SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : Intel Corporation (INTC)
INTC 34.50+2.6%Nov 21 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Elmer who wrote (108592)8/27/2000 3:05:34 PM
From: Scumbria   of 186894
 
Elmer,

Intel still plans on RDRAM for highend systems. The statement made a few weeks ago by an Intel spokesman to the effect that RamBus performance only shows up when running multiple applications simultaneously has merit and is ignored by the uninformed, and the intentionally misleading (that's you Scumbria).

I've discussed this issue before. If multitasking operations thrash the cache, they will cause more cache misses and more DRAM traffic. In these situations, it is much more efficient (less total clock time) to run the applications serially. This is because the cache hit rates remain much higher.

That is why CPU design houses use queueing software like LSF. Proper management of CPU utilization is a much better solution to the problem than putting expensive memory on your workstation. Another solution is to put larger caches on the CPU, which is what everybody is doing (except for P4 which will be crippled by a small L2 cache.)

Scumbria
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext