Comments Locked

54 Comments

Back to Article

  • Marlin1975 - Monday, November 15, 2010 - link

    Why 65nm? Does TSMC only allow larger companies their 40nm?

    Why this, as you pointed out, over bobcat?

    Yea VIA is still around but they will not be for long if they keep playing softbal like this. They need to take a big chance like AMD did with the orignal Athlon. Either come to win or be swept up by the bigger fish.
  • Mr Perfect - Monday, November 15, 2010 - link

    The article says they're releasing 40nm in 2011, so this is probably just to tide them over.
  • wazzap123 - Friday, November 19, 2010 - link

    Yeah, there's a good analysis over at the daily circuit.

    http://www.dailycircuitry.com/2010/11/nano-duo.htm...
  • nafhan - Monday, November 15, 2010 - link

    I think TSMC is pretty constrained on their 40nm node right now. Also, VIA probably had the design ready to go for 65nm.
    I agree with your "why would anyone buy this" sentiment, though. Bobcat seems to be aimed at almost the same market segment. Even though this seemed to work fine, between VIA and AMD, I'll trust AMD to deliver good drivers 10 times out of 10.
  • softdrinkviking - Tuesday, November 16, 2010 - link

    If nano turns out to be less expensive than bobcat, I can totally see it's relevance.

    I'll never play a big game like MW2 on a small mobile platform anyway, so if nano and bobcat both load web pages and allow me to type documents at about the same speed, I'll buy the cheaper one.
  • FATCamaro - Monday, November 15, 2010 - link

    From the days of the KT266 onwards they have been worthless. More power at idle and load than an i3 530. Good job!!!
  • GeorgeH - Monday, November 15, 2010 - link

    This is a pre-production 65nm sample VIA is using to give performance previews. The actual shipping product will be 40nm and have lower power consumptiion.

    Also, VIA made some good enough chipsets post KT266. Bang for your buck was often hard to beat - such as when VIA was one of the only ways to get a P4 with DDR SDRAM.
  • Goty - Monday, November 15, 2010 - link

    I loved my old MSI KT3-Ultra motherboard running Via's KT333 chipset. I think it's still doing duty somewhere for my parents.
  • juampavalverde - Monday, November 15, 2010 - link

    Yupp! That MSI was a hell of a good board, i friend had one and sold it to another friend, its still alive and kicking with an overclocked throughbred.

    I had an Asrock KT600 board, the thing was the cheapest cr@pp around with sata those days, always was solid, with reasonable performance. Also still working (not at my home) with a barton, a couple of ddr gigs, and a radeon 9600, pushing win7 x86 nicely.

    VIA didnt have a consistent platform for 478/775, but at amd chipsets (462,754,939) they did well in the agp times.
  • yuhong - Tuesday, November 16, 2010 - link

    And I remember reading nForce4 being troublesome in the PCIe times. Did VIA gain from it?
  • LoneWolf15 - Tuesday, November 16, 2010 - link

    I still have an MSI KT4-VL (KT400 chipset) on my workbench that was in my parent's system. For over five years without complaint it ran an Athlon XP-M (Barton) 2500+ clocked at 2.3GHz in their system, and it still runs fine.

    Graphics aside, VIA's chipsets have been solid over the years, as long as a reliable vendor built the mainboards. Trouble is, lots of VIA chipsets were bought by companies like ECS to build budget mainboards. The chipsets weren't the problem, but the manufacturing process and quality control gave the boards reputations, and VIA an undeserved black eye along with it. When someone like ASUS or MSI made a VIA board, it always turned out just fine.
  • Snotling - Tuesday, November 16, 2010 - link

    The black eye was totally deserved, mostly for all the bad rep their faulty chipsets and buggy drivers caused to AMD in the K6 period.

    as far as I'm concerned, VIA had three relatively usable products, the KT266 Chipset (and its updated variants 333 and 400) beyond that They were totally Owned by NForce.

    Also their sound chips (Envy) were decent and onboard graphics, when used on server boards did the job.

    other than Than, its all under performing and unreliable CR@P
  • mczak - Monday, November 15, 2010 - link

    Yes, and this being a 65nm sample is a problem - it means the final product may appear too late to be still relevant.
    The cpu looks ok so does the gpu - so as a faster (but more power hungry) alternative to atom this looks just fine. The problem is Bobcat does so too, and might (this is mostly guesswork for now) be quite comparable in cpu performance, a bit better in gpu performance, and still have possibly a bit lower power draw, while being released much earlier. So with this appearing quite a bit later that might not be very convincing. Heck it will probably have to deal with the new atom when it's finally released (cedarview) - which is rumored to have a better graphic core, though it seems likely the via platform would retain a performance advantage both for cpu and graphics (but the difference in power could grow even more, with difference in performance shrinking).
  • ClagMaster - Monday, November 15, 2010 - link

    You do not know what you are talking about.

    I has a KT266A chipset Soyo K7V Dragon Plus that I was very satisfied with.

    The KT266A chipset did what it was designed to do well. However, the caps on the motherboard were crap from the P50 electrolyte fiasco that victemized everyone. I hope the industrial spy responsable for this is rotting in a Taiwanese prison.

    VIA was the principal chipset manufacturer that kept AMD Athlon CPU going until nVidia came along with nForce2 and stole their lunch.

    This is a really promising product for low end office computers. Its not junk and should perform much better at 40nm.

    However, I think AMD with Bobcat is going to steal their lunch.
  • Steelski - Tuesday, November 16, 2010 - link

    I had a 400 series gigabyte motherboard. I thought grea, I might get something more out of my 1700+ chip If I get the nForce2 board....
    Boy was I wrong, I sold the Via and went blind with Nvidia, I had 4 nforce boards that were either unstable, unreliable, buggy or dead.
    I should have stuck with the VIA, it was the best board I ever had!
  • silverblue - Wednesday, November 17, 2010 - link

    Nah, the KT266A was excellent for its time, certainly better than the SiS735 and AMD761 chipsets that were around.
  • SteelCity1981 - Monday, November 15, 2010 - link

    What's interesting is that this cpu uses AMD-V Technology.
  • DanNeely - Monday, November 15, 2010 - link

    Look at the two closest to the IO ports. They appear to be PCIe 4x slots but installed backwards. Is this some oddity of a development/test board, or does Via intend to sell them like this. If so why?
  • Goty - Monday, November 15, 2010 - link

    This is more than likely just a development/prototyping board, so strange slot arrangements/alignments are normal.
  • jackylman - Monday, November 15, 2010 - link

    So if VIA can't compete with the big boys, it might be able to carve out a niche by doing something different, like actually working with the Linux/open-source community and/or working with S3 to make a damn good HTPC product .

    If they just want to live in the Windows world, they're not going to have much appeal.
  • tipoo - Monday, November 15, 2010 - link

    So what I take from this is that performance usually beats Atom+Intel IGP, but that 65nm fabrication process means they aren't competitive in power draw.
  • IntelUser2000 - Monday, November 15, 2010 - link

    Sorry, AMD on the same 40nm TSMC will have similar performance for CPU, and have far less TDP.

    No, Via's designs are just years and years behind. They probably need 22nm RIGHT NOW to be competitive.
  • tipoo - Monday, November 15, 2010 - link

    Huh? This is 65nm, and like you yourself said AMD's is on 40nm. Its not the same like you said. But you are right in saying that it also needs architectural improvements.
  • DanNeely - Monday, November 15, 2010 - link

    40nm will help a lot on load power, but until they implement power gating (and this is somewhere Intel still leads AMD significantly) idle power is going to remain a major liability.
  • chucky2 - Monday, November 15, 2010 - link

    Forget the speed of this thing for a moment, and the power consumption:

    What about stability and compatibility?

    If VIA is going to try and make a come back - of any type - then reviewers need to do much more stability and compatibilty testing than with products based on Intel or AMD solutions, as those were the major issues with VIA in the past. It wasn't that they had bad speed or high power consumption of the money you paid for them, it's that they had an unacceptable level of stability and compatibility issues.

    For anyone familiar with the VIA of old, that will be the benchmark they're weighed against before speed or power consumption even come into question. Doesn't matter how fast something is, or how little power it consumes, if there's a good chance it's going to crash on me with regular usage, or, if the common component I'll be plugging into it is going to have issues (because of VIA) or crash (because of VIA).

    Sure hope VIA learned from its past history.......

    Chuck
  • strikeback03 - Monday, November 15, 2010 - link

    Well this is labeled as a preview, maybe more of that will come when they have final shipping hardware.
  • ProDigit - Monday, November 15, 2010 - link

    Please, when you review bobcat, compare it to this nano chip!

    The results might prove interesting.

    I believe the Nano could have better CPU, while worse GPU ratings than the AMD one.
    Power consumption of the Nano @40nm should be between 28W and 40W idle/load; unless they are able to optimize the nano, and integrate some overclocking (like intel's turbo boost technology).
    It'd be nice to see some downclocking or core disablement on this cpu too!

    Via has much to invest in if it wants to be competitive with Intel!
  • nitrousoxide - Monday, November 15, 2010 - link

    It will not out-perform Fusion APU, which has approximately 80% the performance of current low-voltage Athlon II X2 CPUs, that is really impressive power.
  • Zingam - Monday, November 15, 2010 - link

    nvidia should buy them
  • Shloader - Monday, November 15, 2010 - link

    Actually... Yeah! If not that then at the very least create a strong partnership with them. Were that to happen a lot of the Linux compatibility questions go right out the window (unfortunately letting in a lot of power consumption questions). nVidia needs to team up with a player in the x86 CPU market and insure a platform for their discreet graphics + chipset business. Remember it was nVidia that led the way to dual channel memory on the x86 platform. Get that DDR3 memory controller integrated along with an integrated nVidia GPU on a 22 to 32 nm process. I would actually buy something for HTPC if both those companies shared the helm. nVidia's additions would make a lot of the core performance questions irrelevant for me. Just give me enough cuda power to play my vids while speeding up h.264 encoding.
  • nitrousoxide - Monday, November 15, 2010 - link

    The true competitor for Nano DC will be the AMD Bobcat, which can sweep out Atom as well as this Nano chip with ease. The Fusion APU will simply dominate such market until Intel come up with a fast-enough-Atom.
  • nitrousoxide - Monday, November 15, 2010 - link

    When are we gonna see it? Anand said that the review should be available last week :(
  • JessusChristDoOTcom - Monday, November 15, 2010 - link

    Why do we have to click on "Read more" button on the buttom of the front page article previews where there is a picture there that could be made to be clicked upon to get us to the very same place? Why not make front page preview pictures clickable leading readers directly into the first page of the article? I think it would make alot of sense and would make browsing alot smoother not to mention potential for finger clicking in touchscreen applications.
  • nitrousoxide - Monday, November 15, 2010 - link

    agreed...that helps a lot with touch screens...
  • Vepsa - Monday, November 15, 2010 - link

    if this comes in way under atom in price, i can see it being used for lots of smoothwall/pfsense/clearos/etc routers. i know i'd love an atom box for my router, but the price makes it so i can't.
  • yzkbug - Monday, November 15, 2010 - link

    Anand, could you clarify the power consumption vs. Radeon HD 5450? The original 5450 review (http://www.anandtech.com/show/2931/14) states that the total idle power is 121W (as opposed to 37.8 here). Thanks!
  • mattgmann - Monday, November 15, 2010 - link

    This all looked great until the power consumption page. I don't see this chip as direct competition to atom. Their power usage profiles are completely different.

    In fact, I bet you could build and i3 system that could have similar consumption and loads more performance.

    For what applications exactly are they marketing these boards?
  • Zoomer - Monday, November 15, 2010 - link

    Office machines, POS terminals, the like? That's a huge market.

    It would be really awesome for these apps, esp. once they power gate it.
  • mattgmann - Tuesday, November 16, 2010 - link

    That's what I figured, but I think there are better options for those applications already in the market. Step in the right direction for via, but it's tough playing catchup to amd and especially intel.
  • ClagMaster - Monday, November 15, 2010 - link

    The DC Nano and VN1000 are fine achievements for VIA. Bravo !!!

    If they can get the process down to 40nm AND implement better power management, they would have a winner.

    At 40W, this is still an excellent low power performer for the cost.

    This could easily play DX8/9 games available 4 years ago on 1600 x 1200 resolution.
  • ckryan - Monday, November 15, 2010 - link

    I recongnize that some people may totally write VIA off in this market, but don't overlook the fact that an improved shipping model of this board could at least cause Intel to rethink its Atom strategy. I really wanted an Atom system for a while, but then I realized for the same price as the setup I wanted, an i3/gigabyte mini itx system would be about the same price. A stripped down Atom board from Intel wouldn't be worthwhile at all, even if it is $80. In the business and mobile spaces, Atoms make a good argument. Its just a stale argument. AMD and VIA bringing more options to the market can't be called a bad thing. My hope is not just that VIA doesn't fail entirely, but that I have lots of interesting options in the near future.
  • DanNeely - Tuesday, November 16, 2010 - link

    Intel definitely could use a chip midway between the current atom and CULV product lines. The dual core atoms don't really help much; yeah they're better at decoding video that the GPU doesn't support, but the atoms general performance problems are single threaded in nature.

    Clocking the chip up to ~2.5ghz would probably help a good bit there but would probably blow the power budget out of the water.

    Intel's stated that atom will remain in order for at least the first 4-5 years, so we shouldn't expect this to change. With intel primarily aiming atom at Arm's market share something that adds a lot of complexity to the chip is probably out of the question anyway.

    A more efficient memory controller connection might help. The current implementation is on die FSB so there's definite room to improve here. How much this would help is something of an open question though. Outside of memory bound benchmarks the ~2x latency difference between the directly connected and on die FSB controllers in lga 1366 vs 1156 i7's wasn't very large; but as an in order CPU with a tiny cache memory latency is a bigger impact on the atoms performance, although this is partially balanced by it having a much lower load on the memory sub system due to is generally slow performance This might be the easiest place for Intel to speed things up though.

    Alternatively the runtime gap between atom and CULV isn't that large, it might be possible to push it down into the current atoms power envelope even at atom drops into the higher end part of Arms territory.
  • danacee - Monday, November 15, 2010 - link

    I remember reading an article last year from digit life that you can get some pretty massive performance gains on a Nano just by tricking your windows install into thinking its Intel. Seens the code handed to the nano is pretty shoddy even next to AMD.

    Anand, to get a true representation of the nano's performance I'm afraid you will have to do a cpu-z hack.
  • danacee - Monday, November 15, 2010 - link

    found it;

    http://ixbtlabs.com/articles3/cpu/via-nano-cpuid-f...
  • sprockkets - Monday, November 15, 2010 - link

    Why is there a "ATI Radeon HD 5450" in the power consumption graphs? That makes no sense. Where is the Athlon X2 3250e?

    Should compare the processor in this system, the Neo X2, if different:

    http://www.newegg.com/Product/Product.aspx?Item=N8...
  • yuhong - Monday, November 15, 2010 - link

    "Despite the typical omg-thisisntATI/NVIDIA error that some games always throw,"
    NT 4's CPUID code was full of such problems:
    http://geoffchappell.com/viewer.htm?doc=studies/wi...
    Even more recently, 64-bit Windows has a hardcoded list of CPU vendors it will run on, and will BSoD with UNSUPPORTED_PROCESSOR on any other vendor. An update had to be released to add CentaurHauls to the list.
    Is there an option in the BIOS to fake a GenuineIntel CPU vendor?
  • Oxford Guy - Tuesday, November 16, 2010 - link

    A fair and competitive marketplace!
  • mschira - Monday, November 15, 2010 - link

    The complete Via CPU story - long before they named it Nano - is essentially a story of not delivering.
    All these jesaya and what not platforms one could never really by them.
    And yes Nano looks nice, the single core one didn't look to bad a year ago. But where is anything build with it that one can buy?

    More competition? Great! but please make it to market.

    Maybe now is the time Nvidia buys VIA.
    M.
  • jo-82 - Tuesday, November 16, 2010 - link

    Sorry, but my old Epia C7 sucks only 25W from the socket, and its fast enough for the job.
  • LoneWolf15 - Tuesday, November 16, 2010 - link

    When VIA comes out with a product, I really want to like it, and I want them to succeed. I actually got a cheapie notebook for a parent with a C7-M processor that worked well for quite some time until their needs grew. That said, here are my two issues.

    "I should add that although the Chrome 520 GPU does support H.264 acceleration, I couldn't get it working with the driver drop I had on my test platform. CPU utilization would be low but I still dropped frames. I suspect this is a driver or software compatibility issue which I do expect VIA to rectify before the platform ships."

    VIA (or should I say S3) has had many times where a graphics driver with bugs or compatibility issues that have delayed a product's potential after its release until it is no longer competitive with newer offerings. If the bugs aren't fixed at initial product release (I hope they are, but from experience...) that would be a huge strike against this.

    "The DC Nano platform I tested is built on an old 65nm manufacturing process at TSMC. As a result, power consumption isn't that great. Also note that VIA doesn't do any power gating, so idle power ends up being very similar to Clarkdale"

    If the Nano had power consumption that beat AMD but lost to Intel, I think we'd all be excited. Heck, if it matched AMD but with lower heat output, I think I still would be. However, we're looking at a product that cannot beat a Core i3 in performance, that equals it in power consumption. I think not doing power gating is a huge mistake here.

    I hope the released product has the driver issue fixed, and I hope VIA can consolidate their architecture (i.e., turn a 2-core Nano into an SoC or at least a partial SoC) for power savings, lower expense, and maybe performance improvement. That said, I'll also believe it when I see it.
  • East17 - Tuesday, November 16, 2010 - link

    AMD delivered and even exceeded their promises with Zacate. It's a very good solution that mops the floor with Atom and sometimes, especially when IGP is involved, mops the floor even with Core i3 that is a CPU much more expensive with an expensive platform. What's amazing is that Zacate's best competitor is not Intel Atom but VIA's Nano & VN1000 chipset. Congratulations to both AMD and VIA. I think they should really take over the "power efficient market" and just banish INTEL with its expensive, low quality and low performance part.
  • chukked - Tuesday, November 16, 2010 - link

    can anyone please tell me why can not nvidia take over via and make their own x86 cpu? as via has right to make x86 cpu.
  • UrQuan3 - Friday, November 19, 2010 - link

    I want to thank Anand for testing video playback on the platform. It's entirely too often that only encoding is tested. If I have a htpc, playback is all I really care about. If Via gets that working, I'll be buying one. If not (like the last 4 Via chipsets) it's a no go. In my experience, the Nano can only handle 720p playback in software.
  • General.TerroR! - Saturday, November 20, 2010 - link

    Things would have a bit more interesting, if there was an inclusion of the similarly clocked Atom D525 @ 1.8 GHz, in all the tests.

Log in

Don't have an account? Sign up now