Congrats on the first post and yes, I agree, AMD is bringing some interesting new tech to the embedded market table. Intel's Atom is in dire need of competition in all of its market segments to encourage less blissfully stagnant development.
This: "AMD is putting up this solution against the Embedded Atom series models from Intel, promising better footprint (lesser number of balls to route)."
I like the idea of a better footprint, but if AMD is going to complete, they need to have as many balls as possible! More balls are better, I say!
This article reads like a commercial. Not what I've come to expect from Anandtech.
Also, isn't "APU" a marketing word for AMD's Fusion? In light of that, the way the article uses the word also adds to the feeling of it being more of a commercial than anything else.
It is always good to listen to user feedback. After all, AnandTech can't be where it is right now without its readers.
That said, I am sure AMD's 'commercial' wouldn't contain stuff like:
The embedded market space is dominated by SoCs based on RISC processors such as ARM and MIPS........x86 based solutions do not make the cut. x86, in particular, has been the dark horse due to the excessive power consumption for systems based on that architecture. Process shrinks have helped lower the power consumption numbers. However, we are still a few nodes away from when the x86 based solutions can really compete with RISC based solutions on the power front...
...However, we do have some concerns about the capability of the UVD engine in the platform. While the marketing slides indicated that Blu-Ray titles can be smoothly played back, it also had another entry indicating that 1080p video playback support availability was only in the 18W processors and higher....
...AMD doesn't really have any credible competitor to stand up against Intel SoCs such as the CE4100 / CE4200. We believe that the AMD APU would be a wonderful base for a SoC solution in that market segment. However, the additional Hudson hub makes it difficult to get small form factor systems...
I believe I have presented a balanced view of today's announcement.
Not all of it sounds like a commercial, but paragraphs like these don't really belong outside of a company press release:
"The APUs are ideal solutions for thin clients, medical imaging, point of sale and kiosk systems, gaming machines, digital signage and single board computing systems. They integrate a multi-core CPU and a GPU sub-system on the same die to give a general-purpose, programmable scalar and vector processor core with heterogeneous capabilities."
"AMD is showing a strong commitment to the x86 embedded market. The G-Series platform is the world’s first and only APU for embedded systems. Cutting-edge AMD Fusion technology brings a premier solution for a new generation of differentiated, small form factor embedded systems that consume less power, yet deliver improved performance and features, including an outstanding visual experience compared to other x86 based embedded systems."
I absolutely agree with Brunnis.Those two paragraphs he indicates sound like a press release, AND are somewhat in contradiction to your own criticisms of the parts above.
I like a little extra information in the read, I like having some background as to possible systems in mind. And I think I could learn to live with phrases like "ideal solutions" and "cutting-edge", even though they might be emotionally driven.
Keep in mind the share price keeps falling and AMD may not exist too much longer - that's not a good thing for anyone. Competition is a requirement.
I read the spreadsheet first before the article, and was thinking to myself, what exactly are they targeting here? Too much power for ultra-low power systems (microwaves, phones, routers), and they already have a line in place for netbooks/tablets.
Reading the first 'offending' paragraph put in perspective what they were shooting for. The second paragraph was a little less helpful, but AMD does need all the help it can get here.
I agree with you, I only scimmed cause it read so much like a commercial. Commercials aren't necessarily ALL positive. Mention pseudo negatives in an optimistic fashion to emphasize the positives; which is what this article is.
What a crock, this is complete BS. How are they going to call this a single chip integrated SoC when its clearly two chips, with Hudson using as much power as Brazos?
Embedded G-series my ass, integrate the damn controller hub already and stop calling the kit something its not.
yes, i fully agree with this comment; i'm very surprised to see so many superlative positives in an anandtech article, and approximately no fact to support them. It's not only that expectations are very high, with no benchmark / measurement to back them; it's also about the tone, a few sentences here look like a dictated press release. And maybe that's what it is.
Please look at my response to brunnis's post above.
I still believe that AMD may probably have a better case than the embedded Atom chipsets, but that is a joke because the embedded Atom itself is not a efficient product.
But, this product has quite a number of customers releasing production systems soon.. So, we will have to wait a bit to determine the market reaction to it.
AMD could have made more of a splash by releasing a proper SoC. Not sure whether that is slated for the future.
Fair enough, thanks for the response Ganesh. I would recommend a different lead sentence, as that really does sound like a press release and sets expectations for the whole article.
They have a revised architecture at 28nm in about a year's time. If they keep clock speeds as they are, that in itself should result in a good drop in power usage, not to mention the performance boosts usually associated with a revised architecture. I'm not sure they'll create a true SoC though, at least, not yet.
I'm very happy to see AMD's first Fusion product line being so widely touted for adoption. I can't wait to see how the C series compares to the E series in a full suite of benchmarks, especially considering the E series should hit a bandwidth wall at some point much sooner than the C series due to lower CPU and GPU clocks.
Yeah. But it has "no information" mostly because of all the leaks over the past 2 quarter mean that we "knew" it long before.
But agreed, this should have been a one-pager focused on confirming the OLD rumors and adding a _little_ bit of commentary to it. 1/2 the text is either spin or bloat.
This article will be top-of-the-line on NYT, but this site has a much more demanding and knowledgeable audience ...
Hey Anand, sucking on the wrong tit? I thought that Intel was the correct tit... Anyway, I guess that the way this thing is written just shows the laziness on your part guys. Too bad...
This is a 'News' piece, which means we try to convey what is in the press release, followed by presenting our analysis of the same. Please take a look at my reply to brunnis above.
In any case, please let me know if you want 'News' pieces to be presented in any other way.
Hey now, let's don't bring yammos into this. We should leave beautiful size F yammos right where they belong, on long narrow torsos. I hope May isn't reading this, hi honey!
I for one, am sick of hearing the word "Embedded". Seems like no one really has a clue to what embedded should mean. This new "class" of CPU's are nothing more than downscaled desktop counterparts. Integrated video? Big whoop, come again when you have integrated _everything_ into one SoC, including the southbridge. And don't come claiming embedded with a TDP of 18w. That's just grotesque. Anything above 1w of TDP is not embedded, and will probably require some sort of passive cooling at the least to survive industrial if not military embedded solutions. Calling them "netbook"-class or something alike is more useful. Embedded is just plain wrong.
Agree with you partially (refer to my conclusions, comparing with the CE4100) :)
But, Intel, VIA and AMD seem to have a different interpretation of 'Embedded' ..
Anyways, there are embedded applications like digital signage and point of sale systems which are almost PC-like in nature.. I think the x86 solutions are targeting that currently.. Also, embedded solutions have much longer support cycles compared to the traditional PC platform (The Geode is not going EOL until 2015, for example)... It is a matter of the company willing to support a product for an extended period of time too.
agreed, people basically use embedded to mean "not a pc", which is meaningless given the huge range of aplications in embedded. that being said, this processor does seem to be targeting certain areas of that huge embedded space that don't have the 1w tdp requirement. industrial and military are clearly not the focus here.
"This new "class" of CPU's are nothing more than downscaled desktop counterparts."
But... it's the same as the desktop equivalent.
I agree with the idea that it's hungrier than it should be for this sort of thing, however please bear in mind that it's not going to be drawing 18W constantly. Power gating and downclocking should ensure a far lower average usage.
Embedded is a form-factor matter. An embedded solution can also be a slave system. An example of embedded use for this would be automotive interface computers, like built in GPS or Media Players. Embedded basically means it is not used as a traditional computer.
After reading the comments I wanted to just say that there are some of us who did appreciate the article. I understand that you don't have a whole lot to go off of other than the Press Release so expecting many more details is a bit far fetched. I prefer some context to a Press Release as opposed to just the PR itself. As a student just starting a Computer Architecture course it's always exciting to what's new in the world, especially in embedded since that's the focus of the course. Anyways, thanks for the article, I look forward to reading more.
Article seems to lean toward AMD because of all the AMD's supplied pictures and you're talking about the potential of AMD's embedded product. I would like to point out that you did state negatives for AMD's in the embedded market. Just fyi on why people might think this is an AMD's PR. There is probably nothing you can do, other than maybe photoshop some funny cute cat pictures with AMD on it.
How come AMD and Intel are so behind in the embedded market? Is it because of their lack of interest until now and their non-existing technologies for low power chip? Their lack of IP's in technologies such as FPGA or whatever fancy do hicky? Is it because building cpu for the embedded systems require a different set of skills that AMD and Intel aren't well verse as ARM and MIPS? I guess, I don't understand how these major CPU company AMD and Intel cannot compete or beat ARM and MIPS. All they do is make CPU, well they're doing GPU now I guess, how can they not beat these smaller companies? Is the x86 ISA are too complex for embedded system? Doesn't make sense, I guess, since MIPS have 64bit.
"why can't ARM and MIPs compete with Intel and AMD in the desktop space?"
They can, and will. As has been reported even on this site, windows 8 will supposedly support ARM architecture. Time to buy ARM stock is now (well, ok, it was 18 months - 2 years ago, but still...).
ARM designs are not anywhere complex or large enough to run against big die processors. ARM is a good foundation but they do not have any designs that can compete with Nehalem or Stars. I would love to ARM's take on mainstream computing, and its support in Windows 8 is exciting to say the least.
Perhaps current ARM designs aren't, but remember that ARM is a RISC based processor. The reason Macs used to be so much better at Photoshop and movie editing was because RISC is a more efficient architecture than x86. That's ultimately why they are able to use less power now, each instruction is less work than it is on x86. At least that seems to be my vague memory from classes 10 years ago. It was something one of the professors would complain about on a regular basis.
If you have Windows 8 running on ARM and it is highly optimized for multi-core you could stack 16 Snapdragon cores (for example) into a single cpu and still use less power than most desktop CPUs currently use. All of these running at 1.5-2Ghz. That's an awful lot of processing power. This assumes that Windows 8 will be highly scalable to multiple cores which is likely a good assumption.
Most embedded devices do not have a display controller. At most, they will have a simple serial port that can be used to send text to a terminal. They do not require a great deal of processing power. Usually they need just enough cpu power to keep the I/O buffers filled. Thus they use ARM.
For some, the added convenience of being able to develop and execute code on the same platform vastly outweighs the cost of a display controller. I for one know it is a hell of a lot easier to write and debug code for an xp-embedded system than it is to code for some little piece of garbage that I might or might not have ever worked with and might or might not ever work with again! You can get a project done in half the time by using as much of your standard development platform as possible. And yes if necessary, later port it over to a more power efficent platform if the volume warrants it.
Yes, you are right that most embedded devices don't have a display controller such as a complex framebuffer with raster-ops etc. Most embedded devices reside in washers, elevators and buckedloads of stuff most of us take for granted. That's the core of embedded. But the analogy of using ARM devices are still just plain wrong. Look for example at the Cortex A9. SMP dual core, up to 2GHz class cpu's with up to 4M L2. Full display controller, security engines etc etc etc. They will still develop, in a normal configuration, their max performance within _MILLIWATT's_ of power envelope, typical PEAK. (something like 250-500mW perhaps). That's what will be residing in complex portable devices like whatever-pads and telephones. x86 in anything that has a week of uptime? Not as far as the current showings from AMD and Intel goes. Good luck integrating something with a fan in a ultrathin pad of some sort. x86 is still confined to rather large devices with large battery packs and abysmal uptime. That's why I don't like the frivolous use of "Embedded".
Just an addon. The Cortex A9 is a CPU complex. They are typically integrated as hard macros in a modern process with display controllers etc. It's not a SoC.
I am sorry , but this is not like the usual quality articles I always read on Anandtech , this just a regurgitation of marketing statements and flashy banners , The article added zero information to my knowledge which seemed very odd to me considering my solid experience with this site .
Worse , what's being presented in the article is not at all revolutionary , or even exciting , may be for some corporate folks , but not for the general population , the new platform delivers solid price/performance ratio for sure , however on the performance front and/or the power consumption front , it's nothing special .. Yet the way it is presented in the article may make it sound like the new "Core i7" .
Some of the paragraphs really shocked me , it made me wonder whether I am reading an article on a different "news" site , I know Anand and it's staff can do better than this , and I hope no to see this kind of press ever again on this well respected place .
This piece has been specifically categorized as a 'news piece', in which case we don't have any hardware to test out / characterized / determine performance or suitability for any particular application. As such, we can just do analysis of the press release provided to us with the information available at our disposal.
Please do keep a lookout for our reviews where you will find extensive analysis and performance testing of the gadgets / chips under the scanner.
Damn it was fast. It must be the synthesized methology working big time.
For me it just looks like the same stuff but with added integration - under the name embedded :), - but guess its what the OEMs wantet. Next is probably the southbridge :)
You write that the AMD APU may be competitive with the ARM solutions from a power perspective when it's built on a smaller node (I think you suggested a couple of generations from the current 40Nm) Is that comparing with ARM still built on the current node though? Wouldn't the inherent power efficiency of ARM processors mean that when built on similar node size, they would always be more power efficient?
The embedded market is huge. And it is not as concerned with power use as you might think. Atom with XP-embedded has made huge inroads. Brazos with 7-embedded could do even more. They have to get this out there in as many segments as possible so that people can start developing unique APU code. There are some very niche functions in the embedded world that could be done much faster with SIMD arrays. AMD needs to get that 100th monkey effect as quickly as possible.
"In the meanwhile, solutions like what we are seeing from AMD today integrate premium graphics capabilities within power envelops similar to what --x86-- used to consume in the previous generation."
Should that read
"In the meanwhile, solutions like what we are seeing from AMD today integrate premium graphics capabilities within power envelops similar to what --RISC-- used to consume in the previous generation."
Ok, it's a news piece - but that doesn't fully mitigated the quality concerns about the article.
The problem is that it was an unorganized and unprecise mixing of the PR and the editorial parts (fine if done well), and was disconcerting to read at a site where the bar is set very high on content.
We don't expect things to follow some kind of exact journalistic rules (I don't even know the those rules), but as a regular reader you could just tell it felt wrong and I was already scratching my head on the first page even before reading the other comments.
There are no hard feelings - as others have pointed out it has to be difficult to write for a site like AT especially when there is such an active community.
I think the message to AT is simple: Ganesh seems like a smart guy with some good insights, let's just try and help him take things up a notch.
It would certainly be nice... but given x86 fabrication it'll be a hit or miss with power consumption. I wouldn't want to have an AMD-powered tablet PC or smartphone only run for a record 30 minutes before shutting itself off. :-D
Whenever there is an article with even minimal emotion or preference put it into it by the author, he/she will be considered as a PR, followed by warfare among fanboys from different fractions.
Surprised at all the comments offended that this isn't written as a review. This is a news item regarding a press release, of course it's going to read differently then a review. Commentary is sound, these products are being introduced to compete with the Atom embedded product line with a bit of a question mark about how much market share this AMD higher performing two chip solution will grab.
I think it'd be overly power hungry, slow, and powerful.
I think digicams use digital signal processors, that are generally smaller and have much less instruction sets, def not x86. I think Canon makes its own (DIGIC), but there are other third party vendors. Again, I think TI would be useful in those as well.
And all you're doing here is hijack AMD articles without providing a counterpoint. Please refrain from making comments unless you can contribute to the discussion.
I must say that "AMDiot" doesn't roll off the tongue very well. :/ You need to work out a better one!
All I have to say is that *if* someone does not like the content. . . then they do not need to read it. Personally, I could have got by with a simple data sheet. But you know what ? I did not write the article ! So I take the content as it was given. Seriously, I doubt 1/10th the comment's on this article were written by people who even understand what embedded truly means. Having delusions of grandeur that they will be running COD4 on this platform someday . . .
From a Point of sales standpoint however. I am not completely convinced this is necessary. Unless you think a cashier would better serve us better by staring at a pretty AERO desktop instead of checking the customer out at the check stand. Perhaps self check out(but that really is just a KIOSK). Medical imaging . . . again not completely convinced for multiple reasons. A handheld battery powered gaming platform - Yes. Assuming power consumption could be kept low enough. Thin client ? Yes. KIOSK ? Yes.
With all of the above said. I am still very sad for the industry. It is very obvious to me that the technology companies are having a hard time thinking out side of the box. Otherwise we might have desktop systems that use laptop technology. Instead of requiring a small nuclear power plant to power a moderate sized LAN party. We could have very powerful desktops that sip power. In this persons eyes, the technology companies are going about things wrong.
Perhaps it would behoove AMD to parter with ARM if they truly care about power consumption in the embedded market.
I liked the article, but your point "All I have to say is that *if* someone does not like the content. . . then they do not need to read it." does not make sense. How are you to know what the article is or sounds like unless you've already read it?
"Otherwise we might have desktop systems that use laptop technology." Ummm... why? (1)You could just use your laptop (2) There are already motherboards available for desktops that can use laptop procs. What laptop technology are you referring to?
"We could have very powerful desktops that sip power." That's the way things are headed. Why not just underclock your components if you're that cautious?
A user needs a certain amount of CPU/GPU performance to perform certain computational tasks. This person may, or may not need a huge screen to perform these tasks. Yet still may need enough performance to get the desired results in a timely fashion.
Why must this user pay a ridiculous power bill on top of having to buy the expensive, and possibly proprietary hardware? A laptop GPU for a very simple example, can use far less power, and offer 50%-75% the performance, At all but the highest resolutions, that performance difference will pale in comparison to the power used to achieve the end goal.
To be sure, gaming as an application could fit real well into this category. But gaming is not the only application that can make very good use of this type of hardware. Image manipulation, video/audio editing/encoding, medium duty servers, development systems, multi function larger embedded systems, etc. All of these could greatly benefit on multiple levels by using this type of hardware( and the list goes on).
1) Laptops -> notoriously inflexible. 2) Motherboards you suggest -> also inflexible. Unless, perhaps the end user is not forced into using a desktop classed power hog of a graphics card. Perhaps single or multiple MXM card slots could be implemented.
Again, the technology is already there. Why not use it ? Reinventing the wheel in the shape of a triangle just does not seem to be working well for the industry . . .
"I liked the article, but your point "All I have to say is that *if* someone does not like the content. . . then they do not need to read it." does not make sense. How are you to know what the article is or sounds like unless you've already read it?"
It makes perfect sense. Unless you're the type who needs to be handheld every step of your life. I am sure you have more than 3 braincells to rub together . . . just be careful you do not start a fire.
Simply put, in terms perhaps you can now understand. *You* did not pay to view the content. *You* did not write the content. If *you* do not like it. That is your problem. Keep it to yourself. If it is really that much of a problem for *you*. email the author and complain to him in private. You could even be constructive, and give him a step by step why *you* do not like it.
Now, because I feel you wont get this, since I have had to hold your hand a couple of times already. "*You*" meaning anyone who feels compelled to complain about the article.
intel leads the x86 architectures and sales. And if AMD keep on thinking out of box like this one, so it might put a challenge for intel and then where dramas start. And of course creativity and technology bloom.
I wonder what took so long for AMD to get into the embedded market as trying to compete with Intel on x86 front seemed kind of foolhardy. Well anyway, go AMD!
As much as custom PC builders hate to admit that APUs will be the next great thing, playback of 1080p content doesn't really take much GPU power. Not until deep color ranges (32bit+) become popular will it make a difference. Besides, a small chipset that's fully capable of accelerated displays and computational procedures as well is already being used by several devices on the market and will continue to grow rapidly with handhelds (IE: smartphones) finally becoming mainstream.
AMD is making the right decision here, albeit late. :P
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
76 Comments
Back to Article
pinki - Wednesday, January 19, 2011 - link
omg go AMDSkribbel - Wednesday, January 19, 2011 - link
Congrats on the first post and yes, I agree, AMD is bringing some interesting new tech to the embedded market table. Intel's Atom is in dire need of competition in all of its market segments to encourage less blissfully stagnant development.This: "AMD is putting up this solution against the Embedded Atom series models from Intel, promising better footprint (lesser number of balls to route)."
I like the idea of a better footprint, but if AMD is going to complete, they need to have as many balls as possible! More balls are better, I say!
MeanBruce - Wednesday, January 19, 2011 - link
Tell him what he's won Bob!First poster should receive a $20 gift card/code from Newegg! ;)
Brunnis - Wednesday, January 19, 2011 - link
This article reads like a commercial. Not what I've come to expect from Anandtech.Also, isn't "APU" a marketing word for AMD's Fusion? In light of that, the way the article uses the word also adds to the feeling of it being more of a commercial than anything else.
ganeshts - Wednesday, January 19, 2011 - link
It is always good to listen to user feedback. After all, AnandTech can't be where it is right now without its readers.That said, I am sure AMD's 'commercial' wouldn't contain stuff like:
I believe I have presented a balanced view of today's announcement.
Brunnis - Wednesday, January 19, 2011 - link
Not all of it sounds like a commercial, but paragraphs like these don't really belong outside of a company press release:"The APUs are ideal solutions for thin clients, medical imaging, point of sale and kiosk systems, gaming machines, digital signage and single board computing systems. They integrate a multi-core CPU and a GPU sub-system on the same die to give a general-purpose, programmable scalar and vector processor core with heterogeneous capabilities."
"AMD is showing a strong commitment to the x86 embedded market. The G-Series platform is the world’s first and only APU for embedded systems. Cutting-edge AMD Fusion technology brings a premier solution for a new generation of differentiated, small form factor embedded systems that consume less power, yet deliver improved performance and features, including an outstanding visual experience compared to other x86 based embedded systems."
ganeshts - Wednesday, January 19, 2011 - link
Thanks for pointing out the 'offending' content. Let me edit it to convey the points succintly.FATCamaro - Wednesday, January 19, 2011 - link
I absolutely agree with Brunnis.Those two paragraphs he indicates sound like a press release, AND are somewhat in contradiction to your own criticisms of the parts above.vol7ron - Wednesday, January 19, 2011 - link
I don't agree absolutely :)I like a little extra information in the read, I like having some background as to possible systems in mind. And I think I could learn to live with phrases like "ideal solutions" and "cutting-edge", even though they might be emotionally driven.
Keep in mind the share price keeps falling and AMD may not exist too much longer - that's not a good thing for anyone. Competition is a requirement.
HibyPrime1 - Wednesday, January 19, 2011 - link
I gotta agree with vol7ron here.I read the spreadsheet first before the article, and was thinking to myself, what exactly are they targeting here? Too much power for ultra-low power systems (microwaves, phones, routers), and they already have a line in place for netbooks/tablets.
Reading the first 'offending' paragraph put in perspective what they were shooting for. The second paragraph was a little less helpful, but AMD does need all the help it can get here.
iamezza - Friday, January 21, 2011 - link
+1knedle - Wednesday, January 19, 2011 - link
I think this article should be read not as commercial, but more like "OMG, finally AMD is making a comeback!"Hrel - Wednesday, January 19, 2011 - link
I agree with you, I only scimmed cause it read so much like a commercial. Commercials aren't necessarily ALL positive. Mention pseudo negatives in an optimistic fashion to emphasize the positives; which is what this article is.Samus - Thursday, January 20, 2011 - link
What a crock, this is complete BS. How are they going to call this a single chip integrated SoC when its clearly two chips, with Hudson using as much power as Brazos?Embedded G-series my ass, integrate the damn controller hub already and stop calling the kit something its not.
Tractor - Friday, January 21, 2011 - link
yes, i fully agree with this comment; i'm very surprised to see so many superlative positives in an anandtech article, and approximately no fact to support them.It's not only that expectations are very high, with no benchmark / measurement to back them; it's also about the tone, a few sentences here look like a dictated press release.
And maybe that's what it is.
kfiske - Wednesday, January 19, 2011 - link
This has to be a joke. It has no information and reads like an AMD pr release.pk05 - Wednesday, January 19, 2011 - link
No it doesn't...press releases are shorter and less hyperbolic.ganeshts - Wednesday, January 19, 2011 - link
Please look at my response to brunnis's post above.I still believe that AMD may probably have a better case than the embedded Atom chipsets, but that is a joke because the embedded Atom itself is not a efficient product.
But, this product has quite a number of customers releasing production systems soon.. So, we will have to wait a bit to determine the market reaction to it.
AMD could have made more of a splash by releasing a proper SoC. Not sure whether that is slated for the future.
pk05 - Wednesday, January 19, 2011 - link
Fair enough, thanks for the response Ganesh. I would recommend a different lead sentence, as that really does sound like a press release and sets expectations for the whole article.silverblue - Wednesday, January 19, 2011 - link
They have a revised architecture at 28nm in about a year's time. If they keep clock speeds as they are, that in itself should result in a good drop in power usage, not to mention the performance boosts usually associated with a revised architecture. I'm not sure they'll create a true SoC though, at least, not yet.I'm very happy to see AMD's first Fusion product line being so widely touted for adoption. I can't wait to see how the C series compares to the E series in a full suite of benchmarks, especially considering the E series should hit a bandwidth wall at some point much sooner than the C series due to lower CPU and GPU clocks.
ninjaquick - Wednesday, January 19, 2011 - link
Yeah, I'm personally curious to see what nvidia cooks up with ION+ARM.mino - Wednesday, January 19, 2011 - link
Yeah. But it has "no information" mostly because of all the leaks over the past 2 quarter mean that we "knew" it long before.But agreed, this should have been a one-pager focused on confirming the OLD rumors and adding a _little_ bit of commentary to it. 1/2 the text is either spin or bloat.
This article will be top-of-the-line on NYT, but this site has a much more demanding and knowledgeable audience ...
wolfman3k5 - Wednesday, January 19, 2011 - link
Hey Anand, sucking on the wrong tit? I thought that Intel was the correct tit... Anyway, I guess that the way this thing is written just shows the laziness on your part guys. Too bad...ganeshts - Wednesday, January 19, 2011 - link
This is a 'News' piece, which means we try to convey what is in the press release, followed by presenting our analysis of the same. Please take a look at my reply to brunnis above.In any case, please let me know if you want 'News' pieces to be presented in any other way.
MeanBruce - Wednesday, January 19, 2011 - link
Hey now, let's don't bring yammos into this. We should leave beautiful size F yammos right where they belong, on long narrow torsos. I hope May isn't reading this, hi honey!AssBall - Wednesday, January 19, 2011 - link
I thought Wolfman only injected his trolling nonsense on Intel articles.wolfman3k5 - Wednesday, January 19, 2011 - link
Good Job! Looks like you're catching on. And by the way, I love yammos! Big ones on long narrow torsos!Jesus, some of you take everything to seriously! Just like a bunch of geeks and neerds! Get a life for God's sake!
milkylainen - Wednesday, January 19, 2011 - link
I for one, am sick of hearing the word "Embedded". Seems like no one really has a clue to what embedded should mean.This new "class" of CPU's are nothing more than downscaled desktop counterparts.
Integrated video? Big whoop, come again when you have integrated _everything_ into one SoC, including the southbridge.
And don't come claiming embedded with a TDP of 18w. That's just grotesque.
Anything above 1w of TDP is not embedded, and will probably require some sort of passive cooling at the least to survive industrial if not military embedded solutions.
Calling them "netbook"-class or something alike is more useful. Embedded is just plain wrong.
ganeshts - Wednesday, January 19, 2011 - link
Agree with you partially (refer to my conclusions, comparing with the CE4100) :)But, Intel, VIA and AMD seem to have a different interpretation of 'Embedded' ..
Anyways, there are embedded applications like digital signage and point of sale systems which are almost PC-like in nature.. I think the x86 solutions are targeting that currently.. Also, embedded solutions have much longer support cycles compared to the traditional PC platform (The Geode is not going EOL until 2015, for example)... It is a matter of the company willing to support a product for an extended period of time too.
pk05 - Wednesday, January 19, 2011 - link
agreed, people basically use embedded to mean "not a pc", which is meaningless given the huge range of aplications in embedded. that being said, this processor does seem to be targeting certain areas of that huge embedded space that don't have the 1w tdp requirement. industrial and military are clearly not the focus here.semo - Wednesday, January 19, 2011 - link
I think that Intel use the term to describe CPUs with extended support too. Yep, lost all meaning as far as I'm concernedint9 - Wednesday, January 19, 2011 - link
The T40N and the T44R are 9W but substantially weaker. This seems like another blow against Atom. I can't wait to see what that GPU will do.silverblue - Wednesday, January 19, 2011 - link
"This new "class" of CPU's are nothing more than downscaled desktop counterparts."But... it's the same as the desktop equivalent.
I agree with the idea that it's hungrier than it should be for this sort of thing, however please bear in mind that it's not going to be drawing 18W constantly. Power gating and downclocking should ensure a far lower average usage.
ninjaquick - Wednesday, January 19, 2011 - link
Embedded is a form-factor matter. An embedded solution can also be a slave system. An example of embedded use for this would be automotive interface computers, like built in GPS or Media Players. Embedded basically means it is not used as a traditional computer.driscoll42 - Wednesday, January 19, 2011 - link
After reading the comments I wanted to just say that there are some of us who did appreciate the article. I understand that you don't have a whole lot to go off of other than the Press Release so expecting many more details is a bit far fetched. I prefer some context to a Press Release as opposed to just the PR itself. As a student just starting a Computer Architecture course it's always exciting to what's new in the world, especially in embedded since that's the focus of the course. Anyways, thanks for the article, I look forward to reading more.digitalzombie - Wednesday, January 19, 2011 - link
Article seems to lean toward AMD because of all the AMD's supplied pictures and you're talking about the potential of AMD's embedded product. I would like to point out that you did state negatives for AMD's in the embedded market. Just fyi on why people might think this is an AMD's PR. There is probably nothing you can do, other than maybe photoshop some funny cute cat pictures with AMD on it.How come AMD and Intel are so behind in the embedded market? Is it because of their lack of interest until now and their non-existing technologies for low power chip? Their lack of IP's in technologies such as FPGA or whatever fancy do hicky? Is it because building cpu for the embedded systems require a different set of skills that AMD and Intel aren't well verse as ARM and MIPS? I guess, I don't understand how these major CPU company AMD and Intel cannot compete or beat ARM and MIPS. All they do is make CPU, well they're doing GPU now I guess, how can they not beat these smaller companies? Is the x86 ISA are too complex for embedded system? Doesn't make sense, I guess, since MIPS have 64bit.
silverblue - Wednesday, January 19, 2011 - link
That's almost like asking "why can't ARM and MIPs compete with Intel and AMD in the desktop space?". I don't know... that's just the way I see it.If these are the same as the other Fusion processors, they'll fully support the x86-64 architecture. Oddly enough, they also support AMD-V... :)
Sufo - Wednesday, January 19, 2011 - link
"why can't ARM and MIPs compete with Intel and AMD in the desktop space?"They can, and will. As has been reported even on this site, windows 8 will supposedly support ARM architecture. Time to buy ARM stock is now (well, ok, it was 18 months - 2 years ago, but still...).
ninjaquick - Wednesday, January 19, 2011 - link
ARM designs are not anywhere complex or large enough to run against big die processors. ARM is a good foundation but they do not have any designs that can compete with Nehalem or Stars. I would love to ARM's take on mainstream computing, and its support in Windows 8 is exciting to say the least.LiquidLearner - Wednesday, January 19, 2011 - link
Perhaps current ARM designs aren't, but remember that ARM is a RISC based processor. The reason Macs used to be so much better at Photoshop and movie editing was because RISC is a more efficient architecture than x86. That's ultimately why they are able to use less power now, each instruction is less work than it is on x86. At least that seems to be my vague memory from classes 10 years ago. It was something one of the professors would complain about on a regular basis.If you have Windows 8 running on ARM and it is highly optimized for multi-core you could stack 16 Snapdragon cores (for example) into a single cpu and still use less power than most desktop CPUs currently use. All of these running at 1.5-2Ghz. That's an awful lot of processing power. This assumes that Windows 8 will be highly scalable to multiple cores which is likely a good assumption.
Shadowmaster625 - Wednesday, January 19, 2011 - link
Most embedded devices do not have a display controller. At most, they will have a simple serial port that can be used to send text to a terminal. They do not require a great deal of processing power. Usually they need just enough cpu power to keep the I/O buffers filled. Thus they use ARM.For some, the added convenience of being able to develop and execute code on the same platform vastly outweighs the cost of a display controller. I for one know it is a hell of a lot easier to write and debug code for an xp-embedded system than it is to code for some little piece of garbage that I might or might not have ever worked with and might or might not ever work with again! You can get a project done in half the time by using as much of your standard development platform as possible. And yes if necessary, later port it over to a more power efficent platform if the volume warrants it.
milkylainen - Wednesday, January 19, 2011 - link
Yes, you are right that most embedded devices don't have a display controller such as a complex framebuffer with raster-ops etc. Most embedded devices reside in washers, elevators and buckedloads of stuff most of us take for granted. That's the core of embedded. But the analogy of using ARM devices are still just plain wrong. Look for example at the Cortex A9. SMP dual core, up to 2GHz class cpu's with up to 4M L2. Full display controller, security engines etc etc etc.They will still develop, in a normal configuration, their max performance within _MILLIWATT's_ of power envelope, typical PEAK. (something like 250-500mW perhaps). That's what will be residing in complex portable devices like whatever-pads and telephones. x86 in anything that has a week of uptime? Not as far as the current showings from AMD and Intel goes.
Good luck integrating something with a fan in a ultrathin pad of some sort.
x86 is still confined to rather large devices with large battery packs and abysmal uptime. That's why I don't like the frivolous use of "Embedded".
milkylainen - Wednesday, January 19, 2011 - link
Just an addon. The Cortex A9 is a CPU complex. They are typically integrated as hard macros in a modern process with display controllers etc. It's not a SoC.Muhammed - Wednesday, January 19, 2011 - link
I am sorry , but this is not like the usual quality articles I always read on Anandtech , this just a regurgitation of marketing statements and flashy banners , The article added zero information to my knowledge which seemed very odd to me considering my solid experience with this site .Worse , what's being presented in the article is not at all revolutionary , or even exciting , may be for some corporate folks , but not for the general population , the new platform delivers solid price/performance ratio for sure , however on the performance front and/or the power consumption front , it's nothing special .. Yet the way it is presented in the article may make it sound like the new "Core i7" .
Some of the paragraphs really shocked me , it made me wonder whether I am reading an article on a different "news" site , I know Anand and it's staff can do better than this , and I hope no to see this kind of press ever again on this well respected place .
ganeshts - Wednesday, January 19, 2011 - link
This piece has been specifically categorized as a 'news piece', in which case we don't have any hardware to test out / characterized / determine performance or suitability for any particular application. As such, we can just do analysis of the press release provided to us with the information available at our disposal.Please do keep a lookout for our reviews where you will find extensive analysis and performance testing of the gadgets / chips under the scanner.
krumme - Wednesday, January 19, 2011 - link
Damn it was fast. It must be the synthesized methology working big time.For me it just looks like the same stuff but with added integration - under the name embedded :), - but guess its what the OEMs wantet. Next is probably the southbridge :)
zodiacfml - Wednesday, January 19, 2011 - link
........ go AMD!!! :pblowfish - Wednesday, January 19, 2011 - link
You write that the AMD APU may be competitive with the ARM solutions from a power perspective when it's built on a smaller node (I think you suggested a couple of generations from the current 40Nm) Is that comparing with ARM still built on the current node though? Wouldn't the inherent power efficiency of ARM processors mean that when built on similar node size, they would always be more power efficient?Shadowmaster625 - Wednesday, January 19, 2011 - link
The embedded market is huge. And it is not as concerned with power use as you might think. Atom with XP-embedded has made huge inroads. Brazos with 7-embedded could do even more. They have to get this out there in as many segments as possible so that people can start developing unique APU code. There are some very niche functions in the embedded world that could be done much faster with SIMD arrays. AMD needs to get that 100th monkey effect as quickly as possible.SlyNine - Wednesday, January 19, 2011 - link
"In the meanwhile, solutions like what we are seeing from AMD today integrate premium graphics capabilities within power envelops similar to what --x86-- used to consume in the previous generation."Should that read
"In the meanwhile, solutions like what we are seeing from AMD today integrate premium graphics capabilities within power envelops similar to what --RISC-- used to consume in the previous generation."
JarredWalton - Wednesday, January 19, 2011 - link
I believe the point is that you now get CPU + GPU within the same power envelope that used to be just the CPU. I've clarified that in the text.SlyNine - Wednesday, January 19, 2011 - link
Got it. Thanksextide - Wednesday, January 19, 2011 - link
Did anyone else come in here expecting to see benchmarks vs Atom?...JarredWalton - Wednesday, January 19, 2011 - link
Hint: "News" generally means "no significant benchmarks".ninjaquick - Wednesday, January 19, 2011 - link
Like +100ldman - Wednesday, January 19, 2011 - link
It really doesn't sound like a commercial . Sounds like the writer is excited about new technology...Isn't that why we're here?
I mean if you were just reading for the business/tech aspect, get a data sheet and get back to work.
LTG - Wednesday, January 19, 2011 - link
Ok, it's a news piece - but that doesn't fully mitigated the quality concerns about the article.The problem is that it was an unorganized and unprecise mixing of the PR and the editorial parts (fine if done well), and was disconcerting to read at a site where the bar is set very high on content.
We don't expect things to follow some kind of exact journalistic rules (I don't even know the those rules), but as a regular reader you could just tell it felt wrong and I was already scratching my head on the first page even before reading the other comments.
There are no hard feelings - as others have pointed out it has to be difficult to write for a site like AT especially when there is such an active community.
I think the message to AT is simple: Ganesh seems like a smart guy with some good insights, let's just try and help him take things up a notch.
Onslaught2k3 - Wednesday, January 19, 2011 - link
It would certainly be nice... but given x86 fabrication it'll be a hit or miss with power consumption. I wouldn't want to have an AMD-powered tablet PC or smartphone only run for a record 30 minutes before shutting itself off. :-Dnitrousoxide - Wednesday, January 19, 2011 - link
Whenever there is an article with even minimal emotion or preference put it into it by the author, he/she will be considered as a PR, followed by warfare among fanboys from different fractions.MeanBruce - Wednesday, January 19, 2011 - link
He meant to say "factions". Don't ya just hate people from different fractions? Go AMD!, Go Intel! Go everybody!nitrousoxide - Wednesday, January 19, 2011 - link
Such stupid typo >.<MeanBruce - Wednesday, January 19, 2011 - link
Happens to all of us ;)Vesku - Wednesday, January 19, 2011 - link
Surprised at all the comments offended that this isn't written as a review. This is a news item regarding a press release, of course it's going to read differently then a review. Commentary is sound, these products are being introduced to compete with the Atom embedded product line with a bit of a question mark about how much market share this AMD higher performing two chip solution will grab.jido - Thursday, January 20, 2011 - link
Is that the kind of processor we can find in a digicam or is it too power-hungry for that?vol7ron - Thursday, January 20, 2011 - link
I think it'd be overly power hungry, slow, and powerful.I think digicams use digital signal processors, that are generally smaller and have much less instruction sets, def not x86. I think Canon makes its own (DIGIC), but there are other third party vendors. Again, I think TI would be useful in those as well.
silverblue - Thursday, January 20, 2011 - link
And all you're doing here is hijack AMD articles without providing a counterpoint. Please refrain from making comments unless you can contribute to the discussion.I must say that "AMDiot" doesn't roll off the tongue very well. :/ You need to work out a better one!
yyrkoon - Thursday, January 20, 2011 - link
Do not despair in the face of nay-sayers Ganesh.All I have to say is that *if* someone does not like the content. . . then they do not need to read it. Personally, I could have got by with a simple data sheet. But you know what ? I did not write the article ! So I take the content as it was given. Seriously, I doubt 1/10th the comment's on this article were written by people who even understand what embedded truly means. Having delusions of grandeur that they will be running COD4 on this platform someday . . .
From a Point of sales standpoint however. I am not completely convinced this is necessary. Unless you think a cashier would better serve us better by staring at a pretty AERO desktop instead of checking the customer out at the check stand. Perhaps self check out(but that really is just a KIOSK). Medical imaging . . . again not completely convinced for multiple reasons. A handheld battery powered gaming platform - Yes. Assuming power consumption could be kept low enough. Thin client ? Yes. KIOSK ? Yes.
With all of the above said. I am still very sad for the industry. It is very obvious to me that the technology companies are having a hard time thinking out side of the box. Otherwise we might have desktop systems that use laptop technology. Instead of requiring a small nuclear power plant to power a moderate sized LAN party. We could have very powerful desktops that sip power. In this persons eyes, the technology companies are going about things wrong.
Perhaps it would behoove AMD to parter with ARM if they truly care about power consumption in the embedded market.
vol7ron - Thursday, January 20, 2011 - link
I liked the article, but your point "All I have to say is that *if* someone does not like the content. . . then they do not need to read it." does not make sense. How are you to know what the article is or sounds like unless you've already read it?"Otherwise we might have desktop systems that use laptop technology."
Ummm... why? (1)You could just use your laptop (2) There are already motherboards available for desktops that can use laptop procs. What laptop technology are you referring to?
"We could have very powerful desktops that sip power."
That's the way things are headed. Why not just underclock your components if you're that cautious?
yyrkoon - Thursday, January 20, 2011 - link
Key words; Flexibility, and cost..Example scenario:
A user needs a certain amount of CPU/GPU performance to perform certain computational tasks. This person may, or may not need a huge screen to perform these tasks. Yet still may need enough performance to get the desired results in a timely fashion.
Why must this user pay a ridiculous power bill on top of having to buy the expensive, and possibly proprietary hardware? A laptop GPU for a very simple example, can use far less power, and offer 50%-75% the performance, At all but the highest resolutions, that performance difference will pale in comparison to the power used to achieve the end goal.
To be sure, gaming as an application could fit real well into this category. But gaming is not the only application that can make very good use of this type of hardware. Image manipulation, video/audio editing/encoding, medium duty servers, development systems, multi function larger embedded systems, etc. All of these could greatly benefit on multiple levels by using this type of hardware( and the list goes on).
1) Laptops -> notoriously inflexible.
2) Motherboards you suggest -> also inflexible. Unless, perhaps the end user is not forced into using a desktop classed power hog of a graphics card. Perhaps single or multiple MXM card slots could be implemented.
Again, the technology is already there. Why not use it ? Reinventing the wheel in the shape of a triangle just does not seem to be working well for the industry . . .
yyrkoon - Thursday, January 20, 2011 - link
Also . . ."I liked the article, but your point "All I have to say is that *if* someone does not like the content. . . then they do not need to read it." does not make sense. How are you to know what the article is or sounds like unless you've already read it?"
It makes perfect sense. Unless you're the type who needs to be handheld every step of your life. I am sure you have more than 3 braincells to rub together . . . just be careful you do not start a fire.
Simply put, in terms perhaps you can now understand. *You* did not pay to view the content. *You* did not write the content. If *you* do not like it. That is your problem. Keep it to yourself. If it is really that much of a problem for *you*. email the author and complain to him in private. You could even be constructive, and give him a step by step why *you* do not like it.
Now, because I feel you wont get this, since I have had to hold your hand a couple of times already. "*You*" meaning anyone who feels compelled to complain about the article.
Apply said "idea" to my post while you're at it.
Shadowmaster625 - Thursday, January 20, 2011 - link
http://grab.by/8tvwI'm not an artist but I just couldnt resist pitting a bulldozer against a "sandy bridge". What kind of dumb name is a sandy bridge anyway?
AMDer - Saturday, January 22, 2011 - link
HiyaI work in AMD and truthfully the commitment and enthusiasm is great in bringing out world class products.. Thanks for the wonderful APUs my dear AMD
hd10 - Saturday, January 22, 2011 - link
intel leads the x86 architectures and sales. And if AMD keep on thinking out of box like this one, so it might put a challenge for intel and then where dramas start. And of course creativity and technology bloom.0ldman - Monday, January 24, 2011 - link
Isn't your name the same as the download file for Sisoft Sandra benchmark from like 7 years ago?You can't come up with anything but fanboy drivel or an original forum name?
Sam125 - Monday, January 24, 2011 - link
I wonder what took so long for AMD to get into the embedded market as trying to compete with Intel on x86 front seemed kind of foolhardy. Well anyway, go AMD!pandemonium - Tuesday, February 1, 2011 - link
As much as custom PC builders hate to admit that APUs will be the next great thing, playback of 1080p content doesn't really take much GPU power. Not until deep color ranges (32bit+) become popular will it make a difference. Besides, a small chipset that's fully capable of accelerated displays and computational procedures as well is already being used by several devices on the market and will continue to grow rapidly with handhelds (IE: smartphones) finally becoming mainstream.AMD is making the right decision here, albeit late. :P