Slashdot Mirror
Linus: Praying for Hammer to Win
An anonymous reader writes "The boys at Intel can't be happy with the latest opposition to the IA-64 instruction set. According to this Inquirer scoop, Linus himself has weighed in, and it appears he's putting his eggs in the x86-64 basket. In the original usenet post, he goes so far as to say that 'We're ... praying that AMD's x86-64 succeeds in the market, forcing Intel to make Yamhill their standard platform.'"
Never heard of him.
Je t'aime Stéphanie
If he has his way the linux kernel will require 4 gigs of hardrive space and will still be using instructions from the 386 cpu core.
Only way to move forward is to sacrifice backward compatability.
That's 2 fps in a row, eh? Kudos.
This is just another of Shoeboy's forged LKML postings. Ignore it. Linus has been a nearly rabid Intel advocate for years -- why would he suddenly flip-flop like this?
Troll me if you dare moderators, I have the karma :P
Lately i've been building a machine in 3D for a neighbor down the street. I've been using truespace 5.2 and a plugin called vctek.
Well, the scene got to a point where it just became impossible to work in due to the high poly count. My p4 1.4 just could not handle it. The vctek chains were taking up a helluva lotta time to render.
I asked the neighbor if he could buy me a fast computer to do redering on. From my years of being a sysadmin i've always been able to count on intel for both reliability and speed. So I speced out a dual p4 xeon 2ghz system.
The peices came, I put them together and I started rendering my scene. What normally took me 48 hours to render was now going to take 14 hours. Yipee I told myself, time saved! Wait a minute though...
scene on a single 1.4 takes 48hours
scene on a dual 2.0 takes 14 hours
That's only a 3 fold increase!!!
So what the fuck? I thought the xeons were SUPPOSED to be faster. I thought I should have seen an increase in speed on a magnitide of 4 or 5.
Well another sysadmin buddy of mine has been buyin AMD stuff for years. We get into the same rivalry over our systems as 2 grease monkeys might do with their cars. For kicks he wanted to benchmark the scene on his single 2200MP. I went ahead and e-mailed the scene off to him and waited for the results.
The Results?
A single AMD 2200MP will match a dual xeon.
I'm sorry to say it folks, but from what i've seen this last week intel is slipping. Hyperthreading is a pretty useless technology, basically just a software CPU. It didn't do anything for my render times. Intel has lost yet another loyal follower.
My next system will be AMD for sure. For pure price/performance they are blowing intel out of the water. Yes AMD, you have another convert.
--toq
I am warkin at AMD on Humer procesar.
I things thet Intal suks, and AMD rulez, and AMD hes beter dyzign thet Intal.
Compare the size of the Itanium 2 die with the dies for AMD's Hammer chips. You will soon see who has the real muscle chip. (Hint: Itanium 2 will be FOUR TIMES larger than AMD's Clawhammer --- and it will still be slower.)
Getting rid of cruft is a good move if it lets you get higher performance. But IA64 destroyed that potential performance gain with several idiotic design decisions. That shiny new no-legacy instruction set may give you a warm feeling but that's all you get.
Now, Alpha was a nice architecture. If Intel had invested in Alpha the way they've invested in IA64, they would have left every other CPU in the dust. Too bad.