Apple To Discuss HyperTransport For Future Macs
macrealist writes "CNET is reporting that Apple will discuss the use of HyperTransport in Macs at the Developer's conference. The interesting thing is that the article claims that Apple is not likely to use hypertransport to link the CPU to the memory, but instead to link chipsets together because IBM would have to 'to adapt it to the Power architecture.' But according to arstechnica, the 970 does have a frontside bus that operates at similar speeds to Hypertransport."
<pedantically> I think that Apple has already developed a tried and true solution for external, non-ethernet-based, high-speed data transfer. It is called FireWire800.
Of course, an IP substack can be built on top of the FW, to have additional networking options. (Check out)</pedantically>
0.02â
Apple is a member of the HyperTransport Consortium. They have a hand in the development of the technology.
--
The internet is the greatest source of biased information in the history of mankind.
First of all: A "frontside bus that operates at similar speeds to Hypertransport" most likely isn't Hypertransport - just like a car with performance similar to a Porsche isn't a Porsche. So you can't just hook up a 970 (or POWER/PowerPC) to a Hypertransport link.
Furthermore, linking a CPU to main memory via Hypertransport (a point-to-point link) means you can't share the memory with other CPUs (unless you have dual-ported RAM - uhh, yeah, good luck with that plan).
Lars T.
To the guy who modded me down from perfect to terrible Karma - Apple haters still suck
The next time you play around with a Mac OS X machine look inside an application bundle. See those nib files? They provide the user interface and you can modify them using apple's developer package tools.
Yes, the entire computer is skinnable, user apps included. Now this doesn't include classic apps (which you won't be using much of), unix apps (which don't use NIBS) and monolithic code not in a bundle (like RealBasic). For the rest of the 90% of Mac apps, you can really mod to your heart's delight. Most people don't do this because they *like* the way Apple makes everything work with everything else. But if that's what floats your boat...
To do it right, you'd have to get a new bus as the chips are being strangled by bandwidth bottlenecks on current bus designs.
I don't know where these rumors get started.
The combination of fat caches, low latency, and predictive fetching basically negates the memory bus bottleneck in the current-generation (MaxBus-based) Power Macs. Even in SIMD instances, the processor generally doesn't have to wait on data that much. (This is especially true in SIMD instances, because these are almost always sequential-read applications, which makes those fat caches and predictive fetching work up a sweat.) Consider Apple's AltiVec-optimized BLAST, for instance. It's 10X faster than BLAST on a Pentium 4. It's not memory-bound. It's compute-bound.
What's that famous Seymour Cray quote? "A supercomputer is a device for turning compute-bound tasks into I/O-bound tasks."
So if anybody produces PowerPC 970 upgrades with MaxBus interfaces, they're almost certain to be good buys. Unless they cost thousands of dollars, of course. A dual-1.8 GHz (pulled that number out of my ass, guys) Power Mac G5 (pulled that out of my ass, too) will be faster than a dual-1.8 GHz upgrade in a MaxBus G4, but it'll still be considerably faster than the G4 was originally.
It is looking more and more like the IBM-970 does use/support Hypertransport.
"Six GDA IP cores are available through IBM Blue Logic IP Collaboration Program including HyperTransport Cave, Tunnel, Host and Bridge, 10 Gigabit Ethernet MAC, and SPI4.2 link controller. Information on these IP cores is available on IBM and GDA web sites."
The above is from this news release from the Hypertransport Consortium http://www.hypertransport.org/pr_050503b.htm
Shadow