Slashdot Mirror
AMD Quad-Core Opteron (Barcelona) Tech Report
crazyeyes writes "AMD has been very tardy with Barcelona. Countless AMD fans have eagerly awaited a new processor. As the day draws closer, TechARP takes a look at the upcoming quad-core AMD Opteron. Is there more to it than just its four processing cores? Will it be the Intel-killer that AMD promised long ago? From the article: 'AMD is in the same boat as ATI. Delays after delays of their long-awaited Barcelona core not only ensured the dominance of their rival, Intel, in the desktop processor market, it also ensured that Intel would be the only choice for those who want a quad-core processor. Although that wait will end in August, 2007 when the Barcelona is finally launched, it remains to be seen if AMD's new processor will be able to inflict serious damage to Intel's dominance.'"
Intel needs more then just true quad core. They also need memory controllers build in the cpus and a cpu to cpu link that does need to use the NB to talk the other cpu and also have so you can have more then one NB like chip like you can on a amd system. With a 2 way amd system you can have 2 chip set links and up to 2 HTX slots.
And if it continues to go this well, Intel will push AMD entirely out of the competitive CPU marketplace. Next they'll go after VIA in the low-end, low-power markets and drive them out, and they'll reinvigorate their efforts on IA64, attempting to go after the high-profit Sun and IBM sockets.
In essence, the desktop will slow and rot, perhaps giving us another boneheaded move like NetBurst.
You can take all of that with a grain of salt, but remember this... It's been hammered here many times before that a company is in the business of returning value to the stockholders.
If there is not significant "commodity CPU" competition, it's not worth Intel putting much money into advancing it. Far better to just keep the lines running, keep enough pressure to keep AMD on the ropes, and simply milk it for all its worth. Why bother with unprofitable changes. Process maturation, migration, etc will supply the speed improvements.
Put the develpment budget where the competition is.
So if AMD really is on the ropes and quits challenging Intel, forget about the significant improvements you've been seeing.
The living have better things to do than to continue hating the dead.
Sooner or later they're going to have to go for something similar to an Itanium processor. Once pushing clock speed runs out, pushing cores runs out, pushing micro-op improvements runs out, they're going to start looking at the instruction set.
You can bet that if they could change the instruction set at a whim they would have done a long time ago, and the processor would perform much better.
I think it's inevitable that in the next 10 years things will start to look towards Itanium (or an equivalent), because changing the instruction set will provide a lot of untapped processing power.
// MD_Update(&m,buf,j);
This is very much untrue, as I can attest. I have been running a 64-bit OS since 2003, and it runs like a dream. I can't address all the technical reasons why, but I can say that I have no 32-bit libraries and I'm up and running. No tears here.
And from what I see, the Core 2 Duos are a LOT faster than the AMDs and in most cases the better choice.
On a cost-basis in the low to middle range of the market (basically CPUs in the under $400 range), Intel and AMD are pretty much equivalent price for equivalent performance. As Intel drops prices, AMD drops prices to stay competitive (and vice-versa). There are a few applications where one is better then the other, but on the whole, the two of them are at rough parity.
Personally, I prefer the NVIDIA + AMD motherboards. While Intel is back in the game with the Core 2 Duo, we're still buying Athlon64 X2s because the C2Ds are still too expensive.
2007 called back, just to let you know that 4gb of RAM was $150
If you'd watch the market more regularly, you'd know that RAM has priced out at anything between $30 per gigabyte and $125 per gigabyte in the past 12 months. Last summer it was around $60-$75 per GB, rising to the $125/GB figure in the fourth quarter of 2006. Right now it's bouncing around in the $30-$50/GB range.
All depends on what week you buy it and what week your retailer bought their stock.
I'm hoping that inexpensive ($30 or less) 1GB sticks means that the price is about to start dropping on the 2GB sticks.
Wolde you bothe eate your cake, and have your cake?