Intrinsity Claims 2.2 Ghz Chip

PowerMacDaddy writes "Over at SiliconValley.com there's an article about an Ausin, TX startup named Intrinsity that has unveiled a new chip that utilizes a new logic process with conventional fab processes to acheive a 2.2GHz clock rate. The company is headed by former Texas Instruments and Apple Computer microprocessor developer Paul Nixon. The real question is, is this all FUD, will the real-world performance be part of The Megahertz Myth, or is this thing for real?"

Re:Moslo

[zulux]

I friend and I made a small video game, and being the better programer than me - my frind made a bit of code that estimated the speed of the computer and added a delay loop to the game to slow it down.

Fast forward to Today

We lost the complete source code, and our computers are so darn fast that the bit of code that estimates the speed of the computer over-runs it's 16 bit Int slot. The game now hangs hangs.

So we are forced to run our game in Windows to slow it down. It works half the time - it depends on the time slicing. Recently our computers are getting a bit to fast for even that - so we might have to move to an emulator.

The smart thing to do would be to fire up the hex editor and edit the cose, but that would be *cheating*

Re:Why is everything non-Apple a myth?

[Anonymous Coward]

you should read the anandtech article (i believe, might have been sharkyextreme or tom's hardware, but i think it was anand) about the spec tests. they do a very bad job as far as real world performance goes, and are easily as memory/cache bandwidth dependent as they are processor dependent. the article goes into a rundown and gives a better benchmark, as i recall. 2 or 3 months back.
anyway, if you want the real deal, look at the architectures and do some mental math. that G4 (the 9450) if completely optimized could do 4 times the number crunching in the same time as a p4. it burns more power, and has less bandwidth, but if you have something that runs native on the altivec units that's well-tuned, then there is nothing better, currently. Of course, if you aren't writing your own software for such things, and you aren't running one of the hundred or so altivec-optimized applications, then you're better off on an x86 platform, but if you aren't running one of those applications, then you probably don't need to be spending $1700 on a computer anyway -- a 1.4 ghz athlon is pretty cheap, after all.
but i digress. those benchmarks you point to don't tell you what you think they do, and any benchmark is going to lean more one way than another. sit down with the hardware and see what your money buys you, rather than point to some 10 year old tests that even the group that wrote them considers to be obsolete.

Comment removed

[account_deleted]

Comment removed based on user account deletion

Re:Why is everything non-Apple a myth?

[Anonymous Coward]

>Photoshop has been running on both Mac and >Windows platforms for years and years now. It >is optimized for Intel with the assistance of >Intel engineers. It is optimized for the Mac by >Adobe engineers all on their own. Oh, they got help from Intel's engineers? No wonder Photoshop is slower on Intel. My experience is that code I've written on Intel chips is MUCH faster than Intel's graphics processing DLLs. Even my none-MMX linear interpolated scaling routine was something like 5 times faster than Intel's "MMX accelerated" routine (I forget the exact number). But the reason for this is a mystery, because when I wrote an MMX accelerated my MMX version was also much faster than Intel's code. They must have left that DLL to a junior programmer.

Re:Why is everything non-Apple a myth?

[gig]

> Why don't they benchmark the mac with anything
> other than PS, ever, ever, ever, ever?

They also benchmark with Media Cleaner Pro, which is a very widely-used media encoding application. At this past Macworld Expo NY, a Mac with a G4/867 in it took a Spiderman movie trailer from tape to Web, and then played the result, well before the similar Intel machine (1.7GHz P4) could even finish encoding the clip. Same task, same media, same application, same RAM, same hard disk, same graphics adapter. Only thing that's different is Mac OS / Windows, G4 / P4 and the mobo. The machines even end up being equivalently-priced (I think they use Compaq workstations for these tests).

> How could anyone question the validity of an

> application that has always been primarily a mac
> application?

Photoshop has been running on both Mac and Windows platforms for years and years now. It is optimized for Intel with the assistance of Intel engineers. It is optimized for the Mac by Adobe engineers all on their own.

I work in music and audio, and it is very performance intensive ... all of your processing is done in realtime. The Mac runs music and audio apps faster, too. I get incredible performance in Cubase 5.0 on a PowerMac G4/733. You can fill up all of Cubase's plug-in slots and still have CPU power left over (there's a CPU meter built-into Cubase ... that's how CPU intensive it is). Latency is also better on the Mac, and that's very important in audio.

Video, music and audio, graphics, encoding and encryption ... the Mac is the best-performing machine for all of these. These are the tasks that Macs are BUILT FOR. It just so happens that everybody wants to do these things now, thanks to digital camcorders, cameras, MP3's and security. Doesn't magically make Intel machines any better than they are, no matter what the clock speed of the CPU.

Re:MHz

[gig]

> How would this be explained to the general public?

Compare actual performance, which means putting third-party applications onto demo computers at retail locations, and timing complete workdays and/or complete tasks in major applications. Apple does both of these, yet somehow they are depicted as cheating because they don't just offer the customer a range of beige boxes at 1.6, 1.7, and 1.8GHz along with a spec sheet of compiler shootouts. I have never seen computers demonstrated with actual applications outside of the Apple Store. To me, that just says that Apple has nothing to hide. If you don't believe Apple's performance demonstrations, go to an Apple Store and use your own media and see what results you get.

Re:Why is everything non-Apple a myth?

[tswinzig]

Latency is also better on the Mac, and that's very important in audio.

Video, music and audio, graphics, encoding and encryption ... the Mac is the best-performing machine for all of these. These are the tasks that Macs are BUILT FOR.

And if Apple really wanted to let you tap into that power, they would have shared their hardware specs with Be.

The primary reason Be ported to x86 was because Apple got pissed at them for showing up MacOS on the PPC architecture. Apple took its ball, and went home.

So if you really want a fair comparison of architectures, why not compare BeOS on x86 to MacOS on PPC? I realize it's not likely, the same types of apps are not available for BeOS and probably will never be... but let's not chalk up these so-called benchmarks to the CPU architecture quite yet...