Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

X86's Days as a Consumer Microarchitecture are Numbered

plus.google.com

Post reply on HN
Print view View original

21–30 of 81 posts

Re: X86's Days as a Consumer Microarchitecture are Numbered

#21

Post by microarchitect »

stephenjudkins wrote: post #15

This is an largely vapid and meaningless prediction by someone who doesn't demonstrate anything but the most superficial knowledge of the microprocessor industry. Perhaps he knows something we don't, but as far as I can tell he's only extrapolating current market trends. Obviously Intel (once led by Andy Grove, author of "Only the Paranoid Survive") is aware of the threat posed by ARM. If someone could explain how In…

One thing that could work against them is their cost structure. Intel is used to throwing a thousand or so engineers on each design. Having so many designers means they can squeeze out every last MHz, but it also means they need big margins and large volumes to recoup their costs.

The other big technical issue is the end of Dennard scaling. For most of the last three decades, scaling CMOS processes bought you three things: more transistors, higher frequency and lower power. Things are different now. We can't really scale frequency any more because we've run into the power wall. We used to get lower power at the same frequency by scaling the supply voltage, but this also required us to scale the threshold voltage (a device parameter). Unfortunately we can't scale the threshold voltage willy-nilly like in the past because leakage power increases for lower threshold voltages and is now a significant contributor to total power. We still get more transistors per unit area, but it's not clear whether the economic costs of building up new fabs and switching to a new process are offset by the benefits of having more transistors to play with.

The bottomline is that it's not clear whether Intel's biggest competitive advantage, that of having a manufacturing process superior to everyone else, is still that much of an advantage.

PS. One thing I find truly amazing is that Dennard predicted that we'd run into all these problems back in his landmark paper in 1974!

Re: X86's Days as a Consumer Microarchitecture are Numbered

#22

Post by nextparadigms »

haberman wrote: post #11

This reads like a person who has been saying "RISC beats CISC" since the Apple-on-PowerPC days because of ideological opinions about elegance, and is looking for any excuse to re-express that viewpoint. Look, I still think microkernels are better than monolithic kernels, but you don't see me claiming Linux is doomed just because the L4 microkernel is running on 300 million mobile phones worldwide ( http://en.wikipedi…

Things are a lot different now than they were back then. The fact that ARM keeps growing at a very fast rate is very real. ARM will be in billions of smartphones and tablets and who knows what other kind of devices in a few years. If people start using those devices more and more instead of x86 PC's (including ARM PC's), then it's over for Intel.

ARM doesn't have to beat Intel in raw performance. They just need to make them irrelevant to most people. And they are succeeding.

In a classic disruptive innovation fashion, Intel will (continue) to move up market, in servers and super computers, where it will be more profitable for them and where ARM won't be able to reach them (for now). This will become obvious when ARM-based Windows 8 and OS X computers will become available at the end of next year or in 2013. As soon as that happens, laptops will start becoming a low-margin business for Intel.

As a "normal" person, why would you get a $1000 ultra-book, if a similar looking Transformer-like device will be available for $500, and have almost the same "perceived" performance. Dual core and quad core 2.5 Ghz Cortex A15 chips will show how that kind of performance is enough for most people.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#23

Post by dman »

stephenjudkins wrote: post #15

This is an largely vapid and meaningless prediction by someone who doesn't demonstrate anything but the most superficial knowledge of the microprocessor industry. Perhaps he knows something we don't, but as far as I can tell he's only extrapolating current market trends. Obviously Intel (once led by Andy Grove, author of "Only the Paranoid Survive") is aware of the threat posed by ARM. If someone could explain how In…

Also the beginning of "good enough" performance? In recent years client side software has not generated any new breakthroughs that require vast amount of computing power. Most opengl v2 + games look more or less the same, raytracing hasnt taken off inspite of intels best efforts and there are multiple solutions to do video decode in hardware. I think intel sorely needs something to come along that causes regular users to want to pay top dollar for top performance.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#24

Post by grannyg00se »

feralchimp wrote: post #12

"Performance per watt" is great, but when I step within 2 meters of a power outlet I want "performance." And many machines (including laptops) spend their lives within 2 meters of a power outlet. At what point did "consumer" start meaning "low end" or "handheld"? The 27" quad-core i7 iMac is a consumer computer. Gaming PCs are consumer computers.

Probably around the same time people started predicting the end of the PC era as smartphones and tablets took off.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#25

Post by wtallis »

stephenjudkins wrote: post #15

This is an largely vapid and meaningless prediction by someone who doesn't demonstrate anything but the most superficial knowledge of the microprocessor industry. Perhaps he knows something we don't, but as far as I can tell he's only extrapolating current market trends. Obviously Intel (once led by Andy Grove, author of "Only the Paranoid Survive") is aware of the threat posed by ARM. If someone could explain how In…

One rule of thumb I've seen writers on Anandtech express several times is that any given microarchitecture can cover at most about one order of magnitude for power consumption. This leads to laptop/desktop-oriented microarchitectures that can scale at most from about 13W to 130W by tweaking clock speeds and voltage. More recently, the high end has dropped down to at most about 95W for non-server chips, but it still means you have to go back to the drawing board before you have a CPU that can work in tablets and smaller devices.

So far, Intel has shown that they aren't very good at simultaneously developing two parallel product lines of CPUs. Their tick/tock strategy of alternating process shrinks and microarchitecture updates has been working great for years, but Atom has clearly been neglected. Prior to that, they had the P4 NetBurst architecture and the P6-based Pentium Ms on the market at the same time, but NetBurst hit a wall and the company lost a lot of ground to the Athlon 64 before they could come up with a high-performance successor to the Pentium M.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#26

Post by bryanalves »

I think in a lot of ways this is related to the relative overpowering of desktop computers for daily use. It's been true for years now that computers are highly overpowered for what they are typically used for.

Quad core machine with a million gigs of ram for email and a web browser?

Sure there are LOTS of good reasons for having legitimate CPU power, but a lot of times any random Ghz level processor is going to provide plenty of responsiveness for daily tasks. The only thing I can think of that people typically do that is processor intensive is HD playback, and that is easily accelerated nowadays.

It's not always about absolute performance, it's about "good enough" performance. If ARM is going to supply good enough performance with the additional benefits of being cheaper and more portable, then why NOT use it?

This isn't about ARM versus Intel. This is about having adequately powered portables.

Intel is losing the low-end CPU market. That much is true. But the low-end CPU market is the new middle-end CPU market. I think we are going to see an age where more and more people have "low-end" portables as their main computers. The barrier between low-end, middle-end, and high-end has shifted significantly I think. A few years ago, we all had uses for high-end computers. Nowadays, what would be considered high-end is a waste for most people.

Also, we can't forget the impact of the cloud on this. We don't need a lot of computing power locally now. For many of the types of applications that one would need high cpu for, the cloud potentially provides those solutions for us.

I, for one, don't see myself trading in my desktop at work anytime soon. But I do see myself using my laptop a lot more than my desktop at home. My couch is a lot more comfortable than my computer chair.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#28

Post by divtxt »

pbharrin wrote: post #13
CPlatypus wrote: post #10

Earlier quoted context omitted.

6x the performance . . . for 8.5x the TDP. It's pretty easy to see why ARM designs are already preferable for almost anything that has a battery, and laptops are outselling desktops already. Sure, there will always be applications where single-thread performance will matter more than total performance or performance per watt for many cores - believe me, we learned that lesson at SiCortex - but those applications are…

I will take 6x the performance for 8.5x the TDP. My 3 year old MacBook Pro has plenty of battery life for my use case. You have to look at absolute performance numbers for the application.

The only thing I use that causes the fans on my Core 2 Duo MacBook Air to kick in is Flash, so I would definitely consider a slower CPU.

Also, note that the savings/benefits can be in ways other than more battery life e.g. price, fanless & sealed cpu, etc.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#29

Post by shasta »

feralchimp wrote: post #12

"Performance per watt" is great, but when I step within 2 meters of a power outlet I want "performance." And many machines (including laptops) spend their lives within 2 meters of a power outlet. At what point did "consumer" start meaning "low end" or "handheld"? The 27" quad-core i7 iMac is a consumer computer. Gaming PCs are consumer computers.

Presumably you still care about "performance per dollar" though, and we're approaching a time when "dollars per Watt" isn't negligible.

Re: X86's Days as a Consumer Microarchitecture are Numbered

#30

Post by andrewmunn »

stephenjudkins wrote: post #15

This is an largely vapid and meaningless prediction by someone who doesn't demonstrate anything but the most superficial knowledge of the microprocessor industry. Perhaps he knows something we don't, but as far as I can tell he's only extrapolating current market trends. Obviously Intel (once led by Andy Grove, author of "Only the Paranoid Survive") is aware of the threat posed by ARM. If someone could explain how In…

Hello, I'm the author of this article. I do not have a degree in electrical or computer engineering. I'm merely stating the trends I've seen in the PC industry over the last few years.

I am, however, a Software Engineer. I know that most of the perceived lag on a modern desktop is not due to the CPU, but inefficient I/O to the hard disk or network. One must only look at the iPad 2 too see that's very possible to make a fast computer with beautiful 60 FPS animations and snappy applications using only an 800 MHZ dual core ARM CPU. Ironically, my iPad feels way faster than my Macbook Pro most of the time.

You don't need to be an expert in the microprocessor industry to know that the CPU performance race is over. It's all about power consumption now, and X86 fails miserably at lower power computing. Unless you know something I don't.

Post reply on HN