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

41–50 of 81 posts

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

#41

Post by __david__ »

bryanalves wrote: post #26

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 prov…

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

I hear this sentiment a lot, and in general I agree, but the fact is the app with the largest RAM footprint on my laptop is Firefox. Given the proliferation of web-based apps, I don't see the complexity of web browsers going down. We can always use more power.

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

#42

Post by derleth »

Pinhedd wrote: post #38
andrewmunn wrote: post #30

Earlier quoted context omitted.

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…

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 Most perceived lag on a modern desktop comes from excessive abstraction which results in poor coding practices. You could certainly argue that IO bottlenecks or a lack of system resources will certainly have an impact but that impact wont be realized until the environment is somewhat satura…

Most perceived lag on a modern desktop comes from excessive abstraction which results in poor coding practices.

This is worthless without actual numbers, which I doubt you have. Hardware people blame software, software people blame hardware, as it has always been, so mote it be, amen.

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

#43

Post by sliverstorm »

bryanalves wrote: post #26

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 prov…

You seem to be operating on the assumption that an ARM CPU can match an x86 CPU in performance clock-for-clock.

While this may be true, it is not necessarily. Just pull out your old 4GHz P4, and see how it stacks up against your modern 3GHz desktop.

The point being architecture has come a long way for x86, and even if they match frequency, ARM will not necessarily come out of the gate capable of matching that.

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

#45

Post by sliverstorm »

georgieporgie wrote: post #27

Also, RISC is the Next Big Thing! By the way, Thin Client computing is going to kill the desktop, C++ and C are dead, Microsoft is killing Win32, Microsoft is dead, etc, etc. Flagged for no meaningful content and inflammatory title.

Also 2012 is the Year of Linux on the Desktop. :)

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

#46

Post by v413 »

derleth wrote: post #42
Pinhedd wrote: post #38

Earlier quoted context omitted.

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 Most perceived lag on a modern desktop comes from excessive abstraction which results in poor coding practices. You could certainly argue that IO bottlenecks or a lack of system resources will certainly have an impact but that impact wont be realized until the environment is somewhat satura…

Most perceived lag on a modern desktop comes from excessive abstraction which results in poor coding practices. This is worthless without actual numbers, which I doubt you have. Hardware people blame software, software people blame hardware, as it has always been, so mote it be, amen.

Here though it is not about blaming software or hardware people.

Here is what John Carmack talks about his troubles with the lack of PC performance due to the multitude of APIs to reach the hardware:

John Carmack: ... That's really been driven home by this past project by working at a very low level of the hardware on consoles and comparing that to these PCs that are true orders of magnitude more powerful than the PS3 or something, but struggle in many cases to keep up the same minimum latency. They have tons of bandwidth, they can render at many more multi-samples, multiple megapixels per screen, but to be able to go through the cycle and get feedback... “fence here, update this here, and draw them there...” it struggles to get that done in 16ms, and that is frustrating.

Later in the article John expands on the thick software problem.

The article is here: http://pcper.com/reviews/Editorial/John-Carmack-Interview-GP...

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

#47

Post by microarchitect »

miratrix wrote: post #39
microarchitect wrote: post #33

Earlier quoted context omitted.

This one cuts both ways though. With leakage dominating active power, within a given node, the fabrication process will be relatively more important than microarchitecture, which is a point in Intel's favour. This is kinda nitpicking, but I'm not sure leakage will ever dominate active power. We still have the ability to reduce leakage if we want, we just have to give up frequency for it. In the past we didn't have to…

Leakage power is actually very significant part of the total power usage [1] and one of the bigger reasons why Intel developed the tri-gate technology [2]. Active power is the one that's related to the frequency (P ~= CV^2f). Leakage power will "leak" even if the transistor is not switching. 1. http://www.eetimes.com/electronics-news/4215605/Leakage-powe... 2. http://realworldtech.com/page.cfm?ArticleID=RWT0505111954…

Not sure what you mean by significant, but typical leakage power numbers are something like 15-30% of total power.

Maybe you're referring to some papers that used to come out a few years ago which suggested that leakage power will dominate total power. As I said above, this is unlikely to happen. It doesn't make sense to operate at a combination of supply voltage (Vdd) and threshold voltage (Vt) where leakage dominates total power. I think these papers misunderstood the fact that threshold voltage and hence leakage itself is a knob that the device manufacturing folks can control.

Active power is the one that's related to the frequency (P ~= CV^2f). Leakage power will "leak" even if the transistor is not switching.

If you're implying that leakage power doesn't affect frequency, you are wrong. Transistor speed depends on the gate overdrive which, for modern velocity-saturated devices is proportional to Vdd-Vt. Leakage power itself is proportional to exp(-Vt). There is a clear trade-off here between how fast you run your chip and how much it will leak.

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

#48

Post by r00fus »

wtallis wrote: post #25
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 m…

>lost a lot of ground to the Athlon 64 before they could come up with a high-performance successor to the Pentium M.

You realize that Intel's EMT-64 is effectively AMD-64, right? Intel, which loathed that cross-patent deal, is now reaping AMD's rewards. Core2 and later series processors are all using AMD's intellectual property (legally).

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

#49

Post by zobzu »

nextparadigms wrote: post #22
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 ma…

that being said, since the recent multi core ARM cpus (hello tegra 3) have a TDP close to intel's atoms, and with the amount of engineering intel pushes into the mobile area, i wouldnt be too surprised if intel would actually beat arm as well in that area.

personally, i don't want a transformer device. the main reason is that it runs android and has little connectivity options. it cannot do anything CLOSE to what I do on the laptop. i own some tablets (!) and i rarely use them. i like to test stuff on them, and sometimes, browse the web or the like. but they're not very useful.

i like the phone better (its smaller!!) and the light laptop better (it does everything without compromises ! and im talking using word, the web, IM, etc, not coding. heck im+web and copy pasting around in android is such a pita. not even talking about getting a proper video out, or copying files on a usb stick.)

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

#50

Post by zobzu »

__david__ wrote: post #41
bryanalves wrote: post #26

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 prov…

> Quad core machine with a million gigs of ram for email and a web browser? I hear this sentiment a lot, and in general I agree, but the fact is the app with the largest RAM footprint on my laptop is Firefox. Given the proliferation of web-based apps, I don't see the complexity of web browsers going down. We can always use more power.

And Firefox is actually one of the most memory efficient browsers right now.

What people fail to see is that "just a browser" is a completely idiotic and misinformed statement.

Browsers are probably one of the _most_ complex and powerful app on the system.

Browsers are basically running entiere applications, virtualized, in a sandbox per tab!

Heck, some websites are just not viewable on mobile right now (unfortunately) because mobile jus't aint nearly fast enough. Think WebGL for example. Few mobile browsers support it, but when they do, its pretty slow if the author didnt make a super low polygon and texture count version...

Post reply on HN