Intel fights back with high-end Xeon

TalkBack 16 of 19:: Next »; « Previous

Thread View
Flat View

The "NEW" Steam Engine locommotives are now available !!!: Tulsa is the last model to use Intel's all-but-extinct NetBurst architecture, which Kilroy acknowledged is "long in the tooth." But Tulsa still is a compelling design, he argued.

WHY would people still invest in NetBURP nonsense? That "architecture" should had died before th turn of this century. It is wasteful in power and it produces enough heat to warm a big room in the Winter. Just put it to rest already !

"The 16MB of L3 (level-three) cache really helps position it for superior performance."

NOT for the data which remain in DRAM due to access patterns. Or data evicted frequently from the cache due to process switchings.

Cache is king
Indeed, cache is at the heart of the AMD-Intel rivalry. AMD's Opteron includes a built-in memory controller, while Intel systems require a separate chip that takes longer to fetch data. But including a large cache means that data is more likely to be readily at hand, so the memory controller isn't needed at all, Intel argues.

Yes ON chip L3 can improve performance, this is common sense. There are apps that do not benefit from larger cache as I mentioned above. However ALL apps benefit from shorter access times which IS the case with AMD/HT.

But why would people invest in dead technology instead of demanding from Intel to furnish large L3 Cache in their core-2 processosr?

Intel's 65-nanometer process means more circuitry can be squeezed into a given surface area than with the 90-nanometer process AMD still uses. And even using the same process, Intel cache elements are smaller, said Pat Gelsinger, who co-manages the Digital Enterprise Group with Kilroy.

"My cache cells are about half the size. I got cache to burn," Gelsinger said in an earlier interview.

Intel is wasteful in general. They leverage smaller feature sizes to cram more "stuff" in their chips, not necessarily the right stuff. Core-2 is the first SERIOUS attempt to remove the wastefulness and provide a more well-tought out architecture. But the netBURP is dead NO MATTER how big the L3 cache...

Tulsa also is the first Xeon to include "Pellston," officially called Intel Cache Safe Technology, which shuts off cache elements if errors are detected. Such reliability features are important in higher-end servers, Kilroy said.

Chip-kill technology is NOT NEW. Ask IBM and other serious server vendors. It's been around for many years now.

I think that Intel wants to troubleshoot their chipkill and cache technologies on an old chip FIRST. It will be a waste to buy systems on these chips: OLD NetBURB and NEW and UNTESTED Cache / Mem design... too many bugs for CERTAIN.

But cache isn't free. It takes up real estate, increases manufacturing costs and makes a chip run hotter. The top-end Tulsa with 16MB of cache draws 150 watts of power running flat out, though slower models with 4MB cache consume only 95 watts.

This is the classical Intel style: use FATTER chips, FATTER buses, guzzle tons of power. They remaind me of all the inefficient cars from Detroit with 8 cylinders and 8 Liters that produce a mere 200 Horse power. I would much rather buy a leaner/meaner European car which produces 300HP with around 3litter engines and better miles/galon.

Why would people BUY OLD, OVERHEATING and POWER GUZZLING Intel chips when BETTER ones ARE HERE?

I guess too many naive people with deep pockets?; Posted by: michael_t Posted on: 08/29/06 You are currently: a Guest | Members login | Terms of Use