VIA Nano CPU Benchmarked, Beats Intel Atom 279
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.
Misleading title? (Score:5, Insightful)
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)
Re:Uhmmm... measurements? (Score:5, Insightful)
>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.
Re:Wait for the next generation (Score:3, Insightful)
The current 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.
fixed it for ya
VIA has become a real threat to Intel (Score:5, Insightful)
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 [youtube.com] 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.
Re:Misleading title? (Score:5, Insightful)
I4. There are very few V4 engines, probably because it wouldn't be any more balanced than an inline 4 configuration, but would require much greater complexity. You could make a V4 shorter than an I4, which is why it's used extensively in motorcycle, but it'll cost much more to design and build.
You're bang on though. An Intel Extreme quad-core will eat a Via Nano for breakfast. You could probably emulate the Via Nano faster on the Intel Extreme quad-core than the Via will even go. The thing is, the Nano will last for an hour on the energy the Intel Extreme quad-core will use in a minute.
It's a tie (Score:3, Insightful)
What really bothers me is that the Atom setup seems to use as much power idle as under load. What's going on there? Did the benchmarkers forget to switch on power management or what?
The problem (Score:5, Insightful)
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.
Re:Interesting. (Score:5, Insightful)
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.
Wrong Benchmarks?? (Score:2, Insightful)
Re:Performance for full day battery life (Score:2, Insightful)
The Atom is a bit on the slow side. Like using ARM chips for desktop computing; so why not simply use an ARM chip?
x86 compatibility reasons?
Re:Interesting. (Score:3, Insightful)
Not long ago I only knew VIA as a chipset maker and a maker of chips for some other devices/things that weren't really "brand name" items.
Methinks you are a young man, sir. VIA used to be much more relevant than they have been in the last few years. However, it is very pleasing to see them picking up again and standing against the competition.
Re:Almost had me going there... (Score:5, Insightful)
That's the difference in power consumption between idle and load of the ENTIRE SYSTEM, as is clearly stated at the top of the chart.
The TDP on the most power hungry atom is only 4 watts.
Intel needs to pair the atom with an efficient chipset. Unfortunately any of the chipsets Intel currently has available to pair with the atom look like power hogs next to the atom.
Re:Performance for full day battery life (Score:1, Insightful)
x86 compatibility reasons?
Now why is this important today? I don't want or need x86 compatibility. Maybe it used to be the only game in town when Microsoft dictated CPU architecture but that isn't the case anymore.
What I want and need is power-sipping CPUs like MIPS or ARM in a laptop. Does anybody know what the hold-up is on this front?
Not a fair power comparison (Score:2, Insightful)
The board that Intel is currently selling is paired with a 945G *desktop* chipset. Probably to get it out of the door and reduce stock. That chipset uses 22 watts while the cpu uses 4 watts. When Intel finishes their Atom chipset, there should be a considerable difference between the two as far as power consumption goes.
Re:explaination of energy efficiency (Score:5, Insightful)
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.
And now for the elephant in the room: Why are you encoding MP3s while you're running on batteries?
The normal workload for an ultra-portable running on batteries is not producing MP3s. Its outputting static screens to a beamer during a presentation, or surfing the "series of tubes" [washingtonpost.com] via the local WiFi spot between classes (or waiting for the plane). If you've got numbers or MP3s to crunch, save it for when you've got the thing plugged in, silly!
Assuming the average CPU loading is going to be a paltry 2-3% (essentially idle), you're looking at a very capable system using an average of somewhere around 61W vs. a less capable system using only 56W. The difference in battery time between those two is barely significant, which makes the increased potential performance of the Nano a big win in my book. When plugged in, the Nano is a passable desktop replacement. The Atom, not so much.
Re:Wait for the next generation (Score:4, Insightful)
Although the Nano represents a new chip series for Via, they have dominated the "ultra low power x86 PC-class" market for almost a decade now. I wouldn't, therefore, call it a fair comparison to call them both a first gen-chip. The Atom, yes. The Nano... To put it in terms more familiar to an Intel-dominated market, the Nano as a "first gen" more closely resembles the P3 vs the P2... Same basic core with a few modest improvements and running at a higher clock.
The FP post provides a simple example of my point:
that's 4 watts more than at idle, for about 60 watts total.
A truly low-power (yet entirely usable) system depends on more than just an efficient CPU. If your chipset and GPU and RAM each suck down more than the CP under load, you may as well splurge a bit on the Watts and go for a beefier CPU, because you'll never really see the difference in terms of battery life (or the AC equivalent, UPS runtime).
Re:'Only' 4 watts? (Score:3, Insightful)
Re:Misleading title? (Score:5, Insightful)
Did you read the part where they measured total power expended to accomplish various tasks? Burning more power is OK if you can finish the job faster and get back into a low power state.
Their numbers are messed up, though.
The VIA system uses 17.4 more watts while under load than the Intel system. That means if they are under load for one second, the VIA system has used 17.4 more watt-seconds than the Intel. On the other hand, the Intel only uses 0.9 more watts under load than the VIA uses when idle. So, if the VIA works for one second, then drops back to idle while the Intel is still working to complete the task, it would take 18.33 more seconds before their total power usage becomes the same (17.4 + (-0.9 * 18.33) == 0).
This means that to use the same amount of power over the long term, the VIA has to be able to complete tasks in ~5% of the time that the Intel takes. Put another way, the Intel would take 19 times as long to finish any task.
But, their own graphs show that the Intel system only takes about 2 times as long (at most) to finish tasks. So, there's no way that the VIA uses less energy over the long haul, but that's what they claim.
Their problem is that they are comparing the total power used by the VIA system only while "active" on the task, and not looking at the power that the VIA uses on idle while the Intel is still completing the task. This is like saying that as soon as you finish that task, you immediately power off (or drop to standby).
Re:Misleading title? (Score:3, Insightful)
Although the theory is nice it assumes that you shut down the Nano after it finishes the task. Because the idle drain on the Nano is so close to the load drain on the Atom the theory breaks down. Assuming that the Nano machine sat idling for the remaining time it is still power consumption they did not include in the comparison.
Of course I'm still trying to get my head round the concept that I should buy Via for performance and Intel for power consumption...
Re:Wake me up when Tegra joins the race (Score:4, Insightful)
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.
Power consumption is rather high for both of them (Score:4, Insightful)
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.
Re:Misleading title? (Score:3, Insightful)
Speaking of the 35xx, check out Pandora [openpandora.org] for one example of what people are building with that chip. Heck, even last generation's OMAP2420 had enough oomph to run Linux with acceptable performance (Nokia N800/N810) and the 35xx is expected to be about 4x the speed.
Unless Intel gets their act together soon with Moorestown, they might find that the UMP market is eaten by Cortex-based ARM SoCs; at least the part of the market where x86 compatibility isn't important. One can at least hope, the Cortex certainly has enough performance for most tasks one would want to do with a handheld.
Re:Misleading title? (Score:3, Insightful)