New VIA x86 CPU Takes Aim At Intel Silverthorne

Kaz writes "While not operating on the same scale as the two major CPU designers, VIA has been gaining traction in the world of UMPCs and thin clients with its Eden and C7 lines of processors. While past architectures have been considerably out-of-date in terms of modern features, the new Isaiah architecture looks to be very competitive with what AMD and Intel have lined up for future ultra-mobile products. It features an out-of-order, superscalar execution core, 64-bit support, virtualization, and even SSE3 — all on a 94M-transistor, 65nm process die. The initial offering will be single-core only, though VIA says that multi-core ability is already designed in. Is Isaiah going to replace your Core 2 system for gaming? No, but it might give Intel's Silverthorne a run for the money."

Comments

Follow The Trend

[dsginter]

The next big step in integration is integrated memory. Cache memories are consuming most of the die in your typical high-performance CPU, these days. If you can find a CMOS-compatible, high-density (e.g. - SRAM's six transistors per cell is toooo big) memory technology, then we're going to be at the point where we can simply replace the cache memory with on-board memory. If said on-chip memory technology is nonvolatile, then we're talking panacea cakes, batman.

Naturally, this will first occur in low-performance devices where huge amounts of memory are not necessary. Then, it will work its way into the PC and up from there.

This is why Intel is divesting itself of discrete memory technologies - they don't want to be holding the bag when they're obsoleted by on-chip memory.

SPU manufacturers had better be ready for this because discrete CPUs will be going the way of the horse and buggy if anyone can ever do such a thing.

Re:Follow The Trend

[maxwell demon]

I re-read the post you replied to several times, but couldn't find the place where it advocated replacing the cache memory with DRAM. Instead it was about new memory technology yet to be found. Here's the relevant quote, with emphasis by me:

"If you can find a CMOS-compatible, high-density (e.g. - SRAM's six transistors per cell is toooo big) memory technology, then we're going to be at the point where we can simply replace the cache memory with on-board memory. If said on-chip memory technology is nonvolatile, then we're talking panacea cakes, batman."

I'm interested to see your non-volatile DRAM. :-)

OK, I grant you that he didn't explicitly talk about performance requirements. However, if he considered DRAM as sufficient, why would he have asked for new memory technology?

Re:Follow The Trend

[Waffle Iron]

The CPU is way faster than RAM.Replacing the cache (which is large physically compared to RAM) with normal DRAM would be a disaster for performance.

That doesn't necessarily matter if the DRAM were freed of external pin packaging constraints. For example, imagine if the CPU had an SRAM L1 cache, no L2 cache and on-chip DRAM main memory. With DRAM, you can internally access an entire row at one time. Using row-wide access, you could fill entire virtual memory pages into the L1 cache in a single RAM cycle.

Getting the most out of such a setup might require changes to the way the memory and cache have been managed for the last 20 years, but the total potential bandwith available from on-chip DRAM could be staggering.

Re:Follow The Trend

[imroy]

Cache memories are consuming most of the die in your typical high-performance CPU, these days.

On single-threaded CPU's, perhaps. But look at the Sun UltraSPARC T1 and T2. They are multithreaded - each core rotates between up to four threads on each clock cycle. When a cache miss occurs, it simply pulls the affected thread from rotation and continues with the remaining threads while fetching the data in the background. This means cache misses have a much smaller impact on performance than they do on single-threaded CPU's. Thus they need much less cache to maintain performance and throughput.

Putting main memory on the die just isn't practical, except for application-specific embedded microprocessors. It would be expensive and wouldn't actually give you much of a speed increase. Cache is a way of using a small amount of fast memory to speed up some slow memory. The nice thing about it is that the speed increase is out of proportion to its size because of common access patterns. And it's transparent.

Sorry, brother.

[RightSaidFred99]

"The current C7 processor is a sub 20 watt product.."

Then if I read right they go on to say Isaiah will be similar. Sorry, but that's not even in the same league as Silverthorn. Silverthorn will be more like a sub 5 watt product. If this is right, they'll be competing against Core 2 processors and performance won't even be close.

Re:Sorry, brother.

[glop]

Google says:
Support VIA C7 @ 1.5 GHz D (TDP 25 W). VIA C7 @ 1.5 GHz (TDP 12 W). VIA C7 @ 1.3 GHz (TDP ... VIA C7 @ 1.2 GHz LV (TDP 7 W). VIA C7 @ 1.0 GHz LV (TDP 5 W)

So the C7 can be a 5W part too. Which is not too bad for a 1GHz CPU.

I guess the ISAIAH will have such a version too. Sounds interesting, doesn't it?

Re:Sorry, brother.

[bhtooefr]

Except Silverthorne's architecture is a lot like the C7's, and Isaiah (which is what we're discussing) is a lot like the Core 2.

Re:Sorry, brother.

[RingDev]

VIA's Pico-ITX full systems (not just the chip) have already by clocked at 14w idle, 16w max in pre-release reviews from 6 months ago. The previous generation C7s can easily be throttled back to stay at 5w on the proc as needed. I'm not sure if such functionality is available on the new Pico systems though.

Intel is "shooting for" a 5w processor (no clarification if this is max load, or idle) in 2010.

VIA's Pico-ITX is already available at 1ghz, and the previous generation C7's are available up to 2ghz.

Intel's Silverthorne processor is also aiming for the Pentium M era performance (900mhz - 2.3ghz).

Yes, the initial Silverthorne release is slated for Q1-Q2 2008, but the performance goals you mentioned aren't slated until 2010. So what I'm saying here, is that you can already buy everything that Intel is "shooting for" 2 years before they plan on reaching those goals. With all likelihood, the 2008 release of the Silverthorne will be a 1ghz proc sucking down 20w at peak. Which will put it right in competitive range of the C7 and new Pico-ITX.

-Rick

Re:Sorry, brother.

[Anonymous Coward]

As someone who has worked on Silverthorne for the past couple of years, you will be very pleasantly surprised as to how fast and how low power it will be. If you are expecting 1GHz and 20Watts, you are in for a huge surprise. You are in for an even larger surprise to see the idle power. There were many Silverthorne based mobile internet devices showcased at CES, and those developers can testify to the power and performance that they are seeing with actual silicon. Cheers!

Re:Sorry, brother.

[RightSaidFred99]

You're full of it. Silverthorne is due for Q1-Q2 2008, 1-2 watts, and Pentium 3 performance circa 2004 (which still puts it well ahead of what Via is doing anywhere within 10x that much wattage).

My first clue you were full of crap was this: "Silverthorne will be a 1ghz proc sucking down 20w at peak". I'm not sure if you pay attention, but Intel has Core 2 Solo chips running at 1.06/1.2Ghz that peak at 5.5 watts. Silverthorne is a 45nm chip running on a simplified core-2-esque march, and you're making this ridiculous claim that it will "suck down" 20w at peak.

Seriously, 2006 called, it wants its news back.

Re:Sorry, brother.

[hairyfeet]

Yes, you might be right about pure performance, but I think you might be missing a big advantage with the Via. With the hype and fear of lawsuits caused from data breaches security is becoming an ever increasing concern, especially from a business standpoint. If this Via continues the tradition of its predecessors with its fast on-board cryptography this chip might be very appealing for business laptops and other small devices where data security is of high concern.

And after I RTFA it does have the on-board cryptography, and according to the article it will have double the performance of current Via chips. So this could be a very good chip for a low powered business laptop. I know that my P4m rarely gets above 600Mhz when I'm working on it, so I doubt that I'd even notice if you switched it with a Via. And having quick hashing and encryption/decryption would be a really nice feature if I had clients data on it.That's my .02c on the subject,anyway. Time will tell if Via has a winner or if it will be strictly a low end and hobbyist chip as it has been previously.

"out of date"?

[SuperBanana]

While past architectures have been considerably out-of-date in terms of modern features

They may not be bleeding edge, but their Eden processors used to compare very favorably to Intel's low-power chips, and have unique features like Padlock accelerated encryption (which is supported at least partially by the Linux kernel to accelerate cryptographic stuff.) Padlock made it possible to have a very low power VPN server..

The only real problem I've had with the VIA processors has been availability, pricing, and cheesy 3rd party motherboards. Mini itx dot com for example wants to bend you over backwards for some pretty old systems; the latest stuff you practically need to take out a mortgage from. You can't really buy the boards from but a handful of places. VIA also seems to be ignoring the networking market (if they sold a low-power board with 3 gigabit ports, they'd put Soekris out of its misery once and for all- overnight.)

Same thing with AMD's low-power Geode (which is plug-compatible with certain athlons.) You can't buy them anywhere except bundled with really shitty motherboards.

Re:"out of date"?

[Sly-Guy]

Take a look at the newer VIA VB7001G board. It may be the C7-D processor, but from logicsupply dot com it is $123. Not a hugely cheap board, but quite nicely priced for a mini-ITX board. The only drawback is that some of the cases cost almost more than the M/B itself!

Also the gOS boards are quite nice, though at micro-ATX are harder to fit in to a low power solution... I have two of these, one running my router with a dual Netflex-3 card (yeah I know, older 10/100, but I don't need any faster) and it runs quite well.

I'd be interested to see how this new chip/chipset combo works in say a HTPC and if it does HD content well. None of the current VIA Unichrome chipsets do HD very well.

Mark

Memories

[Tribbin]

Ooh I love this game:

http://www.pcper.com/images/reviews/511/isaiah_arch.jpg

I've got a C7 running a home email server.

[Vellmont]

While the performance is pretty slow (Maybe 800 mhz PIII range), it's low power and low heat, which was what I desired. Email doesn't require much processing power, so why waste the electricity on a high performance machine?

If they make a higher performance chip that get within the range of a Core 2, I'd consider buying one to replace my higher performance server in a few years. I hate paying for more electricity, and then paying to get rid of the waste heat. I'd even consider it for a workstation PC if the performance is good enough. Quiet fans are desirable to me, super-duper performance matters fairly little.

Re:I've got a C7 running a home email server.

[tknd]

For a while I was on a mission to build a really power efficient PC. Unfortunately when I got my AC power meter, I learned a number of disappointing things:

• Power specifications are incredibly hard to find. One good resource is actually Dell's specification sheets.
• Most of the inefficiency is in the power supply. In the past PSUs were made incredibly cheaply and even good brands were selling 70% or less efficient PSUs. When a system consumes 100 watts at the plug, that means 30 watts are wasted at the PSU. This has become a lot better with 80+ ratings, but you still have the issue where efficiency tends to drop as power consumption drops.
• The next big culprit is the video card. The best card I ever found was an ATI Radeon 7000 AGP. They still make them and the power consumption is somewhere in the low single digit watts. Other good options are probably Intel's onboard graphics chips. I think the latest intel integrated x3100 has a max draw of 9 watts (found it somewhere on dell's spec sheets).
• Another huge culprit is the motherboard. Motherboards these days come with everything. For something like a server you don't need the fancy soundcard. The fancy secondary raid chip is also probably useless. They simply don't make plain vanilla motherboards anymore. Also the chipsets (especially nVidia's chipsets) are horrible with power consumption. There are nearly no specifications available for motherboard chipset power consumption but from my experience it can be anywhere from 10 to 30 watts total.
• Laptop parts are the best. If you can build your entire server out of laptop parts, that would be ideal. Laptop parts usually have the right configurations for clocking down the CPU, not having a power hungry motherboard, and having efficient parts along with it (wireless, hard drives). For example a 2.5" laptop hard drive even while spinning will consume around 2 to 3 watts. A normal 3.5" hard drive on the other hand can suck 7 watts while spinning. I still haven't come close to beating my dell pentium M laptop in terms of power even with a Via Eden 600mhz system with nothing but a hard drive attached. The laptop would idle at 26 watts (screen off) while the Via would idle at 40watts.
• Todays CPUs (intel core, a64 single cores) are incredibly efficient. For example I was able to build a 45watt idle AMD64 single core system. The trick is you have to pick the other parts carefully. The board I have (Asus Via board, they no longer make it) allowed me to clock down the CPU to 1000mhz and lower the voltage.
• For really small server tasks, you may want to consider purchasing a wireless router and turning it into a server by using custom firmware like DD-WRT. Some wireless routers come with usb ports which will allow you to easily attach some flash memory for storage. Routers are also naturally headless so you don't have extra useless overhead from sound and video. To top it all off they come with 3 interfaces! One for the wan, another for the lan, and a wireless interface. What more could you ask for!

Competition is good

[fallen1]

I used VIA (and Cyrix) back in the days of Socket 7 and they worked reliably and well for me. I have not used VIA in any new configurations, primarily because I've been rooting for AMD and a long-time supporter of their CPUs. All that aside, I want to see VIA succeed and succeed admirably. Why? Because competition for Intel (and yes, AMD too) will only benefit the consumer in the long run. If the VIA processors force AMD and Intel to rethink their designs and then _innovate_ to keep up with (or keep ahead of) VIA then the consumers win, win, and win.

What could we get out of this? Loads, of course. One thing I'm not worried about is speed of the chips. Yes, faster CPUs are generally a good thing but I'd like to see more efficient chips coming out in all areas from the chip makers. I'd like to see less heat, less power usage under load, less standby power usage, reduced need for fans/cooling, and more along the lines of efficiency. More efficient chips, especially power usage, equates to less money I spend on utility bills or batteries or whatever. More money in my pockets, more efficient chips, more competition among the chip makers - big and small - all equals "the goodness".

My $.02 for the day...

Re:Power consumption?

[morgan_greywolf]

I want a fully recharged UMPC after two minutes of Seiko Kinetic shaking, baby! I think in your case, 30 seconds would probably be better. :-P

Re:Troll. Was Re:Follow The Trend

[morgan_greywolf]

You, and whoever last moderated the grand parent's post, aren't getting what he's saying.

What he means is: forget on-chip cache -- on-chip main memory. IOW, instead of having main memory on the motherboard, it would be embedded into your processor, running, presumable, at the same speed as the CPU.

If you follow the trends happening in CPUs, including this one, faster CPUs aren't the big issue. The real issue is the bus. The bus is slow. The more you put on the other side of it, the better. A CPU like this new VIA CPU might be slow, but if you had sufficient memory integrated right on the CPU die, it would blow the pants off your latest 4+GHz Core 2 Duo.

Re:Power consumption?

[MacarooMac]

What! And risk overheating my unit and suffering a premature installation?

all on a 94M-transistor

[sm62704]

Wow! A 94 meter transistor, that's one big transister! How big is the laptop going to be? Shades of Oldenberg!

-mcgrew
No spam for YOU!

Re:all on a 94M-transistor

[sm62704]

That's insensitive clod, you insensitive clod!

VIA processors and motherboards

[SCHecklerX]

I've had nothing but good luck with them. Combined with a mini-itx fanless case, these things make great appliances. Here's a great place to get them:

http://www.logicsupply.com/

At work, we used the mini-itx with fanless case for branch office VPN solutions using linux + openswan (which in turn connected back to checkpoint clusters as well as other branch office openswan gateways). At home, I have a VIA chipset m/b with an Athlon 3000+ processer which has been running great for me for a few years.

Overengineered against the Silverthorn

[Calyth]

The curious thing is that the Isaiah is heading towards OoO, whereas Intel's going to build the first in-order chip since the Pentium in Silverthorn.

C7 already has a good track-record for small form factor, low power, and providing acceptable performance at that category. IMO with the OoO they're heading more towards the laptop market, and I think they could've done something at least less conventional with the design.

Imagine that they modified the C7-M in-order execution core to a 4-way, fine grain interleaved multithreading, and have 2 cores. The existing C7-M has a short pipe, so pipeflushes aren't as penalizing. At the clockspeed that they're starting at (2GHz), each thread would have acceptable performance for your typical workload. And as OSes are becoming more thread happy (OSX is definitely one of them), such design would be at least something different than ordinary. It would be like having a cut down Sun Niagara in your laptop.

The current design would make it work decently well for low end laptop and desktops, but I can't help but think that the core now has a bunch of stuff that they can't exactly turn off - I haven't heard of a CPU that could switch off its OoO and retire queue, and the die size has increased significantly compared to the C7.

Open Video Drivers

[Doc Ruby]

These VIA CPUs and their motherboards would do a lot more good if their nVidia drivers were completely open. Quite a lot of the overall processing power is in the nVidia chip on the mobo. But when the drivers for Linux (and probably Windows, too) don't fully expose all the video features, the CPU has to do a lot more work preprocessing, at much lower efficiency than the nVidia chip can.

More like Core 2

[ravyne]

Actually, the new Via architecture shares a lot more in common with the Core 2 -- Its out-of-order, spends a lot of die space on speculation, has a fairly wide execution pipe, has something similar to the Intel's uOp-fusion and much more cache than the old C7. Its also prepped to go dual-core, but the company says that'll probably only happen once they go to 45nm. This has basically nothing in common with Silverthorn, which goes back to in-order, narrow execution pipe and smaller caches in the interest of saving die-space and power envelope. Of course, Via's chip is still focused on low-power, so it doesn't scale past 2ghz (at least at 65nm, they say) but its probably comparable to Core 2 on a clock-for-clock, core-for-core basis, give or take 20% or so.

The Summary kind of has it backwards, Via's new chip competes more closely with Core 2, while Intel's Silverthorn competes more closely with Via's C7 chips.

Re:Troll. Was Re:Follow The Trend

[volsung]

Agreed. Hopefully we'll see more of technologies like Z-RAM, which sounds like it has great promise. You get the speed of SRAM, but with only one transistor per bit, and greater density than DRAM. That should lower the power consumption significantly for current cache sizes, or allow much larger caches.

Even the C7 has "even SSE3"...

[TeknoHog]

but as the article said, this time it's more powerful. The C7 is not particularly strong because of its in-order execution core, and the new CPU appears to fix this.

For the record, my 2 GHz C7 machine can play a 720p h.264 video smoothly, but only without sound :) This is using MPlayer, no hardware acceleration except Xvideo.

Re:Troll. Was Re:Follow The Trend

[LWATCDR]

"What he means is: forget on-chip cache -- on-chip main memory. IOW, instead of having main memory on the motherboard, it would be embedded into your processor, running, presumable, at the same speed as the CPU."
  Memory on the die has been done in micro controlers for years. It isn't going to happen on PCs for a long time.

"A CPU like this new VIA CPU might be slow, but if you had sufficient memory integrated right on the CPU die, it would blow the pants off your latest 4+GHz Core 2 Duo."

What is sufficient memory? 4 GB or Maybe 512 MB? There is a reason that they use Static ram for cache. It needs to be fast. So lets say that you get 512 MB on the die are you not going to allow the user to add more memory? Or how about this. You put 512 MB on the die and then let them add memory on the buss if they need more. And then you could have it swap memory from the slower buss memory in to the fast on die memory to speed everything up... Yea and we could call it a cache!

Until you can put the full address space on the die it will not work for anything but microcontrollers.

Re:Open Video Drivers - ya, they suck

[Mike McTernan]

You're right. But the poster has as point. The Unichrome support is really bad on Linux. There are about 3 different drivers to try, all with differing results:

- The OpenChrome drivers, open source, some hw-accel support
- Unichrome drivers, open source but taking a purist approach that lacks features
- Via's own drivers, limited binaries for only certain distros, nightmare compile process, but most features supported

Unfortunately for me, I bought a VIA-epia ex1000 mini-ITX. It has some nice TV out connectors (component out!), so needs a driver that knows how to get this going. Having wasted a lot of time trying to build the drivers for FC7, I gave up and ended up using the Via binaries with FC5. The problem then is that other bits of hardware aren't detected under FC5, leaving me to patch PCI tables and rebuild the kernel to get the right southbridge driver (made a big difference to system performance - much smoother) and the SMBUS working.

Looking at forums I'm definitely not alone. This guy ended up with XP: http://cg-note.blogspot.com/2007/09/via-epia-ex1000-installation-adventure.html

Personally I think the problem is with Via. They claim to support open source, but throwing out the odd binary driver and giving mangled sources with not too easy to follow build instructions isn't much more than lip service. If they were serious, they could setup a yum repository for Fedora and make rpm's and debs for each major release of the distros they choose to support. Putting all the download packages on one page of their site would also help, as would openly releasing all their datasheets.

I hope they learn to do better, because I feel their products are held back by the poor Linux support :(

Mike

Re:Troll. Was Re:Follow The Trend

[LWATCDR]

"I don't claim to know a whole lot about processor tech, but I know that it wouldn't be hard to add this sort of optimization."
It is hard and it has been done. That is exactly what the cache does.
The tasks that need the memory the most stay in the cache longest.