip is to be used in low-power applications, power consumption is a critical talking point. Intel's Atom N270 -- the most popular Atom variant for netbooks -- features a 2.5W TDP at 1.6GHz. However, we can't forget the i945GSE Northbridge which adds another 4W -- more than the Atom processor itself.

AMD’s new processor, however, has an 8W TDP for the processor with its integrated Northbridge/memory controller at 1.0GHz. Although performance figures obviously aren't available at this time, it would be interesting to see how AMD's 1.0GHz processor would do against Intel's in-order 1.6GHz Atom N270.

Intel and AMD have both been in the news in recent weeks -- mostly for squabbles between the two companies. Intel recently got slapped with a $25M fine for anticompetitive practices in South Korea. Shortly after, the Federal Trade Commission opened up a formal investigation into allegations of anticompetitive behavior in the U.S. market.

Finally, AMD and NVIDIA have taken Intel to task over its refusal to release specifications on its open host controller for USB 3.0. Intel countered that it would provide the details once the spec is finished and that the company had invested “gazillions of dollars and bazillions of engineering man hours” in developing the open host controller.



Comments     Threshold


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

guuuuhhhhh
By BSMonitor on 6/17/2008 2:47:19 PM , Rating: 5
quote:
Intel and AMD have been fierce rivals for many years. Intel almost always had the upper hand over AMD until the launch of AMD's K8 architecture which saw the Sunnyvale, California-based company basking in the spotlight (and in enthusiast praise). Intel shoved AMD into the backseat with the launch of its Core architecture and AMD has been pretty much stuck in that position ever since.


Does every AMD/Intel article/blog have to start out with this crap? Can we just report the news? Please.




RE: guuuuhhhhh
By eye smite on 6/18/2008 2:53:54 PM , Rating: 2
I second the motion on dropping the drama and reporting the news only.


Intel FTC etc
By BruceLeet on 6/17/2008 2:44:16 PM , Rating: 1
Intel and AMD have both been in the news in recent weeks -- mostly for squabbles between the two companies. Intel recently got slapped with a $25M fine for anticompetitive practices in South Korea. Shortly after, the Federal Trade Commission opened up a formal investigation into allegations of anticompetitive behavior in the U.S. market.

A copy & paste of one of my older posts during Intel and AMDs race for the Ghz mark, this was posted on zdnet on March 8th 2000


Dell will begin taking orders on Wednesday for its Special Edition Dell Dimension, a high-end PC that it will sell in limited quantities with the Intel 1GHz chip.

"We are going to have a (Dimension) product," a Dell spokesman said. "However, we don't have a date yet." While dates are not final, it is likely that Dell will have its 1GHz Pentium III-based Dimension PC ready by the end of the month as well.


Intel product rebates incentive? its possible...

"We're supporting the 1GHz Pentium III," said a Hewlett-Packard spokeswoman

Alas...

The 1GHz Pentium III processor will cost $990 (£613) in 1,000-unit quantities, making it significantly less expensive than AMD's $1,299 (£805) 1GHz Athlon chip. The new Pentium III, which uses a 133MHz system bus, is available now in limited quantities, Intel officials said.

Since when has Intel ever had a lower priced product than AMD? Rebates? Also why would you sell a product you have limited quantities of for so little, unless they're ONLY buying YOUR product.




RE: Intel FTC etc
By FITCamaro on 6/17/2008 2:57:44 PM , Rating: 2
Intel's early dual cores were much cheaper than the Athlon X2s. But that was because the X2s were much faster.


RE: Intel FTC etc
By BruceLeet on 6/17/2008 3:30:36 PM , Rating: 1
But this is the beginning of the general timeline where AMD wants the FTC to look into.


It gets funnier
By Totally on 6/17/2008 1:52:36 PM , Rating: 2
“gazillions of dollars and bazillions of engineering man hours” that should be added, in it's entirety, in with the collection of quotes that appear at the bottom of the page.

Every time I picture a guy with a few degrees under his belt speak like a 7 year old, he might as well bust out with baby talk while he was at it.




Not including GPU.
By chippysteve on 6/17/2008 2:13:55 PM , Rating: 2
As far as I can see, you missed sometihing in your 'report.' This baby doesn't include any GPU so you'll need to add 3-4W for that too making it big, hot and power hungry comapared to Atom. It's something for cheap vista notebooks and high-end UMPCs but not for netbook or MID territory. I see it competing with VIA Nano.

Oh, by the way, http://www.EeePCNews.de were the ones to get the slides, not Hexxus.




By kilkennycat on 6/17/2008 5:04:22 PM , Rating: 2
It seems as if this discussion thread has forgotten the fully integrated nVidia Tegra series.............

http://www.nvidia.com/page/handheld.html




Nasty 1.5W
By jordanclock on 6/17/2008 5:36:00 PM , Rating: 2
Many people are pointing out that the performance of AMDs new CPU may negate the extra power draw, but I think you are all missing the point: When it comes to platforms like this, power usage is first priority. The AMD chip might be able to complete things faster, but for the kind of use such a platform would see (Streaming video or VoIP comes to mind.), you're looking at constant usage.

This kind of chip definitely has a place in ultra-lower power usage PCs, like the Eee Box. Something where the extra performance will be worth a couple of watts, but where the point of diminishing returns on performance is pretty low. The Eee Box demonstrated that the Atom is fine for such tasks, but there is still a lot of room for improvement. Improvement that AMD may be able to provide.




bias
By KinEnriquez on 6/18/2008 7:38:52 AM , Rating: 2
"Intel and AMD have been fierce rivals for many years. Intel almost always had the upper hand over AMD until the launch of AMD's K8 architecture which saw the Sunnyvale, California-based company basking in the spotlight (and in enthusiast praise). Intel shoved AMD into the backseat with the launch of its Core architecture and AMD has been pretty much stuck in that position ever since."

this is crap. why should the article even starts with this




I think we can see where this is going.
By MrBungle123 on 6/17/08, Rating: -1
RE: I think we can see where this is going.
By Natfly on 6/17/2008 1:36:06 PM , Rating: 5
Depends on how it performs, if it can do out of order execution combined with an IMC and other architectural superiorities, it might be worth the extra 1.5 watt TDP.


RE: I think we can see where this is going.
By System48 on 6/17/2008 1:41:04 PM , Rating: 3
The problem is with the way AMD has been performing lately. By the time they get this out the door they'll be competing against the next generation Atom, Lincroft, which will have an IMC and IGP.


RE: I think we can see where this is going.
By weskurtz0081 on 6/17/2008 1:43:51 PM , Rating: 2
This is yet to be seen. Since it seems like all they are doing is stripping K8, it might not take them too long. I guess we shall see.


RE: I think we can see where this is going.
By freaqie on 6/17/2008 2:15:53 PM , Rating: 2
amd already had the geode processors.
these were very energy efficient
and pretty fast ( basicly as fast as a 2100+ using ony a few watts) this is proably a relaunch with some added features


By Brandon Hill (blog) on 6/17/2008 2:34:26 PM , Rating: 3
IIRC, the Geode is derived from the original K7 architecture -- this appears to be K8-based.


By Regs on 6/17/2008 3:29:23 PM , Rating: 4
This is what I don't like. How AMD can develop something new, bring it to market, and some how before the product reaches the shelves it's branded a stripped down K8.

AMD comes out strong before a product launches, however when it launches or right before it launches, it's like the whole marketing team decides to take a vacation.

AMD has to sell these things like they have a actual purpose. Like true quad core and HT. What are their purpose? They sound sweet, but you forgot to sell me or show me the benifits. I can show people innovation all day long, like being able to brush me teeth with only one index finger, however I forgot to mention to them the purpose or even practicle sense of it.


RE: I think we can see where this is going.
By stryfe on 6/17/2008 4:46:47 PM , Rating: 1
The K8 is pretty much an optimized K7 plus IMC anyway.


RE: I think we can see where this is going.
By zpdixon on 6/18/2008 12:57:01 AM , Rating: 3
Are you kidding ? IMC, AMD64 (!), HyperTransport (!), SSE2, 3-way superscalar uarch, NX bit, etc. By far the biggest gap between the last 4 iterations (K6, K7, K8 and K10) is K7 -> K8.


RE: I think we can see where this is going.
By boogle on 6/18/08, Rating: 0
RE: I think we can see where this is going.
By zpdixon on 6/18/2008 7:07:03 AM , Rating: 3
Yes Intel did have problems efficiently implementing AMD64 in their CPUs. That's why the perf gap between Athlon 64/Opteron and P4/Xeon was even wider on 64-bit code than 32-bit. It took them 2 years to come up with a decent 64-bit microarch (Core).

HT is not "just a new transport protocol". HT + IMC forced AMD to add a XBAR, new cache coherency protocols, NUMA architecture, etc. Look at how many times Quickpath has been delayed. Even the mighty, big, rich Intel doesn't think it's easy to do.

SSE2: getting the specs is the easy part. Implementing the instructions efficiently is the hard part.

Nobody denies my basic point that K7-to-K8 was by far the biggest step in AMD's last 4 microarchs.


RE: I think we can see where this is going.
By boogle on 6/18/2008 8:10:55 AM , Rating: 2
No, the perf gap wasn't slightly wider because they had 'trouble', its because the arch was originally designed for 32bit. To put it in perspective AMD took years and years to make A64, Intel implemented EM64T in a matter of months. So the paths throughout the processor were all 32bit instead of 64bit (even now Phenom / Core 2 is still 32bit in places afaik). Even so the performance difference was relatively tiny, the bigger problem was P4 was just plain slower than A64.

Cache protocols have little to do with HT, and a LOT to do with multiple CPUs + cores. The Crossbar (XBAR) doesn't require HT either, that's another dualcore thing. NUMA *AGAIN* isn't to do with HT, its a multiple processor thing that happens to use HT because its the only communication method. HT is basically a link between the CPU and other CPUs, sound a bit like FSB?. The Crossbar means HT can be skipped entirely so direct core-core communication is possible. Incidentally NUMA is slower in desktop applications that not using NUMA at all, it benefits server apps almost exclusively.

Intel didn't need to worry about HT/QuickPath being out ASAP. Why? Because HT v1 is actually too slow on a multi-processor system using DDR2 memory, Intel's quad-FSB is actually faster. HT works at about 4GB/sec, DDR2 peaks at 10.6GB/sec (5.4GB practical): http://it.anandtech.com/IT/showdoc.aspx?i=3335&p=3

Implementing a more or less required feature (SSE2) from a 3rd party CPU shouldn't be considered a 'massive step', it should be called 'matching the competitor'.

quote:
Nobody denies my basic point that K7-to-K8 was by far the biggest step in AMD's last 4 microarchs.


Well, based on your lack of knowledge of AMD's actual internal architecture I would say you stumbled upon that 'fact' and luckily it pans out. But I would argue the first Athlon was the biggest jump AMD ever made. They went from making Intel clones / low performance CPUs to making their own CPUs that were faster & often cheaper than Intel's.


RE: I think we can see where this is going.
By zpdixon on 6/18/2008 3:56:58 PM , Rating: 2
"Intel implemented EM64T in a matter of months." Nope. June 2004: first x86-64 Intel CPUs. June 2006: first decent x86-64 implementation. As I said it took them 2 years to get it done correctly.

"The Crossbar (XBAR) doesn't require HT either, that's another dualcore thing.". Wrong. The XBAR was present even in single-core CPUs, like the first Opterons back in April 2003. The purpose of the XBAR is to link the core(s) to the IMC and HT links.

"Cache protocols have little to do with HT". Wrong. That's why there are 2 types of HT links: plain HT and HTcc specifically designed to run cache coherency protocols.

"Intel didn't need to worry about HT/QuickPath being out ASAP. Why? Because HT v1 is actually too slow on a multi-processor system using DDR2 memory". Wrong. It is common knowledge that FSB designs offer less combined bandwidth than socket-to-socket links. Even Intel implicitely admits it by the fact they have been forced to implement 4 independent FSBs on chipsets targetting the 4-socket market. Also FYI HT has long passed the 4 GB/s limit. CPUs have been shipping with HT links capable of 4.0 GT/s * 16 bits = 8 GB/s in both directions for at least 1.5+ years.

"Implementing a more or less required feature (SSE2) from a 3rd party CPU shouldn't be considered a 'massive step'". Yes it is ! No matter who invented SSE2, it was a massive step to implement it, both for Intel and AMD.

"Well, based on your lack of knowledge of AMD's actual internal architecture [...]". Based on the above factual errors, it sounds like you only have a vague understanding of K8...


By boogle on 6/21/2008 8:01:45 AM , Rating: 1
quote:
Nope. June 2004: first x86-64 Intel CPUs. June 2006: first decent x86-64 implementation. As I said it took them 2 years to get it done correctly.


All in your opinion. I can see no evidence that the implementation is different between P4 and Core2. Core2 is a lot faster sure, but the CPU itself is a lot faster. By your logic, because Core 2 is way faster than Phenom in 64bit apps, I could say the Phenom has a poor 64bit implementation.

quote:
"The Crossbar (XBAR) doesn't require HT either, that's another dualcore thing.". Wrong. The XBAR was present even in single-core CPUs, like the first Opterons back in April 2003. The purpose of the XBAR is to link the core(s) to the IMC and HT links.


So, still nothing to do with HT then, even in your own words. It avoids the HT link at all costs still, cores talk to each other, and the IMC needs a way of communicating with the CPU. Looks like a technical inevitability rather than a super-duper-amazing feature. I hook myself up to my keyboard, should I be considered an integral feature of computer design? Or is the keyboard just an interface?

quote:
"Cache protocols have little to do with HT". Wrong. That's why there are 2 types of HT links: plain HT and HTcc specifically designed to run cache coherency protocols.


I can't find a single reference to HTcc outside of this very post of yours. I would imagine AMD would have a strategy for managing cache coherency with multiple CPUs/cores, but that still doesn't require, or even need HTT. Intel would be stupid not to have their own strategy - and they're using FSB.

quote:
Yes it is ! No matter who invented SSE2, it was a massive step to implement it, both for Intel and AMD.


OK, I'll fall back to your x86-64 argument. Since Athlon64 didn't have 128bit FPUs, and took many more cycles to perform SSE2 instructions, A64's SSE2 implementation was so poor that they might as well have not bothered since standard 32bit instructions were barely any slower than grouping them up into 1 128bit vector.

I stand by my statement that HyperTransport is just an evolution of FSB, a strong optimisation of a bus that is required by any computer system in one shape or form. It's almost independent of the CPU and should be considered an advancement in platform design.


By stryfe on 6/18/2008 3:11:36 PM , Rating: 2
quote:
Nobody denies my basic point that K7-to-K8 was by far the biggest step in AMD's last 4 microarchs.
I would disagree. K6 -> K7 was the biggest jump. K7 was a brand new architecture from the ground up. As I said before K8 is an evolution of K7. Sure it has a bunch of new features but it's by no means a fresh architecture the way K7 was.


RE: I think we can see where this is going.
By phatboye on 6/17/2008 1:39:59 PM , Rating: 2
Not if you take into consideration the lackluster performance of the Atom processor at 1.6Ghz. You have to remember that in order for Intel to reach such low TWP Intel had give the chip an in-order pipeline which significantly impacts performance.

But I do think that if AMD wants to be taken seriously they will need to drop a lot lower than 8W.


By zpdixon on 6/18/2008 1:01:07 AM , Rating: 2
A lot more ? There is only a 1.5 W diff between Intel and AMD. And we know nothing about performance (AMD might turn out to be faster if they go out-of-order). It's way too early to speculate...


By weskurtz0081 on 6/17/2008 1:41:22 PM , Rating: 5
Yeah, I would expect a daily tech reader to understand that core frequency means very little. Think about it, Intel enjoyed a MUCH higher core clock with the P4 Prescott and Pentium D, yet those CPU's were thoroughly trounced by there K8 counterparts. The Pentium D's needed more than a 1Ghz advantage just to stay competitive.

As the other reader posted, Atom is also an In-Order executing CPU, while the AMD version appears to still be OoO, simply a stripped down version of K8. So, it is very possible that the AMD chip could outperform the Intel chip, giving it better performance per watt used even with the lower frequency.

It might be difficult to make up the frequency delta, but it's has been proven to be possible in the past, and this is no different.


RE: I think we can see where this is going.
By psychobriggsy on 6/17/2008 1:43:08 PM , Rating: 5
Oh, still using clock speed as a worthwhile metric are we?

What really matters with this product is:

1) cost of the platform (CPU + chipset)
2) size/area of the platform
3) typical platform usage power consumption
4) performance

AMD might do well on (1).

The CPU isn't as small as even the Diamondville Atoms however. Over 800 pins/balls for a single channel memory controller and one HT link? Weird.

Decent integrated graphics and hardware acceleration (video decode, etc) might allow the CPU to sleep more often, keeping the power consumption lower than the Atom which has to do a lot more on the CPU (for this revision). I presume it will be using some aggressive power saving tricks, but will it get down to 100mW at idle?

Performance should be more than adequate, I imagine it would run Aero without a problem. I hope that AMD are quite advanced with the product as well, this is no time to be announcing that you will be starting to think about the possibility of maybe doing something in this area.


RE: I think we can see where this is going.
By zpdixon on 6/18/2008 1:06:15 AM , Rating: 2
I think you got it wrong on point (2) :-) AMD has the advantage since Intel needs an extra chip: the northbridge.


RE: I think we can see where this is going.
By esgreat on 6/18/2008 1:32:12 AM , Rating: 2
I think you forgot that AMD needs an extra Southbridge AND a GPU. Intel's 2.5W+4W configuration is inclusive of memory controller, graphics, PCIe, USB, IDE.

Footprint
Atom area: 14mm x 13mm = 182mm2
SCH chipset: 22mm x 22mm = 484mm2
Total = 666mm2

AMD CPU: 27mm x 27mm = 729mm2

Intel's CPU+chipset footprint is smaller than just the AMD cpu! This isn't including AMD's southbridge and graphics.


RE: I think we can see where this is going.
By zpdixon on 6/18/2008 2:36:28 AM , Rating: 2
Actually we are both wrong.

Yes, AMD will need a southbridge, but it will most likely include a GPU, like their current AMD 700 series integrated graphics chipset family.

Also, the area you quote for the Atom is wrong. 182 mm² represents the die area, not the package area. The Atom Silverthorne µFCBGA package is 25 mm x 25 mm = 625 mm².

This gives:
- Intel: Atom 625 mm² + SCH 484 mm² = 1109 mm² .
- AMD: CPU 729 mm² + (southbridge+GPU) 300-500? mm² = 1029-1229? mm²

Looks like neither Intel nor AMD is going to have a significant space advantage.


RE: I think we can see where this is going.
By esgreat on 6/18/2008 4:12:41 AM , Rating: 2
Are you sure?

Take a look at Anand's report:
http://www.anandtech.com/cpuchipsets/intel/showdoc...

...the die size is only 25mm2. The package size is indeed 14mm x 13mm...and can be verified by comparing it with a penny.


By zpdixon on 6/18/2008 7:40:13 AM , Rating: 2
You and I are talking about different things:

- Atom 2xx series and N2xx series "Diamondville": package is 22 x 22 mm (not 25 x 25 as I claimed). Source:
http://download.intel.com/design/processor/designe...
- Atom Z5xx series "Silverthorne": package size is 13 x 14 mm.

As explained in the Dailytech article, the AMD CPU is designed to compete against Diamondville. So it doesn't make sense to compare it against Silverthorne.

However it also means that AMD will not, initially, attempts to compete against Silverthorne.

See also http://www.dailytech.com/Intel+Announces+Five+New+...


By esgreat on 6/18/2008 9:28:03 AM , Rating: 2
Thanks for clarifying. Yeah, Diamondville is larger. However your post specifically mentioned Atom Silverthorne, hence my reply. Should be a typo then :-).

Anyway, since point #2 was about size/form factor, you'll need to compare with the product that meets this criterion. Of course, I'm assuming that performance isn't so much of a concern in the very small form factor space.


By Brandon Hill (blog) on 6/17/2008 1:43:30 PM , Rating: 5
In most performance benches that I've seen around the web, a 1.6GHz Atom barely outpaces a ~1GHz Celeron M and in some cases is actually slower.

The main benefit of the Atom is the lower power requirements.


RE: I think we can see where this is going.
By weskurtz0081 on 6/17/2008 1:53:17 PM , Rating: 5
Also, keep in mind, the AMD cpu uses about 18% more power at load, but if it is 25% faster, it will use less power overall due to the fact that it completes the work much quicker.


RE: I think we can see where this is going.
By Klober on 6/17/2008 4:17:43 PM , Rating: 5
Exactly. I was just looking at some older benchmarks of how the K7 performed against the Dothan, and overall it was 5%-20% faster on average when equivalently clocked. Considering this is a K8 derivative we can probably expect better than that (how much is speculative, but then, isn't all of this right now?).

Also, another thought I had is that Intel's "TDP" is not the same as AMD's "TDP". As I remember, and correct me if I'm wrong, Intel's "TDP" is closer to average power draw whereas AMD's "TDP" is more like absolute maximum power draw. So, taking this into account, it's entirely possible the Atom's TDP of 6.5W is much closer to AMD's TDP of 8W.

Thoughts?


By HrilL on 6/17/2008 5:50:07 PM , Rating: 2
Your post is one of the best. It is very true. Intel and AMD's TDP are not the same and people reading these #'s and thinking AMD has already lost. First of all 6.5W verses 8W is not all that much and taking into account that Intel's TDP is the average power draw and AMD’s is Maximum then one would have to conclude that these two platforms will use about the same amount of power + or - 1W. And If AMD uses one of its superior IGPs it will surely smoke the Intel offering until Intel can get their next architecture out.


By raddude9 on 6/17/2008 2:44:27 PM , Rating: 3
Except that:
* the AMD chip includes the northbridge and memory controller on the chip whereas with the Atom this functionality is part of their lacklustre (currently at least) chipsets which neither perform very well or are particularly power efficient
* The 1.6Ghz Atom is frequently outrun by a 900Mhz Celeron!

I think AMD has a very good chance if they can pair this type of chip with a power-efficient 780G type chipset. Maybe that because I'm dying to play a modest game of Crysis on one of these machines though!


By omnicronx on 6/17/2008 2:48:37 PM , Rating: 4
I think the article should be a bit more clear in saying the Atom 2.5W plus the northbridge of 4w of the chipset takes 6.5W combined. Intel clearly states that the i945GSE takes 5.5W not 4 when taking the southbridge into account. AMDs rating will actually be higher than 8W when taking the southbridge into account. I assume it was said this way because the AMD chip has the onboard memory controller (i.e northbridge onboard) but its kind of confusing.

Just a note to the OP.. Intels celeron 220 (1.2GHZ) performs on par with the Atom 1.6 in multithreaded applications, and actually outperforms the atom in single threaded apps, thanks to the in-order-execution architecture of the Atom. In other words, if a 1ghz AMD chip can outperform a 1.6GHZ Intel chip, that 1.5W means little to nothing, as for Intel to scale the same as the AMD chip would require added power, which would at least equal if not go over and beyond AMDs rating.

The battle is far from over, it has really just begun..


"When an individual makes a copy of a song for himself, I suppose we can say he stole a song." -- Sony BMG attorney Jennifer Pariser














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