Intel Developer Forum Spring 2004 - Day 1: Wider and Faster
by Derek Wilson on February 18, 2004 10:41 AM EST- Posted in
- Trade Shows
IA-64 on the Desktop?
The Itanium processor has shown itself not to be the worlds greatest x86 emulator. The problem with bringing IA-64 to the desktop is that the architecture just isn't well suited to x86 style code. Much of the power of IA-64 can only be exploited via very complex compilers designed to optimize and schedule IA-64 code. It is possible to translate, dynamically recompile and optimize code on the fly (ala Transmeta's code morphing or some of the edgy Java JIT compiler research), but the complexity of IA-64 doesn't make this process any faster.Optimization and scheduling is an NP-complete problem (as is the famous traveling salesman problem) which means that the faster and more efficient you want your code to run, the longer it will take to compile. On the bright side, there is generally a point of diminishing returns at which the virtually infinite loop of optimization and scheduling can be stopped without sacrificing too much. Of course, doing all this on the fly and hoping to come up with near optimum code at high speeds is a very difficult problem to solve.
There is still the issue of getting that very wide, cache hungry, complex architecture down to a price point consumers can afford even if Intel is able to bring it out with performance that makes it a better option than native x86 CPUs.
IA-64 really would be a kludge on the desktop without turning it into an ultra emulated x86 with 8-way-hyperthreading and a +5 Dynamic Compiler of Doom to try to exploit its potential for achieving high IPC (Instructions Per Clock - how much work gets done every clock cycle). Honestly, by the time we get to a point where something like this is feasible, we will probably already be enjoying multicore CPUs and it still won't be any faster than cheaper native solutions.
Intel has informed us that they have not thought of IA-64 as a desktop architecture in any way for the present or the future. Popular opinion seems to suggest that either x86-64 is causing problems for IA-64, or that IA-64 was supposed to come to the desktop but that Intel's plans have now been thwarted. From our brief analysis of IA-64, it seems to us to be a particularly bad idea to even think about moving it to the desktop space. It seems to make more sense that Intel definitely had other plans up their sleeves. Let's take a look at our other two options.
Facebook
Twitter
RSS
17 Comments
View All Comments
Mrburns2007 - Wednesday, February 18, 2004 - link
XDR has 6.4 GB/s per chip not module.Ecmaster76 - Wednesday, February 18, 2004 - link
"ultra emulated x86 with 8-way-hyperthreading and a +5 Dynamic Compiler of Doom"Sweet! Where can I get one? Is it compatible with my DRAM skin armor?
Someones been playing too much Baldur's Gate, and not just me.
(Think of all the processors Intel could sell with marketing like that.)
DerekWilson - Wednesday, February 18, 2004 - link
Actually, PCI-X is completely differet from PCI Express ... PCI-X is a parallel architecture that's wider and faster than the 32bit 33mhz pci bus ... PCI Express is specification for a point to point serial bus protocol (and multiple serial data streams can be sent to the same periphreial, thus the x16 pci express graphics card).Any when I was talking about ATI's "next gen" chip I wasn't talking about their current PCI Express solution RV380. I was talking about some unspecified demo that I'm going to assume was R420 or R423... I just didn't want to mention a card since ATI wouldn't tell me which card it was that was powering the box.
I think I fixed all the typos, sorry bout that ... I've been working by jumping between hotspots and hand coding html rather than using the dreamweaver over broadband that I'm used to ;-)
Lonyo - Wednesday, February 18, 2004 - link
Intel was pretty much always going to use compatible 64bit extensions.They have to work with the OS, since MS is pretty much dictating that.
AMD set up the initial spec (I would assume), and Intel didn't have much choice but to follow.
ATi and nVidia have to stick to the PCI-Express spec to make their next gen graphics cards, and that was designed by Intel, it's just a similar thing.
AMD obviously did well to get there first though and set the standards.
Malladine - Wednesday, February 18, 2004 - link
KillaKilla's older brother: PC3200 Bandwidth is 3.2gb/s :)http://www.kingston.com/newtech/ddrbandwidth.asp
KillaKilla - Wednesday, February 18, 2004 - link
whoops forgot a few things, guess I "jumped the gun[post]"...1st, this isn't KillaKilla, hes my brother, I don't have my own nick yet, sorry...
What did you mean by "2x to 3x performance gains" for native PCI-X (pci express is PCIX, right? I've seen it as PCI-E, but that was from before?) Also, what are these "HD streams"(2nd to last paragraph, 2nd page) you talk about?
3rd page:
"The upcoming XDR chips were on display up at the RAMBUS both across from a demo of Toshiba chips running at very high speeds (the bandwidth of XDR is 6.4GB/s)." Isn't DC-DDR 3200/400's bandwidth 6.4GB/s?
4th page:
I'm not surprised that intel cross-licenced x86-64... it was only logical seeing MS-XP64. Kudos to AMD for making a better 64-bit solution(extension set).
-KillaKilla's older brother
KillaKilla - Wednesday, February 18, 2004 - link
Once again, first post.Anyway, there are a few typos.
the Borad in the title?
The open tags on 2nd page