Slashdot Mirror
VIA Nano CPU Benchmarked, Beats Intel Atom
Vigile writes "Back in May, when the Isaiah architecture was first disclosed, VIA declared a performance victory over Intel's upcoming Silverthorne technology. Since then, Isaiah has become the VIA Nano processor, and Silverthorne changed to the Intel Atom — and now we can finally see tests comparing the two technologies. The Nano's out-of-order super-scalar design is definitely an architectural leap over the Atom's in-order single-issue design, but with Intel including HyperThreading technology in their CPU the competition is closer than expected. The Nano does win the performance tests by a considerable margin, but what might be more impressive is seeing the Atom use only 4 watts of power under full load!" As reader Mierdaan points out, that's 4 watts more than at idle, for about 60 watts total.
Seems to me that the title is getting across the wrong message. These processors are meant to be placed in ultraportables, where battery life is a MAJOR factor. In that sense, the atom easily beat out the nano here, seeing as they used 4 watts and 18 watts respectively on a full load.
With that amount of difference in power required, it's pretty obvious the nano would beat the atom, but that's like saying a smart car with a V8 is going to beat one with a V4 when it comes to speed (except they should have been testing efficiency, where the V4 blows the other out of the water)
The atom doesn't use 4 watts under full load. It just used 4 extra watts. I knew that was too good to be true.
If you're not in a rush to get one of the Atom/Nano based computers, wait for the next generation. Although both CPU:s are excellent in performance, the next iterations will bring two cores and far better efficiency.
The first generation of any product line is usually fairly rushed and experimental. That does not mean the product itself is bad, but we should expect a big jump from the next generation.
Full Tilt
And how does it stand up agains a 2.6Ghz Intel Quad Core? Seriously does anyone else see this conspiracy? They couldn't make any faster CPUs so they decided the best business decision was to start over at like 400 MHz and then pretend be making amazing speed increases all over again when really all they're improving is power efficiency a little. Maybe Microsoft should do the same thing and toss 7 out the window and make a Windows 3.1 clone and then go to a 95 clone and soon they'll be back at an incredible re-release of XP!
Google's Super Secret Search Algorithm: SELECT @search_results FROM internet WHERE @search_results = 'good'
>It seems they may be measuring the whole system load in comparing the efficiency of the processors
I think that's more fair as it's what's relevant to me as a customer of the end product; the computer.
Problem with the Atom side is that the chipsets used are crappy and use more than twice the energy of the CPU itself. So while the CPU might look great on paper, the actual products that use it does not have the fantastic battery times that you'd like (10h+)
These CPUs should be compared together with a viable chipset and memory subsystem combination. Add that up and there's the number you're interested in.
Belief is the currency of delusion.
The 60 watts is what the entire system is using. That includes the hard drive, the RAM, psu, mobo, etc etc.
They get the 4 watts from observing that when idle the system is at 56 watts, but when at a full load it meanders over to the 60.1 watt range.
60-56 = 4
There's a clear future in little laptop machines that don't cost much and don't use much power, yet are powerful enough to do most of the things most users do with laptops. The low end x86 CPUs are finally good enough to power such machines.
The laptop manufacturers had a Detroit mentality of "more computer per computer". This kept laptop prices up and margins high. But, as it turns out, cramming enough CPU power into a laptop to run wind tunnel simulations isn't what users really need. Especially when the network connection is the bottleneck anyway. The actual uses for a 4-CPU laptop are somewhat limited.
The flood of low-cost laptops has just started. The EE PC set off a race for the bottom. In a year or two, laptops will come in blister packs at the drugstore, in the section with the calculators, electronic dictionaries, and other office supplies. From here on, it's all about lowering margins. Intel and Microsoft will be squeezed hard on price.
More benchmarks and analysis here: http://www.hothardware.com/Articles/VIA_Nano_L2100_vs_Intel_Atom_230_Head_to_Head/
...with the same findings.
http://arstechnica.com/reviews/hardware/atom-nano-review.ars
Engadget (or was it Gizmodo?) made an interesting observation that it's "pin-compatible" with existing C7-M devices, so a whole lot of currently-dodgy VIA-based mini-notebooks, like the HP Mini-Note (which desperately needs to run cooler and longer) can make the transition very smoothly. Well played!
No kidding!!! What do you say at this point?
For those of you interested, the Atom CPU really DOES use just about 4 watts at load. The 60 watts number is for the entire system including power supply, motherboard, DVD-ROM, hard drive, etc. Idle power on both of these parts is measured in milli-watts so you can see how much power each uses under load by looking at the power consumption graphs on page 8:
http://www.pcper.com/article.php?aid=597&type=expert&pid=8
The gap between rest (on the far left) and load (middle) is much greater for the VIA Nano processor than the Intel Atom - in fact you can barely tell the Atom processor has changed wattage at all.
The problem is that they don't know how much of that idle load is due to the CPU. You don't know whether that 4 watt difference is due to an efficient high power mode, or a really inefficient low power mode.
for instance, the nano might be 1 watt unloaded and 19 watts fully loaded, while the atom might be 20 watts unloaded and 24 watts loaded. This is clearly not the case, but would be consistent with the results.
http://notanumber.net/
I could have had a first post, too. :(
Via's been churning out processor's for years now - it's just that they don't target the average american desktop user. They make slower, cheaper, low power chips that were traditionally intended for very low cost computers sold in Asia (where in some of the poorer economies performance isn't so important as getting the cost down as low as possible), and now in mobile devices where the power consumption is a big issue.
I don't think you'll see Via competing with Intel and AMD in the mainstream desktop business anytime soon - that's a real but increasingly less important venue. People are replacing their computers less often these days (desktop processors have been "fast enough" for a good while now), and there is a big focus on mobile devices these days.
It certainly would be nice to bring back choice in desktop processors though. I remember way back when the Pentiums were on the scene, a customer generally had a choice between Intel, AMD, IDT, Rise, or Cyrix (sometimes marked IBM) processors. Further back in the 486 days you didn't have Rise or IDT but TI made x86 processors back then. The upside too was that back then, everything used the same motherboards/sockets, so going from one chip maker to another was trivial.
"People who think they know everything are very annoying to those of us who do."-Mark Twain
x86-64 and EM64T are the same instruction set.
I've upped my standards, so up yours.
The article writers don't seem to be very technical guys.
If we look at the energy efficiency, Atom hands Via it's bilblical arse.
Let's talk about Joules, the things a battery stores. Batteries are important. Especially for the target marget of these two CPUs. In fact, battery life is most likely THE most important factor in anything below a notebook.
Keep in mind a battery only has so many joules between charges, that's obvious, I know.
Now, an efficient architecture would only use as many joules as needed to get the job done in a timely manner. Joules per seconds are Watts, btw.
So lets look at how these two stack up in terms of Joule consumption and Performance based on this data...
The VIA requires about 17W of power to chug through MP3 encode, for about 460 seconds. That means the power supply had to deliver 17 * 460 = 7,820 joules.
Now the Atom crawled along 30% slower, about 600 seconds to complete. But it only needed a delivery rate of 4 J/s, so it ate 2,400 joules.
So for a 30% improvement in performance, VIA had to gobble down MORE THAN THREE TIMES the energy!
That means you could encode 3x as many MP3s on an atom, but it will take 30% longer. Imagine if this was an iPod. Who would trade 3x less battery life for such a tiny bump? That isn't something to brag about when you are targeting a market starving for battery life.
I'll be really surprised if Via goes anywhere other than a few cheap Asian design wins.
https://www.accountkiller.com/removal-requested
Back in May, when the Isaiah architecture was first disclosed, VIA declared a performance victory over Intel's upcoming Silverthorne technology. Since then, Isaiah has become the VIA Nano processor, and Silverthorne changed to the Intel Atom...
OK, let me see if I've got this straight. The VIA Isaiah beat out the Intel Silverthorne. Then the VIA Isaiah was renamed the Via Nano, and the Intel Silverthorne was renamed the Intel Atom. Now the VIA is still beating the Intel? So what you're telling me is that a name change has no effect on chip performance? Well, color me shocked!
When our name is on the back of your car, we're behind you all the way!
I'd say it's rather far from a tie when you consider more than simply power consuption.
As the story points out Intel is restraining board designers from using desirable technology on the Atom platform. No PCI Express, no DVI, no second memory slot. Theory is "Intel appears to fear Atom will cannibalize its Celeron sales". Perhaps. I'll bet VIA is more than willing to cannibalize those sales if Intel is going to let them.
The reference board in this review is nice. There are two ethernet phys, one of which must be gigabit. Compact Flash, mini-PCI and PCI Express. Damn. I like that board. That is the perfect board for the small, quiet home server.
Lurking at the bottom of the gravity well, getting old
I took my graduate level architecture class from Dean Tullsen at UCSD, who invented 'hyperthreading' although it was called Symmetrical MultiThreading (SMT) back then. As I recall the entire greatness of the architecture was recognizing that all the fancy hardware introduced to allow out-of-order speculative execution could actually be leveraged to allow the processor to drive multiple independent threads at the same time, without much additional overhead. So if intel's atom (haven't been following it) uses an in-order core and hyperthreading that just don't make much sense. Anyone care to provide an explanation?
I was liking both processors up until I found this gem in the article:
Here we see Intel, up to its obnoxious "You'll use our technology only as we prescribe" games. This is the same philosophy that leisurely milked the market for 33Mhz CPU bumps every 6 months, while they sat on years worth of better technology, until AMD lit a fire under their ass.
Don't be fooled again.
Reading through that article, I found this:
My my. Swap CentaurHauls for AuthenticAMD, and Nano's performance magically jumps about 10 percent. Swap for GenuineIntel, and memory performance goes up no less than 47.4 percent. This is not a test error or random occurance; I benchmarked each CPUID multiple times across multiple reboots on completely clean Windows XP installations. The gains themselves are not confined to a small group of tests within the memory subsystem evaluation, but stretch across the entire series of read/write tests. Only the memory latency results remain unchanged between the two CPUIDs.
Whoops! I wonder what they'll have to say about that...
I don't think x86 compatibility is a very useful feature for hand-held devices, or even for mini-laptops. Windows is fine on my desktop. I don't want it hogging the resources on my hand-held. When it comes to BSD/Linux, it's easy to recompile apps for a different platform. It's less easy to customize the apps for the smaller screens and lack of input devices, but it's not like that would be any easier for a Windows app.
Ultra low power combined with powerful graphics, on the other hand, is so much more useful. I may be a bit biased because I'm a 3D graphics/game developer, but great games and audio/video playback are incredibly desirable features on devices like this. And it's not like it won't be able to run a web browser, mail client, etc.
The energy star 5 standard requires 50 watts or less at idle, something the old C7-D platforms from via managed quite easily, are they including the display in the system power consumption perhaps, or just using shoddy parts in other spots?
Also, what is the power consumption of the lower end Nano processors? As I recall, the slower nano managed to (barely) outbenchmark the atom, it would be a much better platform to check power consumption against in this case.
I also point out that for these kinds of systems, 3D based benchmarks seem fairly useless, neither platform is targeted at gaming or graphics development.
Liberte, Egalite, Fraternite (TM)