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.
Wait for the next generation (Score:5, Interesting)
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.
Interesting. (Score:3, Interesting)
But lately I see them getting more and more into the CPU business. They start pushing out their own motherboards, with their own processors, graphics chips, everything. Not only that, but their processors are beating Intels and their integrated graphics are on par with Intels!
I think it won't be long until we see some real desktop processors for other motherboards coming out- I mean VIA CPUs for ASUS, Foxconn, Supermicro, MSI, etc., competing at the same level with AMD and Intel... I think it's about time, too. We have this underdog who we buy because they're our favorites and not because they're better, still on 65nm processors while Intel has released 45nm and is getting ready to push out 35nm and 25nm- It's time we get some real choice. Maybe we can have a favorite company who also makes the better products. Choice is good.
heh 32,000 watts of power?? (Score:1, Interesting)
someone seriously failed out of engineering school.
from TFA:
"For our MP3 encoding test, the VIA Nano processor used a total of 37,323 watts of power "
that's priceless.
morons.
In-order hyperthreading? (Score:4, Interesting)
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?
Re:Misleading title? (Score:2, Interesting)
Any 90 degree V configuration of two cylinders is going to have better reciprocating mass balance than any inline configuration of two cylinders.
So a V4 (assuming 90 degree V) is going to exhibit better mass balance than an inline 4. It is purely the complexity issue where an inline 4 wins.
A V configuration averages mass acceleration rates between the two cylinders. While one piston is at the point of minimum velocity (standing still) and entering an acceleration phase, the other piston is at a point of maximum velocity and entering a deceleration phase. The energy transfers between the pistons, leaving the combustion process purely to drive torque to the crank. If you draw this out schematically, you will find this velocity/acceleration relationship throughout the rotation of the crank.
This is good for two things. 1) smoothness and 2) responsiveness to throttle input at high RPM. At high RPM the acceleration rates are much higher because of the higher peak piston speeds, and the torque reaction to the acceleration cycle begins to compete with the torque generated by the combustion process, reducing the responsiveness of the engine to throttle changes. It becomes a signal to noise problem.
This is probably less of an issue for your "daily beater" but can make a difference in competition driving.
Yamaha did some excellent investigation work on this where they fitted an inline 4 engine with an offset crank so that the mass velocity cycle mimicked that of a V4. The were other issues that they had to do to make it work in inline 4 format, but the results were very good.
'Only' 4 watts? (Score:3, Interesting)
Am I supposed to be impressed?
The new Cortex-A8 ARM processor [arm.com] consumes 300mW; less than a tenth that of the Atom. The Atom is marginly faster, but not much so --- the figures I've found show that a Cortex develops about 2.0 Dhrystone MIPS per MHz, vs about 2.4 for the Atom. Plus, the Cortex is a CPU core, not a discrete chip; most actual products couple it with an on-chip OMAP DSP engine, which is ideal for doing things like video encoding or decoding or OpenGL. With Atom you end up having to couple it with a dedicated GPU...
Re:Misleading title? (Score:3, Interesting)
Re:Misleading title? (Score:3, Interesting)
Imagine that the HD uses 20W during the test. If the Atom takes 120s to complete it, that's 240 joules of the total that come from the HD; if the Nano takes 60s, that's 120 joules from the HD. My point is that, if you use a low power device, both lines would go down by the same amount, so the integral for the Atom would go down by more than the one for the Nano. This effect could be big enough to make the Atom more attractive.
Unfortunately, they decided to use a power hog to test the energy use of low power systems, making their test very flawed and, therefore, unreliable. I'll wait for a better test before making any conclusion.
Wake me up when Tegra joins the race (Score:3, Interesting)
I think all of this will be moot when the nVidia Tegra devices come out. That will be when I break down and buy either a mini-laptop or a hand-held device.
Platform choice (Score:5, Interesting)
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.
Biggers news: PCMark 2005 skews memory tests (Score:5, Interesting)
Reading through that article, I found this [arstechnica.com]:
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...
Re:Almost had me going there... (Score:1, Interesting)
Intel has a low power chipset: Poulsbo http://softwarewiki.intel.com/mid/Poulsbo. This is marketed together with Atom Z5nn series as Menlow platform for handheld devices (MID - Mobile Internet Device).
TDP for Atom Z5nn is even lower: 0.65 - 2.5W http://en.wikipedia.org/wiki/List_of_Intel_Atom_microprocessors#MID_processors_.28UMPC.29
Re:The 4 watts comment (Score:3, Interesting)
Re:Almost had me going there... (Score:3, Interesting)
For a lot of users one of the low power Semperons would be a better choice right now. The problem is they are not as sexy as the Atom.
Re:conspiracy (Score:4, Interesting)
Re:The problem (Score:3, Interesting)
Atom doesn't pull 20W at idle, TDP on the Atom cpu in that benchmark is afaik ~4W. Which means that pretty much all of that power drawn at idle is from the rest of the board.
One of the major culprits would be the i945 chipset, which comes in at about 20W. The rest would be RAM, disks, etc.
If we only look at the CPUs, notice that the Nano pulls about 5 times more wattage than the Atom but only manages to be 20-30% faster.
What this benchmark really shows is that putting a low-wattage CPU in a system is kinda silly if the other components in the system are watt-guzzling pigs.
It also means that a total system with an Atom and proper low-power chipset/ram/etc will draw about 16W less than a Nano paired with the same low-power components. Which means that the Nano simply can't be used in MIDs, while the Atom will do quite fine in that form factor when Intel gets a decent low-power north/southbridge out the door.
Re:Misleading title? (Score:4, Interesting)
The Via Nano is currently built on a 65nm process and the Intel Atom on 45nm so Via has some room if they move to the 45nm process.
Makes me wonder if building the Atom on 45nm is costing them production of high price multi-core chips in order to squeeze themselves into this UMP market before the sector solidifies more. And seeing things like the TI OMAP 35xx chips it makes me wonder when the UMP market moves off x86. There is already pressure to bump up the price of the UMP as to not take away from the lowend laptop market.
LoB
Re:Misleading title? (Score:3, Interesting)
You know why they did that don't you?
The atom has next to no features by itself. It really is a "dumb-terminal" amongst CPUs.
The Nano is capable of much more, even with its chipset. Namely, last I checked it's capable of playing h.264 at 1080p, and can play Crysis.