Speculations Intel's Next Generation

An anonymous reader writes "The Inquirer speculates about the next generation Intel chip. It's low power, 64 bit, multi core (up to 16?) and the real reason for the Apple switch."

Comments

But will it arrive in time

[Nom du Keyboard]

The article speculates that this is going to be the reason for the Apple switch, but...

If they're announcing an archtecture this radical at next week's IDF, what are the chances that it will be available and running well in time for Apple's announced timeline for desktops?

Or is Apple going to sell a lesser version first, in which case why haven't they already switched over to selling it to early adopters already. Yes there really are people who buy systems and wait for the applications to arrive later.

Re:But will it arrive in time

[Nasarius]

I think the people who are most disappointed are the Linux geeks who like playing with exotic hardware. No more cheap PPC hardware for us.

Rosetta

[shmlco]

If a VLIW X86 processor had a "native" mode, one would have to wonder if Apple's Rosetta technology could compile directly to it instead of X86. I mean, it would seem dumb to JIT-compile to X86, which in turn is translated to VLIW.

More information at Real World Tech

[Anonymous Coward]

There's a better explanation of why the Inq article's speculation is bogus here:

http://www.realworldtech.com/forums/index.cfm?acti on=detail&PostNum=3655&Thread=3&entryID=55310&room ID=11

I am so upset about 64 bit busses

[js7a]

The hidden Markov model Viterbi beam search algorithms that I depend on for my work run less than 50% as fast on 64 bit architectures than on 32 bit processors. Primarily, that is because of the fine memory access paterns, complicated locality issues, and probably other things that I am not really very aware of, such as less mature compiler technology.

In any case, the fact that everyone wants to jump to 64 without testing the waters very carefully first is seriously foolish. I know I'm not the only one who feels this way -- Microsoft's Windows speech recognition subsystem refuses to run on any 64 bit architecture unless all of the OS and applications are strapped to 32 bit mode.

This is possibly worse than five years ago when people were paying absurd premiums to go from 800 MHz to 1.3 Ghz with RAM speeds stagnant. At least then you got something more from algorithms which weren't memory access-bound. From 32 to 64 is a significant step backwards in many cases.

Re:I am so upset about 64 bit busses

[demachina]

I'd agree the 64 bit part is a bit overrated and bleeding edge for most applications, unless you are handling massive data sets. Video editing, simulation, circuit design, seismic all can use it. Of course all the supercomputing fields need it. I imagine some big databases probably can too. Some games will probably need it to in a few years. Film animators are about to the point they will need 64 bit address space if the software developers will take the plunge.

The best thing in the x86-64 API is they just added a lot more registers which are sorely lacking in IA32. 8 new registers and 8 SIMD registers can help performance a lot if you compile for them.

Are you compiling for and taking advantage of all the new registers?

They might have an even better chip if they had just tacked on the new registers on IA32 but since they were breaking the ABI anyway you can understand why they would go 64 bit since it has longer legs for the future. There are going to be more and more applications that will need 64 bit as RAM and disk capacity grows, and people start working with bigger data sets.

Running Gentoo on amd64 is a bit bleeding edge. There are still a lot of apps that are masked out for it, partially just because no one tests and owns them since the user community is still pretty small. I find most things work fine when you unmask them. I need to start volunteering to support the packages I use that no one has blessed for amd64.