Live data from Hacker News

The Economist on Intel versus ARM

economist.com

21–30 of 31 posts

Re: The Economist on Intel versus ARM

#21
post #20

I find it super interesting that Microsoft (in 2010) bought an ARM architecture license. I think it will be interesting to see what they do with it (if anything). http://www.eetimes.com/electronics-news/4204863/Microsoft-ta...

The next release of Windows will run on ARM. This is a key point in the article.

Re: The Economist on Intel versus ARM

#22
post #17

Interesting factoid: "Between them they shifted perhaps 8 billion ARM-based semiconductors in 2011, half of them in mobile phones and mobile computers, the other half embedded in consumer items and elsewhere." "According to IDC, a research firm, the market for PC-powering chips that use Intel’s x86 processor architecture, which Intel dominates, was about 400m last year." 8 billion ARM chips to 400 million x86. I hadn…

It's a terribly apples-to-oranges number. Starting with the basics, there's simply no such thing as an "ARM chip". Essentially all of those 8G units are SoC chips where the ARM core(s) make up a comparatively small fraction of the die area. Most of those SoCs actually have multiple ARMs actually, using smaller cores as asymmetric multiprocessing (c.f. the "baseband" CPU on most android phones), but they're mixed in w…

Also there are an awful lot of ARM7, ARM9, Cortex-M, etc. cores in microcontrollers and that market is very different from where Intel is competing.

Re: The Economist on Intel versus ARM

#24
post #19

I posted this article to my blog back in 2010, "The End of x86?" - http://fernstrategy.com/2010/10/21/the-end-of-x86/ . It's an analysis of how ARM is disrupting the x86 architecture (along with Intel). For the last several decades the x86 architecture, with its major proponents Intel and AMD, have dominated the CPU market in personal computers (PC). Today, Intel and AMD control 80.4% and 11.52%, respectively, of the…

> The current technology is overshooting the needs of the mass market.

I was actually thinking of starting a thread about throwing away computers: does anyone else find it hard to throw away old computers these days? I have a core 2 duo sitting on my desk right now, in the box. I can't convince myself to put it in anything, yet, I can't throw it away. I feel like I'd be throwing a way a supercomputer.

Re: The Economist on Intel versus ARM

#25
post #19

I posted this article to my blog back in 2010, "The End of x86?" - http://fernstrategy.com/2010/10/21/the-end-of-x86/ . It's an analysis of how ARM is disrupting the x86 architecture (along with Intel). For the last several decades the x86 architecture, with its major proponents Intel and AMD, have dominated the CPU market in personal computers (PC). Today, Intel and AMD control 80.4% and 11.52%, respectively, of the…

> The current technology is overshooting the needs of the mass market. I was actually thinking of starting a thread about throwing away computers: does anyone else find it hard to throw away old computers these days? I have a core 2 duo sitting on my desk right now, in the box. I can't convince myself to put it in anything, yet, I can't throw it away. I feel like I'd be throwing a way a supercomputer.

Which cpu is it? A lot of computers are still on LGA 775 (socket T), like the Pentium D. So it could easily be a drop-in replacement for some older CPU. I would gladly take it off your hands if you lived near me.

Re: The Economist on Intel versus ARM

#26
post #17

Earlier quoted context omitted.

It's a terribly apples-to-oranges number. Starting with the basics, there's simply no such thing as an "ARM chip". Essentially all of those 8G units are SoC chips where the ARM core(s) make up a comparatively small fraction of the die area. Most of those SoCs actually have multiple ARMs actually, using smaller cores as asymmetric multiprocessing (c.f. the "baseband" CPU on most android phones), but they're mixed in w…

Also there are an awful lot of ARM7, ARM9, Cortex-M, etc. cores in microcontrollers and that market is very different from where Intel is competing.

Don't forget the high-end FPGA's, too - that's where ARM's licensing gives them a decisive advantage (not least because if you're using one of them to prototype something, you will end up producing your ASIC with licensed components from ARM anyway.)

Re: The Economist on Intel versus ARM

#27
post #20

I find it super interesting that Microsoft (in 2010) bought an ARM architecture license. I think it will be interesting to see what they do with it (if anything). http://www.eetimes.com/electronics-news/4204863/Microsoft-ta...

The next release of Windows will run on ARM. This is a key point in the article.

Unfortunately, Economist fails to mention that Windows was once ported to Alpha, MIPS, and PowerPC -- all RISC processors.

Re: The Economist on Intel versus ARM

#28
post #3

Technology reporting at the Economist can be hit-or-miss, but this was a surprisingly informative read.

It was an interesting read, but the writer seems a bit uninformed when he forgets to mention the other CPU platforms which are dominant in their markets, such as PowerPC (PS2, XBOX 360 and Wii). Also, no mention whatsoever that Intel actually used to have an ARM license.

Re: The Economist on Intel versus ARM

#29
post #27

Earlier quoted context omitted.

The next release of Windows will run on ARM. This is a key point in the article.

Unfortunately, Economist fails to mention that Windows was once ported to Alpha, MIPS, and PowerPC -- all RISC processors.

These were to run Windows. The tablet is a different well-defined market. I'd run a MIPS desktop but most people won't.

Re: The Economist on Intel versus ARM

#30
post #5
post #4

>Using a three-dimensional chip design Intel plans to shrink that even further over the next couple of years, to 22nm and then 14nm, and sell chips that beat the competition on both energy-efficiency and performance. /facepalm. The rest is pretty good, though, I think.

What is wrong with that statement? Intel is using a new 3D Tri-Gate Transitor tech for 22nm & have plans for 14nm in the future.

It makes it sound as though you need 3D to shrink the chips. I don't think that's the case. I don't like calling a 3D component a 3D chip design, either.
Post reply on HN