Slashdot Mirror


AMD Says It's 'Ambidextrous,' Hints It May Offer ARM Chips

J. Dzhugashvili writes "Today at its Financial Analyst Day, AMD made statements that strongly suggest it plans to offer ARM-based chips alongside its x86 CPUs and APUs. According to coverage of the event, top executives including CEO Rory Read talked up an 'ambidextrous' approach to instruction-set architectures. One executive went even further: 'She said AMD will not be "religious" about architectures and touted AMD's "flexibility" as one of its key strategic advantages for the future.' The roadmaps the execs showed focused on x86 offerings, but it seems AMD is overtly setting the stage for a collaboration with ARM."

140 comments

  1. let's hope that... by w.hamra1987 · · Score: 1, Interesting

    this means less intel in the market and more AMD!!!!

    though seriously, how good is the ARM architecture today? havent tried it yet, does it provide comparable performance to an intel processor of similar price tag?

    --
    my sig pwns your sig
    1. Re:let's hope that... by the+linux+geek · · Score: 4, Informative

      It's a tough question. The Intel Atom has an edge on ARM, but it's not a big one, and while a high-performance ARM chip costs below $20, the Atom is significantly more. On the other hand, right now there are no ARM implementations that are really competitive on the PC front, and probably won't be until ARMv8 (64-bit) chips, or at least until Cortex-A15. A15 chips will probably come out in late 2012 and be a bit faster than the Atom, but a long way from Sandy Bridge and the other current Intel designs.

    2. Re:let's hope that... by stms · · Score: 1

      I am not an expert but from what I hear ARM has much more speed per dollar. Though ARM can't match x86 in parallelism.

    3. Re:let's hope that... by migla · · Score: 1

      this means less intel in the market and more AMD!!!!

      though seriously, how good is the ARM architecture today? havent tried it yet, does it provide comparable performance to an intel processor of similar price tag?

      The appeal of ARM is not measured in performance/$, it's about flipflops/wigwam.

      --
      Some of my favourite people are from th US; Vonnegut, Chomsky, Bill Hicks.
    4. Re:let's hope that... by Anonymous Coward · · Score: 5, Interesting

      Its also worth noting that ARM has never been about performance until the semi-recent smart phone (mobile computing) surge. And even today, performance takes a backseat to power consumption. And it is here where ARM has always led the way. ARM vs Intel, ARM provides better price, better consumption, and very competative performance, albeit second place. But given the market to whch ARM is primarily focused on, ARM easily scores the win; in spite of Intels best efforts.

      For those doing more traditional embedded development, Intel's offers are likely front runners. For those participating in the mobile computer segment, ARM, by far, is the very clear winner.

    5. Re:let's hope that... by Guspaz · · Score: 5, Informative

      The price tag is directly comparable, because ARM doesn't make processors, they sell licenses to designs. The only relevant metric is really performance at a given power point.

      The closest competitor is Intel's Atom chips. At comparable power points, the current ARM chips seem to substantially outperform Atom chips, and the ARM chips scale far lower than Intel's do. It becomes a bit murkier at higher power levels, since until recently nobody was really making ARM chips that high, but we'll see a lot more competition in this field in the future with the ARM Cortex A15, which is intended to be a lot more scalable. The current design is planned to go from 1.0GHz single-core, up to 2.5GHz eight-core, depending on what the integrator wants. On top of that, they've got the new Cortex A7 that they've designed as an ultra-lower performance chip, which is intended to be a much simpler architecture that's still ISA-compatible with the A15. The intention is actually to put an A7 and A15 in the same SoC, so that the SoC can entirely turn off the A15 cores when only low performance is needed (like playing audio or video, since that's done almost entirely on a DSP). This is similar to what nVidia did with the Tegra 3, just taken even farther.

    6. Re:let's hope that... by Andy+Dodd · · Score: 3, Informative

      Much of this is a change of focus... Instead of beefy desktop CPUs running bloated OS, the focus is becoming more on portable devices.

      Basically, this is "We're hanging in there in the desktop/laptop market, but rather than hang on to our piece of a shrinking pie, we want to get in on the pie that's getting bigger".

      ARM is superior in low-power applications. It's highest-end CPUs maybe match Intel Atom, but often have far more peripherals (such as a fairly decent GPU and 1080p multi-format video decoding all on a tiny chip about the size of your thumbnail. Seriously - I can almost completely cover an OMAP4 with my thumb.)

      --
      retrorocket.o not found, launch anyway?
    7. Re:let's hope that... by hitmark · · Score: 2

      Seems some are working on bringing ARM into the server rack, and we can see the reason when we read about the kinds of power and cooling issues there are around some of the larger server farms.

      --
      comment first, facts later. http://chem.tufts.edu/AnswersInScience/RelativityofWrong.htm
    8. Re:let's hope that... by nschubach · · Score: 2

      I never understood why file servers didn't use low power processors. Recently we've seen more and more ARM NAS devices, but I figured FTP servers and such would use these "lower end" processors simply because they only need to perform minimal computation to validate users and serve files.

      --
      Every time I start to have faith in humanity, I ruin it by driving to work between 7 and 8 am.
    9. Re:let's hope that... by Anonymous Coward · · Score: 2, Informative

      Its also worth noting that ARM has never been about performance until the semi-recent smart phone (mobile computing) surge. And even today, performance takes a backseat to power consumption.

      It was a long time ago, but not "never", when ARM was about performance and running circles around the 80286 and 68000 CPUs.

    10. Re:let's hope that... by hairyfeet · · Score: 4, Insightful

      The problem with ARM is there are literally millions of x86 programs that have become an integral part of peoples lives, this is also why even though Linux has been getting better each year it fails to find any real gains. Everything from that camera that came with the photo software your Aunt Sue loves to Corel and Photoshop, from that bain of Linux geeks MS Office to Quickbooks/Quicken which is God in small business and rightly so.

      The reason ARM is able to gain so much in mobile is because frankly geeks have never understood how normal users think, as someone who has to understand their needs or go out of business i think i can shed some light. you see to a geek that Droid or iPhone is a general computing device, to a normal user it doesn't even have an OS, its just "A screen with buttons i can google and play games on that I'll chunk when the contract is up" and that's it. they have been conditioned that nothing is compatible so assume when they chunk the phone the only thing they'll keep is the SIM card and that's that. Creates a lot of waste but is great for the carrier. Tablets to the consumer is the same, its a large mostly disposable flatscreen TV that can let them Google. There is no real attachment there, no real desire by the majority to develop long term rapport with programs. this is why ARM netbooks went nowhere because to them a netbook is NOT just a general computing device, its a "baby laptop that should do everything my big laptop does only slower, because babies are smaller than grownups" see how that works?

      I think where AMD is on the right track and has a real shot is Fusion. Not 3 years ago i could walk into the local Walmart or staples and i'd be lucky if there was a single AMD machine, usually the cheapest machine in the house. Now I see AMD Fusion netbooks, laptops, all in ones, and even desktops, some going up to nearly $1000 in price and talking to some of the guys that i know working there they are brisk sellers. More and more the PC is not only the office machine, its also an entertainment center With the AMD Fusion chips not only do you get great battery life/lower electric bills, like my EEE E350 that gets 6 hours playing 720p and lets me HDMI into any 1080p set and watch videos, but you also get to have all your programs that you know and are familiar with and which frankly there is often no FOSS equivalent and probably never will be. There is no FOSS software that matches the features of Quickbooks or photoshop, and certainly nothing like the little quilting app I installed the other day for a customer on her new Acer AMD C60 netbook. while FOSS users would probably think its stupid and not waste time for her its a "must have" because it helps her to work up the patterns she is gonna use on her next quilt and to visualize what it will look like.

      So I think the future is bright IF, and that's a BIG IF, AMD continues to play it smart. the new Vector based GPUs will lower the power footprint even lower while letting the APU use the GPU cores like a super fast floating point which will give any program using floating point a nice kick in the ass, and considering they've had to lower desktop output to keep up with all the orders for the Bobcat chips shows the OEMs think its the right path too. you can now get those chips in every form factor you can name, from HTPC to iMac style to netbooks and laptops. While i'm sure AMD never considered it a desktop chip the OEMs found that its more than good enough for the average user and its selling quite briskly so they made a good call there.

      Finally there is one place where AMD has already fucked up, and that's the recent killing of the entire AM3 line. While consolidating to a few chips would have been smart IMHO killing the AM3 Stars chips when Bulldozer has neither the yields nor performance to take its place was just stupid. if you have an AM3 board I'd suggest you pop over to tigerdirect where they are selling Thu

      --
      ACs don't waste your time replying, your posts are never seen by me.
    11. Re:let's hope that... by LWATCDR · · Score: 4, Insightful

      "The problem with ARM is there are literally millions of x86 programs that have become an integral part of peoples lives"
      Not really. There are many ARM programs that have become and integral part of people lives. Android and IOS are two big example not to mention the apps that run on them.
      Software is not as locked to an ISA as it once was. Microsoft and Apple have shown that with the move of Windows to ARM and the move of OS/X to x86.
      Applications are not written in assembly anymore they are written in C++ or another high level language. Take your example of Photoshop? Moving Photoshop from Windows to Windows on ARM is probably a much simpler project a Windows and OS/X version. The same is true of Office.

      I do think that AMDs Fusion is interesting but your reasoning on why people will keep use the x86 is not valid. They will only keep using x86 for as long as that is the best solution. IMHO x86 is endanger of being the next PDP-11 or VAX unless it can scale down to mobile and fast.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    12. Re:let's hope that... by Nursie · · Score: 1

      The problem with ARM is there are literally millions of x86 programs that have become an integral part of peoples lives, this is also why even though Linux has been getting better each year it fails to find any real gains.

      I'll just stop you there.

      The problem with ARM is that it's not x86.
      Yet Linux is x86 and it's not making any gains.

      I think you might be trying to say that anything that's not Windows on x86 is going to be a failure?

      I wonder, do you have the same attitude to Windows 8's much touted ARM version?

    13. Re:let's hope that... by WaywardGeek · · Score: 0

      First of all, Atom has an edge? Really? My dual-core ARM smart-phone has more juice than my Atom based netbook. What I've been wondering for about 15 years is why the heck doesn't Intel buy Arm? It's the no-brainer way to protect your #1 status - buy out all competitors that show any signs of being a threat -- and do it before they're big enough to attract any anti-trust scrutiny. Intel is at least 10 years over due here. Are they being incredibly super stupid, or was there any valid reason ARM is still independent? ARM has been the biggest threat to Intel for many years. What's up?

      --
      Celebrate failure, and then learn from it - Nolan Bushnell
    14. Re:let's hope that... by the+linux+geek · · Score: 2

      Published benchmarks disagree with your assessment of ARM.

    15. Re:let's hope that... by Anonymous Coward · · Score: 0

      > What I've been wondering for about 15 years is why the heck doesn't Intel buy Arm?

      Because ARM doesn't want to be bought.

      Intel can offer all the money in its coffers, and a lot more, but the ARM executives can simply say "no thank you".

    16. Re:let's hope that... by ppanon · · Score: 2

      Well there's always encryption, but they could probably integrate an on-chip co-proc for those functions.

      --
      Laissez lire, et laissez danser; ces deux amusements ne feront jamais de mal au monde. - Voltaire
    17. Re:let's hope that... by evilviper · · Score: 1

      I figured FTP servers and such would use these "lower end" processors simply because they only need to perform minimal computation to validate users and serve files.

      ARM NAS boxes are a nightmare. Slow as all hell. That's not the kind of performance you want from your FTP server. And FTP servers have generally been replaced by HTTP servers, and a lot of dynamic pages which use up lots of CPU time. But even if that wasn't the case, it's only in Windows that there's a drive to single-task. On any Unix server, you'd just keep throwing more functions on the box if it has spare resources. No reason your FTP server can't be doing the job of SMTP server, running spamassassin, etc.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    18. Re:let's hope that... by Anonymous Coward · · Score: 1

      They tend to save from wrong place. The 400mhz arm9 cpu in my lspro could easily saturate gigabit link, but it won't because of the interrupt overhead. Tweaking it to use jumbo frames boosts throughput fivefold, but the rest of my network doesn't work well with those.

    19. Re:let's hope that... by evilviper · · Score: 2

      What I've been wondering for about 15 years is why the heck doesn't Intel buy Arm? It's the no-brainer way to protect your #1 status - buy out all competitors that show any signs of being a threat

      First off, Intel was selling ARM chips up until a few years ago. They snagged the famous "StrongArm" series off of DEC and rebranded it "XScale".

      Second, ARM only recently established itself as THE x86 competitor. Go look up all the RISC architectures out there which were competing for dominance. If you needed high performance embedded, PowerPC has long been the way to go. SPARC has been competing in the embedded space. Hitachi made a go of it with their SuperH chips (eg. SH3).

      Last but not least, MIPS is the old man of the bunch, and the one with the most fight left in it... It was always faster than ARM, even powering high-end (SGI) workstations and supercomputers in the past, while still competitive on the low-end. With China throwing it's weight behind MIPS as the basis of their domestic CPU development effort (Loongsoon/Dragon Chip), it's both advancing nicely, and being produced extremely inexpensively, which gives us things like the infamous $100 ICS Android tablet running on MIPS.

      But more than that, ARM doesn't fit Intel's model... ARM just licenses the IP/Cores, and let's others fab them. Intel wants the whole pie. Even if they bought ARM, they couldn't stop existing licensees from continuing as before, and if they didn't keep ARM producing what customers wanted, switching over to MIPS wouldn't be that hard.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    20. Re:let's hope that... by hairyfeet · · Score: 0

      Actually i think Win 8 ARM, aka WinTab, is gonna be such a huge fucking flop it will finally put the MSFT Bob jokes to rest. The reason Linux isn't gaining is because it doesn't have the apps number one, and number two frankly the geeks refuse to make it a user friendly OS. Tell me where are the find drivers and rollback drivers buttons? oh right they don't exist even though MSFT had those 12 years ago. A single button push equivalent to last known good config in case that upgrade craps on my system? oh yeah that don't exist either.

      Linux is ONLY good for programmers and those that have the skills to do systemic step by step troubleshooting of highly complex systems, which just eliminated a good 99% of the population. I have tried over a dozen "user friendly distros" here at the shop, and with both LTS to LTS and regular to regular Linux frankly sucks ass when it comes to not shitting on its own drivers. kinda sad when i was told "Oh you have to do a completely clean install" which when I started trying Linux in 04 was something they used to make fun of MSFT for, but at least you get a decade of updates with each MSFT OS, well except for Vista but that thing bombed and most abandoned it like WinME.

      But it might surprise you that despite many of the FOSSies, which is a name I use to separate the zealots from the normal Linux users which are actually sane and decent folk, claims that I "must be an M$ Ninja!" that i think Windows 8, both in x86 AND ARM variants, is gonna bomb so badly it'll make WinVista look like Win95. Its a cell phone GUI designed for touch screens which 99% of the machines simply won't have due to the high cost of touch screens. i mean when you can get a 24 inch LCD for less than $150 but a 17 inch touch enabled costs over $300? Touch support for desktops and laptops simply won't be there. And WinARM will bomb because number one, OEMs can have Android for free, and number two the most important reason you have a version of Windows that WON'T RUN WINDOWS PROGRAMS so it'll just cause confusion and have a shitload of tablets being returned and sold for a loss. Funnily enough I think the Linux guys will be the big buyers of Win 8 ARM, because once all those tablets hit the market at TouchPad pricing because of the returns I'm sure the linux guys will figure out how to boot them off of SDHC and they'll be the new TouchPad playtoy for geeks.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    21. Re:let's hope that... by unixisc · · Score: 2

      I agree w/ this. ARM is an overcrowded market already, and why would someone prefer AMD to an established vendor who's been making it for years, such as TI, Qualcomm, nVidia, Freescale - just about every other big name in the semiconductor industry? Why would anyone prefer AMD to those guys? AMD did a good thing when it first went to the x64, and they can make that a more RISCy CPU over time when memory is never less than 4GB, there are 64-bit versions of most apps and then they can start dropping 32-bit instructions from future implementations.

      Otherwise, there is no reason why a particular instruction set by itself will make a CPU consume less power (beyond the traditional RISC vs CISC argument). So AMD needs to play to its strengths, which is the x64. Any Android vendor can already buy chips from the vendors I listed above, so why go to AMD? But if AMD makes an x86/x64 chip that's low power enough, it can potentially help save Microsoft's Windows 8 tablets from becoming a debacle, which again I agree w/ the other observation above that it will.

    22. Re:let's hope that... by Nursie · · Score: 2

      I can't say I've seen the driver issues you talk about.

      Things tend (for me) to either work in linux, because the driver is supplied as a kernel module, or there's just no driver. In fact, for me, it's now considerably easier than windows. You don't even have to think about installing or rolling back drivers, because they're either just there already, or not available.

      That's just me though, and what you're used to is a large part of it. I certainly do fall into the 1% here though.

      Was 2004 the last time you tried linux?

      I didn't really start using it seriously until about '06.

    23. Re:let's hope that... by unixisc · · Score: 1

      Actually, I think that AMD is the only company that can save Windows 8 by providing something like a mobile APU for the platforms - both cell phones & tablets. That's the only way people would have even a prayer of running their existing Wintel apps on Windows 8. And I think you are right about your last point - just like Silicon Graphics once made a MIPS based workstation for NT, but later, sold it only w/ Irix b'cos NT did a piss poor job supporting RISC, similarly, the Nokia Lumias and others will end up w/ their phones running Android or WebOS (the latter at least being more open than Android)

    24. Re:let's hope that... by bWareiWare.co.uk · · Score: 1

      Antitrust legislation (and rightly so).

    25. Re:let's hope that... by unixisc · · Score: 1

      ARM has only been dominant in this low end, portable market. Otherwise, they've never been in the big leagues of performance, alongside x64, POWER, MIPS, Sparc and even Itanium. Not to mention that Intel doing this would just re-invite anti-trust regulators that used to investigate Intel in the past.

    26. Re:let's hope that... by Anonymous Coward · · Score: 0

      Applications are not written in assembly anymore they are written in C++ or another high level language. Take your example of Photoshop? Moving Photoshop from Windows to Windows on ARM is probably a much simpler project a Windows and OS/X version. The same is true of Office.

      If only it were that easy. Chances are that unless it was written with portability in mind then it will be a nightmare to port from x86 to ARM. Heck, I would even go as far as to say that it would be easier to port to OSX/Linux then to another architecture.

    27. Re:let's hope that... by hairyfeet · · Score: 0

      Is 6 months ago new enough for you? i tried going LTS to LTS just to shut up a "If you use LTS that won't happen!" irritant on LinuxInsider and watched as PulseAudio puked on the sound and the graphics wouldn't go native resolution without needing....drumroll...CLI to fix!

      I need to write down a list sometime of all the different versions i've tried, last count I was into double digits and frankly Linux just don't upgrade worth a crap. personally i blame Linus who is so damned arrogant he thinks he's smarter than the devs of BSD, Solaris, eComstation, OSX, and Windows because he seems to think he don't need a stable ABI for drivers...WRONG. Sure if you know the make/model/rev of EVERY piece of hardware you own AND have the ability to tweak some "fix" because it was written for Rev B firmware C and you have Rev F firmware H then you can fix it, but again you've just eliminated a good 99% of the planet. if you'd like I can give you the link to LinuxInsider where an actual Linux server admin with many years of administration has given up on Linux and is going BSD because when she upgraded OpenSUSE it puked and left her without a working machine at home for a week and wasted two years worth of emails. Sure she had backups but the point is if even SHE can't make Linux do an in place upgrade without borkage, what chance does Suzy the checkout girl who barely knows how to turn on a PC gonna have?

      The answer is none and THAT is the problem. Perhaps you'd like to read an article I wrote back in 2009 pointing out what I needed to sell Linux to consumers and SMBs. Also note that not a single idea, all of which were basic common sense stuff, has been implemented in any Linux distro that i know of. Now I'm just a humble retailer I don't have several million to throw at the problem like Shuttleworth, all I can do is point out on forums what is wrong and hope somebody listens. instead i either get accused of being an M$ ninja or get told "Go back to winblowz Winfag". so don't be surprised when Linux goes exactly nowhere on the desktop. we retailers have done everything short of handing you a map and a GPS unit and all we've gotten for our troubles is insulted or ignored. But when people would rather risk pirating the other guy's OS than take your 100% free one its time to ask yourself a fundamental question: "What is the other guy doing right that I'm doing wrong?" and I've laid out in that article several examples which sadly nobody will heed.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    28. Re:let's hope that... by hairyfeet · · Score: 1

      Ultimately it comes down to a hard fact of life MSFT doesn't want to accept, which is this: If you aren't running Windows applications frankly there is NO point in running Windows! Its the x86 ecosystem that gives MSFT its power and that's exactly what they do NOT have on ARM. Why would an OEM pay MSFT for an OS when they can have Android or WebOS for absolutely free? Without Windows apps to bring in the value add frankly the answer is no reason at all. Add to that the win 8 GUI is touchscreen only for the most part, if you've tried the dev preview (which i urge everyone to do, words and pics just don't describe the horror) then you'll know that without touch frankly its painful. Even the gal doing product plugs on yahoo, who is always a bubbly 'Buy it! Buy it now!" kinda shill says 'Wait until you buy a touch screen device with Windows 8" because even she admitted that while win 8 will work without touch, frankly it wasn't nice to use.

      As for AMD I'd argue that they can do that NOW without wasting huge bucks on ARM, and that is with Brazos. They already have the C series down to less than 8w and the E series which frankly as someone who owns an E350 is pretty powerful down to a MAX of 18w and most of the time is less than 10w and that is on a 40nm fab. Even if they didn't change a thing just the power they'd save by going to 32nm which IIRC TSMC already has up and running they'd easily get it into phone and tablet range and 22nm will make it competitive with most smart phones with ARM easily. again that's if they don't change a thing but in point of fact AMD is about to switch the GPU component to a vector based instead of its current VLIW which will add up to some pretty significant savings on power, while allowing the GPU to behave like a super floating point when not gaming. this would allow them to probably halve the amount of FP units while still being more powerful than current offerings.

      So I'd argue frankly that AMD doesn't need ARM and would be stupid to waste money in such a crowded space chasing fads. As I said the only thing I would do different from their current roadmap is bring back AM3 since GloFlo was producing pretty significant yields on Thuban and simply turn off cores to cover the Phenom/Athlon spaces. This with the C/E series and Bulldozer would give them more of a top to bottom approach and then i would phase out Thuban when Piledriver comes out if they get the performance problems licked. Because as it is now frankly my 95w Thuban can spank the top of the line Bulldozer yet cost nearly 40% cheaper than a BD based setup. Because of the lower yields honestly BD simply isn't a competitive chip and unless you are a diehard AMD fan it would simply be pointless to go BD over Sandy/Ivybridge as BD gets too close to Intel's lower end chips that spank BD. thuban and Phenom/Athlon at least gave them something competitive due to the lower price which gave excellent bang for the buck. But other than this i think AMD should simply stay the course, fix the design on BD, and crank out Brazos while getting Brazos II with the vector GPU out the door ASAP. The Brazos II I'm willing to bet my last buck will be low enough power one could put it in any device you'd like and still get decent battery life. WinARM is honestly an abortion, its an OS looking for an audience that simply isn't there, and the Win 8 touch UI required to make that abortion will sink Win 8 as an OS just like the bloat sank Vista.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    29. Re:let's hope that... by jcdr · · Score: 1

      A few moths ago, I have compared a ARM Cortex-A8 and a Atom N450 running the same Linux application using OpenCV to process images. I was surprised that the speed was about the same if I reduce the processing to a single thread and set the two processors at the same clock frequency. This show that the architecture, while very different, yield about the same processing speed. The Atom N450 still have dual cores and higher clock clock capability that explain a higher power drain if fully used.

      Probably, ARM and X86 will not produce so different results for a given power envelope and manufacturing process. Compilers and kernels largely reduce the architecture difference from a user point of view. A the end, this is just a new competition, and this is generally good for the end users.

    30. Re:let's hope that... by visualight · · Score: 3, Interesting

      I told you already, Debian is the best at updates even across multiple versions. Also, OpenSuse and Fedora are where experiments happen and I doubt an "experienced Linux Admin" would be using them for something really important -unless she has the requisite depth to deal with a little breakage during an upgrade.

      And posting again and again and again the same rant about an ABI isn't going to change the FACT that a stable ABI for drivers would make things worse for everyone. You keep trying to make comparisons to Windows in areas where it makes no sense at all to compare the two.

      What's it going to take for you to realize that nobody cares if Linux gains market share on the desktop? You're making arguments (for years now) based the assumption that market share is a goal when in fact no one has such a goal.

      Your perspective on this is so wrong and you've been corrected so many times by so many people I can't help but wonder if you've got some kind of learning disability or OCD or something. Seriously, not trying to be insulting at all. You've apparently started down this road in 2004 with some wrong assumptions that you just can't let go of, and that's really why you're so frustrated now.

      --
      Samsung took back my unlocked bootloader because Google wants me to rent movies. They're both evil.
    31. Re:let's hope that... by kelemvor4 · · Score: 1

      this means less intel in the market and more AMD!!!!

      though seriously, how good is the ARM architecture today? havent tried it yet, does it provide comparable performance to an intel processor of similar price tag?

      To answer you directly, no. Not even close. I've read a few articles where folks are hopeful AMD could try to change that. Time will tell, I suppose.

    32. Re:let's hope that... by UnknowingFool · · Score: 1

      For mobile, power consumption has been more of the deciding factor than performance. Atom runs about 3W while ARM can vary from 0.1 to 2W. Also ARM is a little more customizable to companies. With Atom you get something less powerful but more power efficient than a laptop Intel CPU but it's a general purpose CPU. With ARM you get a very power efficient chip than can be varied to suit your needs more.

      --
      Well, there's spam egg sausage and spam, that's not got much spam in it.
    33. Re:let's hope that... by hairyfeet · · Score: 1

      Then please tell everyone who says that "Linux is ready for the desktop!" shit to STFU, will you? Oh and tried Debian, puked on wireless, next? Sadly you are using a classic meme called use distro X. Oh and stable ABI? Your argument has its own meme too. BTW, just FYI, but the ONLY thing you will find written against a stable ABI is a RELIGIOUS RANT by one of the kernel devs that goes so far as to say 'I hope that those that have non free drivers have their systems broken often!" now does that sound like an OS developer, or someone punishing the unbelievers of their God? sounds like the latter to me.

      But you can't eat your cake and have it too, if you truly don't care then state right here that Linux isn't ready for the masses and i'll be happy to link to your post when we get the annual "Year of the Linux desktop!" meme.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    34. Re:let's hope that... by Dog-Cow · · Score: 1

      x86/x64 will rule in desktops and servers for the foreseeable future. They are not in danger of obsolescence at this time. Despite a desire, Intel has never been in the mobile market, and while it's a lost opportunity, it's not as if they've been squeezed out -- they were never there.

    35. Re:let's hope that... by Svartalf · · Score: 1

      Heh... Clock to clock, they're neck and neck right at the moment with the A9. Remind yourself that most of the A9 devices are clocked 1.0-1.2 GHz where the Atoms are all clocked at 1.6-1.8 GHz. There's your speed difference. Power consumption...heh...they're not comparable right now. ARM consumes quite a bit less at comparable clocks to the Atoms. And the A15 changes the name of the game. It kind of pastes the current and the claimed next generation of Atoms in overall performance- and it still keeps the rough power advantage.

      Intel doesn't have an edge on ARM right at the moment except at the mid to high-end. And soon, the mid-end is going to be encroached upon by them.

      --
      I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    36. Re:let's hope that... by Dog-Cow · · Score: 1

      Linus is arrogant, and honest enough to tell you that himself.

      But he has never said that Linux doesn't need a stable driver ABI. He's only said that he doesn't give a shit about anyone who can't write a driver without one. His stance has always been that drivers in the kernel tree are updated for free as the ABI changes, and that drivers outside the tree are not his problem. He is not wrong at all.

      Linux is the fastest growing OS (server, mobile, set-top) in the world. Obviously the idea that Linux needs a stable ABI is completely and utterly wrong.

    37. Re:let's hope that... by Svartalf · · Score: 1

      The problem with ARM is there are literally millions of x86 programs that have become an integral part of peoples lives, this is also why even though Linux has been getting better each year it fails to find any real gains. Everything from that camera that came with the photo software your Aunt Sue loves to Corel and Photoshop, from that bain of Linux geeks MS Office to Quickbooks/Quicken which is God in small business and rightly so.

      Really? Millions? You know, using hyperbole is all well and good, but outright exaggeration never wins you arguments.

      There's maybe several HUNDRED that people rely upon that you can buy right now. If it's not on Windows7, OSX, or Linux, it's liable to be an unsupported piece of software- and at some point they're NOT going to be able to continue to run it- so it DOES NOT COUNT if it's one of those. For the rest, if it's on Windows7 there's a possibility that the vendor will make a Win8 ARM version. OSX is probably out of the question. Linux...heh...most everything that is built for X86 can be built for ARM with minimal or no effort whatsoever. (I contend that if they can't do it, they need to re-think their software or find a new line of business...but that's MNSHO.)

      And, this doesn't get into iOS and Android- along with a host of other up-and-coming answers on ARM.

      Keep kidding yourself. CPU matters less these days and as the old apps no longer are supported, the users will go looking for other answers to their problems- which will free them up considerably from that base world you talk to.

      --
      I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    38. Re:let's hope that... by Guspaz · · Score: 1

      That was supposed to be "the price tag ISN'T directly comparable"

    39. Re:let's hope that... by swilly · · Score: 1

      "Finally, Linux is ready for the desktop" is almost always said in a sarcastic fashion. It's a joke, and has been for quite some time. It's great for workstations, but it's been a while since a significant number of people believed that Linux could overtake even the Mac for desktop marketshare.

      Personally, I use Linux and Solaris for servers and workstations at work, Linux for my home server, and Windows for my desktop and my laptop. If I didn't want to play games, then I would consider replacing my Windows boxes with Macs (which I almost did last time I bought a laptop). Use the best tool for the job, and all that.

    40. Re:let's hope that... by magnusk · · Score: 1

      Its also worth noting that ARM has never been about performance

      Performance was exactly the reason the ARM architecture was created in the first place. Acorn's engineers determined that the performance of existing and announced architectures (from Intel, Motorola, etc.) was insufficient, so they needed to create a new one. e.g. http://www.ot1.com/arm/armchap1.html

  2. PowerPC by MightyYar · · Score: 1, Funny

    Apparently they are bringing back the PowerPC for the new Amiga.

    --
    W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    1. Re:PowerPC by the+linux+geek · · Score: 3, Informative

      The most powerful general-purpose processor in the world (Power7) is a huge seller for IBM, and is a PowerPC implementation. PPC is also big in telecom applications, and Freescale does a number of fairly high-performance designs for that market.

      The PPC used in the AmigaOne X1000 is a PA Semi PA6T - not very fast, designed as a low-power chip, and long-dead. Apple bought the company a few years ago, and I'm pretty sure new PA6T's are not being made. I suppose that speaks volumes about how many X1000's they reasonably expect to sell...

    2. Re:PowerPC by PatDev · · Score: 3, Insightful

      Not technically true. Power7 belongs to the same family of architectures as PowerPC, but it's not really appropriate to say that Power7 is a PowerPC implementation. You might say that PowerPC is an uncle of Power7.

    3. Re:PowerPC by the+linux+geek · · Score: 3, Informative

      Power7 is fully compatible with the PPC 2.06 spec. How is it not a PPC ISA implementation?

    4. Re:PowerPC by Anonymous Coward · · Score: 1

      This is true. The PowerPC ISA is a subset of the POWER ISA.

    5. Re:PowerPC by Anonymous Coward · · Score: 0

      Actually, the PA6T was quite fast when it came out, back in 2006. Faster in integer but slower in FP than a 970 (aka G5). The main reason for being faster in integer is that it the integer units did not have the horrible 2 cycle latency of back-to-back integer operations of Power4/Power5/PPC970. This misfeature means that compiler have to find 4 integer instructions to execute if they wanted to fill the integer pipes, which is very hard to reach in actual code. With most other processors, you only have to find 2, which is reasonably easy.

      The point of the PA6T was to have a fantastic performance per watt, and in this respect it was successful, way ahead of its time. The maximum power dissipation was 17W for a dual-core 2GHz processor, with all the host bridge functions, dual channel DDR2 (2006 again!) memory controller and something like 24 PCI express lanes. This was implemented in a 65nm process without modern tricks like high K gate dielectric.

      Note that the 17W are the maximum power dissipation from a power supply designer's point of view, while when Intel speaks of a, say, 130W TDP, they mean this: thermal design power. When you look at the sum of all the individual power supplies from an Intel datasheet, you are north of 200W. Actually in performance/watt the 32nm Intel processors are not yet at the same efficiency as the PA6T, although they are close and 22nm should finally beat it, 6 years later. In practice the TDP for a PA6T was closer to 12-13W, since it was really hard to dissipate more (really corner cases with everything, cores, memory controllers and I/O running at full steam).

  3. Well. by Anonymous Coward · · Score: 0

    I don't care what they say. I'll keep buying and reccomending AMD until they screw me over like intel did. once.

    Bonus. I don't have to help pay for stupid commercials.

  4. Could we have a hybrid? by mehrotra.akash · · Score: 3, Interesting

    A PC(or laptop) running Windows 8(or any OS which supports both x86 and ARM) powered by a processor having full x86-64 support, and a low power ARM with a GPU capable of basic stuff like handling browsing and media playback
    So, when you switch to a high requirement program (Gaming,encoding,VS,etc) the x86 cores turn on like a coprocessor and the work is handed to them
    The ARM handles the UI and other stuff

    1. Re:Could we have a hybrid? by scheme · · Score: 3, Informative

      That's tough enough to do when all the processors use the same instruction set, but if the system has processors with different instruction sets, it makes it much harder to have the OS/system switch from a lower powered mode where it's running on the ARM processors to a high performance mode where it's running on the x86 processors. It's not impossible, it's just very complicated and I don't see companies lining up to do the work to implement something like that.

      --
      "When you sit with a nice girl for two hours, it seems like two minutes. When you sit on a hot stove for two minutes, it
    2. Re:Could we have a hybrid? by gQuigs · · Score: 1

      Sorta like this?

      It's not currently available though, and I'm not sure how long it was really available for...

    3. Re:Could we have a hybrid? by calibre-not-output · · Score: 1

      Performance-wise, what advantage does this offer over just having a faster x86-64 CPU? I don't see it.

      --
      Nothing lasts forever but the certainty of change.
    4. Re:Could we have a hybrid? by mehrotra.akash · · Score: 1

      Not really, since it requires a reboot to go into full power mode and doesnt do it transparently

    5. Re:Could we have a hybrid? by mehrotra.akash · · Score: 1

      The advantage would be in terms of battery life

    6. Re:Could we have a hybrid? by mehrotra.akash · · Score: 1

      We manage to do it for Graphics in laptops (like Nvidia Optimus which shifts to the dedicated GPU when required, and the intergrated one otherwise)

    7. Re:Could we have a hybrid? by Microlith · · Score: 2

      But which of Microsoft's divergent, self-serving rules regarding Secure Boot apply to a hybrid x86_64/ARM system?

    8. Re:Could we have a hybrid? by jeffmeden · · Score: 2

      We manage to do it for Graphics in laptops (like Nvidia Optimus which shifts to the dedicated GPU when required, and the intergrated one otherwise)

      That is for just one app, with one bit of specialized code that runs better on the GPU. And it's to do just one thing (arithmetic that the GPU is good at). Finding what operations work most efficiently on ARM vs x86 would be a whole project in itself.

      You would basically need to convince Microsoft (or whoever is the prevalent OS vendor in this fantasy) along with ALL of their partners, to switch to ARM as the primary architecture, and THEN convince them to include additional code types if their apps want to run faster than a crawl (i.e. move off the ARM chip and onto the x86 chip). It's a complete chicken and egg problem, you would need a very well built development studio to manage all the differences in a way that didn't completely cripple developers with the work needed to make their code run in two places at once, and you would need the CPU hybrid vendor to get out in front with a hardware platform that was appealing to the masses.

      We have worked hard enough to get to where we are with x86 (something like 30 years now) so while I like to think long term, I believe the practicality of this idea is probably on the low side. But since we are in fantasy land, you might as well propose that a machine be built with the ability to "dock" a smartphone through some sort of hyperbus, run all apps off of the smartphone as the primary CPU and then when an app needs more resources it can add on x86 or even multi-core or ramped-clock ARM CPU resources in the docking station (like the Motorola LapDock idea, except extended greatly.) But good luck getting a standard that all handset makers can get behind, and THEN a standard that all (or a majority of) app makers can get behind, and THEN finding people to buy the whole rig.

    9. Re:Could we have a hybrid? by aepurniet · · Score: 1

      its a fair question, dont think that was ever addressed. if plopping in a atom chip can get rid of the requirement for secure boot, it would be huge. not to mention this whole top level thread is completely off topic, and the type of idle speculation that is usually reserved for cable news.

    10. Re:Could we have a hybrid? by Microlith · · Score: 0

      Ooh, someone's hurt because I brought up what would be an entirely valid question in the environment the GP quoted, and it put MS in a bad light!

    11. Re:Could we have a hybrid? by fast+turtle · · Score: 1

      I'll put my $1M in on this one.

      What you need is the ARM core to provide the hypervisor/uefi/bios access with the x86 cores being VM's. You then get the best of both worlds and can easily ensure that the best chip handles the apropriate load. Audio and Video get handled by the ARM core and it's DSP's while the x86 cores handle all of the x86 based software.

      --
      Mod me up/Mod me down: I wont frown as I've no crown
    12. Re:Could we have a hybrid? by Belial6 · · Score: 1

      Exactly. It really is a trivial problem to solve. I am kind of surprised that we have not seen it yet. That would be one place that AMD could really make a splash. Imagine a laptop that had an APU with x86, ARM and graphics on a single chip.

    13. Re:Could we have a hybrid? by unixisc · · Score: 2

      I recall that this was tried once in the 90s by Apple - they had a special accelarator card w/ an AMD CPU on it, which would plug into a PCI slot on the motherboard. So one could run native PPC apps on the Mac, but if one needed to run any Windows apps, it could simply be run on the AMD. (I think it was a K5 or something - don't think the Athlons were out by then). Of course, today Apple uses the x86 itself, but any other workstation maker could use something similar.

      Dunno that it would work for tablets though - by adding an Atom or a Fusion chip, one is just increasing the power consumption of the tablet, which is something critical.

    14. Re:Could we have a hybrid? by unixisc · · Score: 1

      What exactly in the ARM instruction set do you think would extend the battery life?

    15. Re:Could we have a hybrid? by Anonymous Coward · · Score: 0

      No offence but you really made anyone with a clue smirk HARD. Multimedia and browsing are some of the most difficult and demanding uses a modern computer faces - nowadays browsers are borderline "a fine OS just lacking good web browser" while video and audio requires careful timing and resource allocation. And you dedicated hardware morons should finally get it into your thick skulls that first there's software implementations, hardware if any follows years later when the new thing has gained traction and there's popular demand for it which can only happen when there's usable software implementations first. Just take a look at H.264 High 10 bit profile - to this AC's knowledge no known hardware decoder is even scheduled to support it yet but of course just as H.264 High Profile (8 bit) with Vorbis all in Matroska (later two not even being industrial standards) can now be sort of handled by even entry level hardware players the new 10 bit one will be supported, too, at best few years before anime fansubs move towards something better like 12 bit color depth or a new codec or finally a new subtitle format, making the brand new and shiny and state of he art dedicated hardware properly obsolete (observive reader will have noticed that by defintion dedicated hardware is obsolete before arrival). Just like MPEG-2 and H.264 support on video adapters came right around the time when average CPU could handle them without breaking a sweat.

  5. StrongARM by Anonymous Coward · · Score: 0

    They probably should have thought of this while they had the StrongARM team in house (~2001) ... before they forced them all to quit or move to x86.

    1. Re:StrongARM by lostmongoose · · Score: 3, Informative

      You're confusing AMD and Intel. StrongARM was bought by Intel not AMD.

  6. sub-45nm ARM? by lobiusmoop · · Score: 2

    Wondering if a big state-of-the-art chip-fab like AMD getting into ARM processors might make sub-45nm ARM processors a possibility? AFAIK, only X86 chips are made like this just now. Could lead to fantastic performance-per-Watt chips coming off the line.

    --
    "I bless every day that I continue to live, for every day is pure profit."
    1. Re:sub-45nm ARM? by Btarlinian · · Score: 4, Informative

      AMD lost its fabs a while ago. (Their fabs are part of GlobalFoundries now, and they're a bit ahead of TSMC, but not anywhere close to Intel in terms of process capabilities.)

    2. Re:sub-45nm ARM? by Btarlinian · · Score: 2

      And being ahead of TSMC is arguable in any case.

    3. Re:sub-45nm ARM? by the+linux+geek · · Score: 2

      28nm TSMC ARM is likely this year.

    4. Re:sub-45nm ARM? by unixisc · · Score: 1

      Did they sell all their Fabs - the ones @ Austin and Dresden as well?

    5. Re:sub-45nm ARM? by Btarlinian · · Score: 1

      AMD is a fabless company now. They contract out their manufacturing to their former fabs (including the one in Dresden), which is a separate company that they own ~10% of. That company is building a new fab in Saratoga County in NY. Their former Austin fab was spun off with their flash memory division as Spansion. It's no where close to being a leading edge fab. It still uses 200 mm wafers.

  7. Ambidextrous? by mark-t · · Score: 5, Funny

    Does that mean it's using two ARMs at once?

    (duck)

    1. Re:Ambidextrous? by cmburns69 · · Score: 1

      Wouldn't that be ARMbidextrous?

      --
      Online Starcraft RPG? At
      Dietary fiber is like asynchronous IO-- Non-blocking!
    2. Re:Ambidextrous? by Anonymous Coward · · Score: 1

      As a lefthander, I prefer the term "ambisinister"

    3. Re:Ambidextrous? by Anonymous Coward · · Score: 0

      I'd give my right ARM to be ambidextrous.

    4. Re:Ambidextrous? by eulernet · · Score: 1

      Yes, but they cost an arm and a leg.

    5. Re:Ambidextrous? by shadowofwind · · Score: 1

      It means the mix big-endian and little little-endian in the same architecture.

    6. Re:Ambidextrous? by unixisc · · Score: 1

      MIPS is already like that.

    7. Re:Ambidextrous? by cyclomedia · · Score: 1

      Amdibextrous?

      --
      If you don't risk failure you don't risk success.
  8. As a complete NOOB on the subject... by wisebabo · · Score: 2

    ... would it be possible (or I guess more importantly) worthwhile to put x86 cores WITH ARM cores on a single chip?

    In addition to offering dual boot capabilities, it might be useful to run "Virtual" (or sort of virtual) machines at full speed. I've often thought it would be nice to run some of the thousands(!) of cellphone Apps that I have on my laptop. Although it might be tricky to implement multi-touch correctly, still I'd think there might be some utility.

    Or maybe all CPUs today are very generalized RISCy architectures with everything taken care of in microcode (or maybe nowadays it's nanocode)? That would make it (comparatively) really easy to do, right?

    1. Re:As a complete NOOB on the subject... by Anonymous Coward · · Score: 0

      Not cores as that would require major redesigns in the architecture for something pointless (no speed boost or feature that benefits everyone) but they could put 2 cpu into 1 silicon chip. There is no point though as the benefits are niche and dual booting can be benefits by having the arm proc on the mb in it's own chip or in the mb chipset.

    2. Re:As a complete NOOB on the subject... by Koen+Lefever · · Score: 3, Informative

      Or maybe all CPUs today are very generalized RISCy architectures with everything taken care of in microcode (or maybe nowadays it's nanocode)? That would make it (comparatively) really easy to do, right?

      Sounds like you are reinventing the Crusoe processor.

      --
      /. refugees on Usenet: news:comp.misc
    3. Re:As a complete NOOB on the subject... by CharlyFoxtrot · · Score: 1

      It'd be far easier to do Apple-style "universal binaries" (bundles that contain executables for more than one architecture) than it is to create this kind of hybrid hardware. Apple could already create iOS/OSX universal binaries in Xcode if they wanted to since it can already compiles for both x86 and ARM for the "emulator" and device respectively. The biggest hurdle is the fact that the main control interface (touchscreen) is missing on the dektop.

      --
      If all else fails, immortality can always be assured by spectacular error.
    4. Re:As a complete NOOB on the subject... by Belial6 · · Score: 1

      The missing touchscreen is a temporary setback. As is the missing mouse pointer on the portable devices.

  9. Didn't they try this already before? by Anonymous Coward · · Score: 0

    AMD used to make a SoC based on MIPS arch. It must not have worked out for them because they didn't really do a lot with it and finally got rid of it.

    OT. Does AMD still have the same CEO and officers it did when the stock melted down a few years back? If so, the best thing AMD could do would be to fire the lot of them. There has to be competent officers at the helm for a company to succeed.

    1. Re:Didn't they try this already before? by Anonymous Coward · · Score: 0

      They bought Alchemy Semi, which is the company who did MIPS SoCs. Alchemy was founded by the vast majority of the DEC StrongARM team. AMD didn't know what to do with Alchemy (even though they were profitable!) and decided to be x86-only, and sold them off. Shortly after, Intel decided to be x86-only "even harder" and got rid of the XScale/StrongARM stuff they grabbed from DEC.

      Funny, I bet Intel and AMD would be much further ahead if they held onto their non-x86 people. Let's not even mention AMD's 29K or Intel i960...

    2. Re:Didn't they try this already before? by unixisc · · Score: 1

      Sounds strange, given that until recently, their CEO Dirk Meyer was the same guy who led DEC's Alpha team. At that time, MIPS was a more crowded market than it is now. However, in retrospect, AMD's move to do the x64 was fantastically successful - even being used in some super-computers. While Intel's Itanium project - their 3rd attempt to come up w/ a successful non-CISC architecture - bombed.

      Intel's i860 had moderate success, like in the Paragon, while the 960 as well as AMD's 29k was used in peripheral equipment, such as printers. These are things that would be good for ARMs, the ex Alchemy MIPS SOC and so on. But for platforms where people would be expecting to use their x86 apps, Intel & AMD have no choice but to keep producing x86 or x64 CPUs

  10. A new high end CPU by Anonymous Coward · · Score: 0

    I'd love to see an AMD high end CPU using ARM instruction set , full 64 bits, etc . This could be interesting for servers.
    But I'm dreaming

    1. Re:A new high end CPU by unixisc · · Score: 1

      What would servers gain? Already, Power7 gives one a pretty good power savings, as do Opteron and Xeon. Once ARM made an ARM 64, particularly targetted towards servers, it's power consumption would keep rising as the implementation strives to be @ par w/ the competition. Honestly, I don't see ARM ever gaining in this market.

  11. Where does AMD come into the picture? by Anonymous Coward · · Score: 0

    AMD and ARM are both design and marketing companies that don't actually make chips (external foundries do the manufacturing). ARM already has the ARM cpu design pretty well figured out, so what would AMD bring to the table in an AMD-ARM alliance? Just branding, or what?

    1. Re:Where does AMD come into the picture? by petermgreen · · Score: 4, Informative

      AIUI ARM do HDL design of processor cores, then they pass that HDL on to other companies who make complete chip designs based on it. Those companies in turn pass the designs onto fabs (which may be in-house or external) for manufacture. IIRC some vendors also do their own HDL work and only license the basic architectural design from ARM.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    2. Re:Where does AMD come into the picture? by Nikker · · Score: 2

      Licensing fees.

      AMD bleeds money to Intel for the x86 instruction set. At one point this was manditory since all the programs out there that were able to be run by a comparatively inexperienced computer users were written for the computers they could find at Radio Shack et al. Now that Microsoft and Google are popular and platform agnostic (Linux/Android vs win8) AMD has a window of opportunity to start from scratch and just offer a kernel patch to have your apps run on their chips. This new direction is going to be interesting to see execute. Intel was and is the gatekeeper of the consumer PC space now that is not so stable. Android can and has already been ported to x86,MIPS and a whole slew of variant ARM archetectures. To top it off millions of people use and enjoy Android, distributors like that they can make the products cheaply and must stay with the platform to keep their purchases/investments, lastly carriers love it cause they can lock you in for 3 years at premium rates.

      It looks like this time Intel might have to tighten it's belt for a change.

      --
      A loop, by its nature, continues. If that didn't make sense, start reading this sentence again.
    3. Re:Where does AMD come into the picture? by Locutus · · Score: 1

      ARM does do most of the design work but I think there's still lots of integration and other optimizations done by the licensees. And not all licenses are the same so some are allowed to tweek and others not.

      So what does AMD bring to the table with ARM game? They do have a pretty nice graphics GPU and they do have some familiarity with optimizing not to mention the ability to merge x86 with ARM if they want to. ie 2 x86 cores and 2 ARM cores so you could have blazing performance at the cost of power or boot the ARM cores for power sipping usage all in one package. just throwing it out there with off the top of the head comments. Hopefully some chip design geeks chime in with more complete examples of where this could work for AMD and possibly the general customer bases. And hey, maybe that'll mean ARM devices without bootloader lock outs via MS requirements.

      LoB

      --
      "Anyone who stands out in the middle of a road looks like roadkill to me." --Linus
    4. Re:Where does AMD come into the picture? by symbolset · · Score: 1

      The leap from "not x86" to "ARM" involves a large unfounded assumption.

      --
      Help stamp out iliturcy.
    5. Re:Where does AMD come into the picture? by unixisc · · Score: 1

      Actually, ever since AMD came up w/ x64 and got Microsoft to endorse it, AMD & Intel have a cross licensing agreement allowing each of them to use the others instruction set. The question of AMD not owning it, or violating Intel IP, is a thing of the past.

  12. ambidextrous by trb · · Score: 0

    How will I decide whether I want a right ARM or a left ARM? If they are ambidextrous, will it matter?

    1. Re:ambidextrous by Anonymous Coward · · Score: 0

      The real question is: Will the left hand know what the right hand is doing?

    2. Re:ambidextrous by Anonymous Coward · · Score: 0

      It depends on the chirality of your code.

    3. Re:ambidextrous by K.+S.+Kyosuke · · Score: 2

      The real question is: Will the left hand know what the right hand is doing?

      Modern architectures usually don't do that. There is a solution to this problem, but it's kind of MESI.

      --
      Ezekiel 23:20
  13. choice of words by moco · · Score: 3, Funny

    Since they have no products using that other architecture I think the word they were looking for is "Bicurious".

    --
    moi
  14. Re:option d, all of the above by Anonymous Coward · · Score: 0

    This story being submitted being Stalin himself, x86 may be dying in a Gulag, and AMD and ARM may be Soviet spies. My breath freezes from the implications.

  15. Why it's called "trinity" by gr8_phk · · Score: 1

    I'm shocked that the press hasn't gone wild with speculation on the name "trinity" which implies 3 of something. My guesses are as follows:

    1) They integrate CPU, GPU, and "system" on a chip - not really worthy of the name
    2) They integrate 3 distinct CPU architectures in APUs. Bulldozer, Bobcat, Power. Or x86, Power, ARM.
    3) They are aiming for PC, Apple, and Console markets with the stuff in #2 (consoles require Power arch for backward compatibility).

    My bet is that Wii U will have an IBM CPU and AMD GPU on the same die manufactured at GF. The only thing not official there is the integration.

    It's also insane for Apple not to go with Trinity and there have been rumors. AMD has canceled product and delayed (public) availability of Trinity even though they claimed it was ramping and on track (last fall) for early 2012. This suggests they're stockpiling for a large customer.

    That's just my speculation based on Googling of course. So they either have something big and have kept it very quiet, or the just suck.

    1. Re:Why it's called "trinity" by Anonymous Coward · · Score: 1

      Sorry to burst your bubble, but Trinity is a name of a river in Texas, which is the theme for the APU naming (e.g., Brazos, Sabine, Lynx).

    2. Re:Why it's called "trinity" by the+linux+geek · · Score: 1

      There is exactly zero chance of Trinity being anything other than what it's been announced and demo'd as from day one: L3-less Bulldozer (well, technically Piledriver) with a GPU on-chip. In other words, an incremental successor to Llano.

    3. Re:Why it's called "trinity" by gr8_phk · · Score: 1

      Agreed. For the desktop PC part. I just figured that was part of a larger picture. The other poster saying it's named after a river in Texas really deflated my hope too.

  16. Competitor for Tegra? by Tapewolf · · Score: 3, Informative

    The Tegra is basically an ARM SoC with an nVidia video system. Maybe they're looking at doing an ARM SoC with the ATI video core...

    1. Re:Competitor for Tegra? by Anonymous Coward · · Score: 0

      Maybe they're looking at doing an ARM SoC with the ATI video core...

      Whoever sold their mobile business to Qualcomm has probably been promoted as a visionary...

    2. Re:Competitor for Tegra? by Anonymous Coward · · Score: 0

      Don't forget, another part went to the all evil Broadcom, from which they now have some advanced 3D graphics capabilities...

  17. What I really want to know is if they can ... by Skapare · · Score: 1

    ... upgrade the ARM architecture to 64 bit (hopefully, they have some experience in that), put 64 cores of it on one die, and crank the speed up to 4 GHz.

    --
    now we need to go OSS in diesel cars
    1. Re:What I really want to know is if they can ... by nschubach · · Score: 1

      64 cores at 6.4Ghz running 64-bit code... we'll call it the AMD 262144 processor

      --
      Every time I start to have faith in humanity, I ruin it by driving to work between 7 and 8 am.
    2. Re:What I really want to know is if they can ... by LWATCDR · · Score: 1

      For many tasks 64 bit is over rated. Unless you are doing something that needs a HUGE memory space and or 64 bit ints 64 bit code takes up more room and is slower than 32 bit code... If the ISA isn't brain dead and starved for GP registers in 32 bit mode.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    3. Re:What I really want to know is if they can ... by ThePeices · · Score: 1

      "For many tasks 64 bit is over rated."
      And as time goes on, that 'many' turns into 'some' and eventually into 'once in a blue moon'. Thats the nature of progress.

      The thing is, many of us actually do need 'HUGE' memory space and/or 64 bit ints.
      this is 2012, and i just need more than 4GB of RAM in my computer.
        - My flight combat simulator gobbles RAM like a crack whore gobbles crack. (DCS A-10) 4GB is simply not enough for this one application.
        - Photoshop CS5 / Lightroom just runs better 64 bit natively and most especially when working with multiple 18MP RAW format photos.

      The performance difference between 32 and 64 bit is very minor, and the extra storage/memory is again a minor thing. If your OS is 64 bit, there is no reason not to run a 64 bit version of an app instead of a 32 bit one if you have the choice between the two.

      Did you believe Bill Gates when he said that 640k of RAM is plenty enough for anybody?

    4. Re:What I really want to know is if they can ... by LWATCDR · · Score: 1

      You can have more than 2/4GB of space with a 32 bit cpu. The limit is on per process.
      I am also into flight sims and they do tend to fit that category.
      Lightroom/photoshop. You bet.

      Now the idea that their is no reason to not run a 64 bit version of the app... If the App will never need the memory space I disagree. Your GTalk client will never need that much space. Your word processor hopefully will never need that much memory. If it does then bloat has gotten out of hand.
      Now on X86 things are different. In the 32 bit mode you are register starved so running in 64 bit mode gives you an advantage even with smaller memory usage programes. That is not an issue with ARM.

      Is 64 bit the way of the future. Yes. IS not having it today I big deal. Not for many applications including a lot of desktop and server applications.

      Now what I would like to see Intel do is create a new Mobile Atom that ditches all the kruft and uses the 64 ISA as a template for a new 8, 16, 32 bit modes.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
  18. Idea... by tgetzoya · · Score: 2

    AMD builds a hybrid chip. It uses the ARM core for everyday tasks and then the x86 core when power is necessary. Kind of what Samsung does with their 5 core processor. Add in an AMD graphics core and that would bring some power.

  19. Works for me. by Daniel+Phillips · · Score: 1

    I will so buy a bagfull of these chips if AMD follows through on this smart thing. 28 nm multicore ARMs. Booya! Also looking forward to the integrated low power GPU.

    --
    Have you got your LWN subscription yet?
  20. a*r*mbidextrous by adavies42 · · Score: 1

    shirley they meant armbidextrous....

    --
    Media that can be recorded and distributed can be recorded and distributed.
    -kfg
  21. at last! by lkcl · · Score: 0

    the problem with the x86 architecture is that it was designed to be compact and space-saving: the escape-sequences that go up and up and up from 8086 to 80186 to 286 to 386 to 486 to 586 to 64-bit are incredibly efficiently encoded. *BUT*, there comes a massive performance penalty which is that the clock rate now has to be twice as fast as a RISC processor in order to achieve the same results. RISC processors, with the exception possibly of the Xtensa (which kinda cheats by allowing VLIW as well), tend to substitute larger memory requirements for less compact instructions; ARM cheats by actually compressing the instructions! (thumb).

    so it's all quite horrendously complex, but the kicker is that power goes up in a square law with processor speed. double the speed you need FOUR times the power. so, if an x86 processor has to run twice as fast to achieve the same results as a lowly RISC core which is eating twice the amount of RAM as an x86, the x86 is using FOUR times the power in order to keep up with the RISC processor.

    it's never that simple, though: ARM and other RISC cores also trade higher latency for lower power. _and_ there is the issue of trying to run a 64-bit or a 128-bit memory bus, off to a separate "Northbridge" chip: these RISC all-in-one SoCs with embedded GPUs and integrated I/O just don't have that problem, and they're not trying to drive massive amounts of external lines just to get access to memory [through a silly "Northbridge" chip].

    but that's not the end of the story. with the advent of DDR3 and the introduction of 28nm, RISC cores are going to eat x86 for breakfast, lunch and dinner, as RISC CPU designs means can easily run at 2 to 2.5ghz in 28nm... and still only use 1 to 1.5 watts! and with DDR3 RAM being so fast, the "problem" of latency for RISC CPUs is *also* going away.

    if AMD tells you they can do a 2 watt x86 CPU (like in TFA), they aren't exactly lying, but they're sailing pretty close to the wind.

    bottom line is: if they're saying that they're architecture-agnostic, that basically saves their bacon. let's hope that they do a decent job, eh? it would be absolutely cool for them to put an ATI-based "Open" GPU with full and complete GPL'd source code along-side an ARM or any other CPU core.

    1. Re:at last! by Chris+Burke · · Score: 3, Insightful

      *BUT*, there comes a massive performance penalty which is that the clock rate now has to be twice as fast as a RISC processor in order to achieve the same results.

      That's just complete bollocks.

      A modern x86 processor (meaning... since the Pentium Pro in the mid 90s) is, internally, a RISC-like core with full OoO execution and so on and so forth.

      Variable instruction decode is a pain in the ass and does add latency in the front end. This isn't great, but it is nowhere near a 50% reduction in IPC. Try more like 1-2% (measured via correlated cycle-accurate performance simulator), depending on how clever you get and in any case easily made up for by a clever widget or two.

      Basically predictions of RISC eating x86 for breakfast were made over 15 years ago and never came to pass. Mostly by x86 morphing so that the difference was essentially irrelevant.

      Your talk about northbridges sounds woefully out of date, too. This has nothing to do with ISA, and both major x86 vendors now have integrated northbridges.

      You're closer to reality when talking about power. Regardless of the small IPC penalty, those decoders burn up a lot of power. There are ways to get around this, too, and for moderate perf moderate low power x86 does just fine. At the very low end of power, though, going to something like ARM makes sense.

      --

      The enemies of Democracy are
    2. Re:at last! by Alioth · · Score: 1

      It's not just the variable instruction decode (incidentally, just the bit that works out the length of the next instruction is the size of an entire ARM execution core) but it also makes things like branch prediction and out-of-order execution much more complex to implement compared with a more straightfoward ISA encoding.

      The predictions that RISC eat x86 for breakfast DID come to pass. ARM outsells all other CPU architectures *put together*.

  22. x86 and GPU, not x86 and ARM by Pulzar · · Score: 2

    AMD is clearly talking about using both x86 and GPU for compute work vs. focusing on x86 only... the ARM thing is just a wild speculation, or wishful thinking.

    --
    Never underestimate the bandwidth of a 747 filled with CD-ROMs.
  23. comrade! by Anonymous Coward · · Score: 0

    Was this posted be Stalin?

  24. Tards by Life2Death · · Score: 0

    I think if anything, they would be commenting on their OpenCL and x86-64 arch's that are in their pipe ie x86+GPU processing, but I guess that goes over everyone's heads. Bobcat was geared towards going into phones and low-compute devices that are anything but gaming and server level applications.

  25. ARM suffers from the same problem all riscs do by luminousone11 · · Score: 1
    ARM like any risc chip is great for a particular level of complexity, for a particular application, or situation.

    Basically predictions of RISC eating x86 for breakfast were made over 15 years ago and never came to pass. Mostly by x86 morphing so that the difference was essentially irrelevant.

    Exactly. x86 might be a pain to decode, but the fact that you can replace the backend arch that actually does all the work with one that fits the particular level of complication desired means that x86 unlike ARM(or any risc for that matter) can scale from simple 8086 with 29,000 transistors to that of a westmere-ex with 2,600,000,000 transistors. and go from 8bit to 64bits, or with SIMD 256bit. when they added large caches throw in instructions for cache control/hinting. What is really needed is a fixed instruction length CISC arch with an opcode address space large enough for future expansion, a means to deprecate old instructions, keep x86 addressing(the 64bit model that is), and an ISA that is designed to be easily decoded into whatever the chip is really running.

    1. Re:ARM suffers from the same problem all riscs do by Anonymous Coward · · Score: 0

      Fixed length CISC instructions would be a terrible waste of memory. Suppose you had a fixed instruction width. If you want to do everything x86 can do, each instruction would have to be at least 16 bytes long (to hold two 64-bit immediate values). But if you have an instruction where it only references two registers, it requires a lot less that since it only requires a few bits to represent a register.

      RISC ISA's are able to have fixed-sized instructions because all of the work is done in registers. There are a few bits for the opcode, and a few bits to specify the registers. And they allow only small immediate values (for example, PowerPC ISA, even though it is a 64-bit architecture, only allows for 16-bit immediate values).

    2. Re:ARM suffers from the same problem all riscs do by luminousone11 · · Score: 1

      http://www.sandpile.org/x86/opc_enc.htm its a mess, with 64bit we have a prefix byte , 1 to 4 bytes for the op, mod byte, and above that with avx we have the DREX byte, potentially imm byte. etc. I see no reason why intermediates can't occupy the space the next instruction would have and be aligned to the size of the fixed instruction length. that one exception to the fixed size rule shouldn't cause that much trouble for decoding of instructions.

    3. Re:ARM suffers from the same problem all riscs do by Anonymous Coward · · Score: 0

      You can replace a backend arch that actually does all the work with one that fitst the particular level of complication desired regardless of what the frontend arch looks like. In fact if the frontend arch is neat and regular like ARM rather than crufty and horrid like x86, it's easier.

    4. Re:ARM suffers from the same problem all riscs do by Anonymous Coward · · Score: 0

      Actually, it's such a pain to decode that some recent processors have 2 instruction caches: one in native messy encoding and one in a saner encoding with a very complex mapping between the two (Intel describes it somewhere).

      Really decoding 3 or 4 x86 instructions in parallel is a tour de force that costs a lot of transistors (die area) and, more importantly, power. Other processor areas (FPU) can be switched off when not in use but that's not possible on instruction decoders.

      For example some AMD processors have 16 decoders running in parallel and than they typically throw away 75-80% of the energy spent on decoding since the first decoder deduces the instruction length and selects where the second instruction in a 16 byte block starts, throwing out the outputs of the intermediate decoders. A minor side effect is that every instruction byte coming from the must be replicated up to 16 times, which probably costs one clock cycle, at least on branch prediction failures.

      Note that part of it is specific to extremely messy x86 instuction encoding, other CISC machines (IBM mainframes) can sport a 3 way instruction decoder without as much effort since the instruction length (only 2, 4, or 6 bytes are allowed) can be deduced from the 2 most significant bits of the first byte of the instruction. This may explain why they ship these machines at 5.2GHz (obviously they are also low volumes and cost is not a major concern), despite the fact that everything is duplicated, ECC checked and so on.

      Given this level of complexity (dual caches, power dissipated in decoders), x86 still has some advantages over RISC in straight inline code (but ARM thumb is typically denser), but not at all in loops with significant repeat counts (where most of the time is spent).

    5. Re:ARM suffers from the same problem all riscs do by unixisc · · Score: 1

      Given that most of the hit that x86 takes is as a result of the instruction length decoders and microcode, isn't it possible to have a 2 chip solution where:

      1. One chip contains all the RISCy x64/x32 instructions, including the floating point (unless the FPU is being contained within the GPU)
      2. Other chip contains all the variable length, CISCy x86 instructions that make it difficult to implement in a pure RISC architecture?

      That way, the first chip can be optimized for maximum power savings, RISC performance and FPU performance, while the second chip is there to support the first w/ legacy code. Over time, as 4GB becomes the bare minimum in all sorts of systems, not just laptops, newer versions of applications will tend to go all 64-bit, and when that happens, the second chip above can be dropped from the chipset, resulting in an instant cost reduction as well as power savings. Oh, and any glue logic needed for the second chip to work w/ the first will be contained within the second chip.

  26. RAD6000 / RSC / POWER1 by OrangeTide · · Score: 3, Insightful

    RSC(POWER1) is the most popular CPU architecture on Mars, and possibly in the solar system outside of Earth.

    --
    “Common sense is not so common.” — Voltaire
  27. Wish Android had universal binaries by Anonymous Coward · · Score: 0

    Google could learn a thing from Apple's universal binaries. I currently have an android tablet running a MIPs processor. There is a severe shortage of apps available to use.

    1. Re:Wish Android had universal binaries by evilviper · · Score: 1

      I currently have an android tablet running a MIPs processor. There is a severe shortage of apps available to use.

      What the hell are you talking about? Android is a slightly modified java based platform. 95% of the Android apps out there are completely CPU-agnostic, because that's just the default state of affairs.

      The exceptions are the CPU-intensive multimedia apps... Adobe Flash, video players, and some games. Actually Firefox is on the list as well for no good reason.

      You can't get Flash for any other mobile platform, and it hasn't been ported to ICS even, so it's almost a niche product...

      Android comes with built-in audio and video players, which support a decent number of formats. They're not polished, but it's not like you're left without a music/video player. They're part of the base system and will be ported to your MIPS chip with the rest of it.

      So it looks like you're JUST talking about (high-end) games, really...

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    2. Re:Wish Android had universal binaries by unixisc · · Score: 1

      Apple has universal binaries? Their only platform is their ARM - A4/A5 and so on. Can they on the fly switch to, say, PowerPC and build iPads on those?

  28. Re:option d, all of the above by V!NCENT · · Score: 1

    I'd go for hoping x86 will die. It's an outdated piece of junk, that even internally doesn't work anymore. Intels and AMD's simply convert that crap to RISC-ish architectures. The reason that they don't make the CPU ARM instruction compatible is because the instructions change everytime, just to get x86 apps to work faster. This has been said by John Bridgman, AMD's GPU driver manager, so the info must be correct.

    It won't hurt open source and Microsoft has an internal port of Office and Windows already running on the Texas instruments and Tegra ARM platforms. This will come as Windows 8 on tablets. Killer combination, if you ask me. iPad is going to get a run for its profits.

    This is pretty much in line with the AMD's Coreboot BIOS assasination strategy and the Radeon free software strategy.

    Gotto love those geeks at the top of AMD :D

    --
    Here be signatures
  29. Can ARM & X86 come together? by Quick+Reply · · Score: 1

    I can see a future where the main computer functionality runs on ARM for basic functions such as the Operating System, User Interface, and Basic apps, and an x86 co-processor is there for compatibility with legacy apps (including running a Virtual Machine to do this if necessary) and for Intensive computing apps (eg: Gaming, Content Creation, Transcoding)

  30. Not about instruction set... by Junta · · Score: 1

    I think a lot of people mistakenly believe ARM's success is because the instruction set is just better. AMD impleminting the ARM instruction set does not, by itself, suddenly make AMD more compelling.

    The ARM architecture's licensing has allowed a larger variety of companies to get in the game with their own ideas around implementation. This has led to exceeding low prices compared to the levels the x86 solutions have been willing to go, energy optimized designs to target specifically the mobile device market moreso than Intel and AMD did, and perhaps the most concrete distinction between Intel/AMD efforts to date and the successful ARM bits, system on a chip oriented designs facilitating the previous two points.

    Intel seems to have begun to accept the SoC reality with Medfield, though still not willing to price down to ARM level and still not integrating as much as leading ARM implementations, they are getting closer. If AMD could push a compelling ARM archictecture solution, they could probably leverage their license for the x86 instruction set and have an implementation centered around that.

    I know many people disparage the x86 instruction set but 95% of them don't even understand the arguments around it. I don't think x86 instructions drive the cost and power to the extent some people presume, it's mostly more general engineering choices.

    --
    XML is like violence. If it doesn't solve the problem, use more.