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 : Rambus (RMBS) - Eagle or Penguin -- Ignore unavailable to you. Want to Upgrade?


To: Scumbria who wrote (43892)6/9/2000 7:36:00 PM
From: jim kelley  Read Replies (1) | Respond to of 93625
 
Mr Scum....

Silly boy! We have been through this before. You know about big parallel busses and memory interleaving techniques although many on this thread do not. These techniques are not suitable in low cost desktop PCs. Fortunately, RAMBUS stands to collect royalties on these devices as well as the RDRAM.

Eventually, the SDRAM used in servers will have to give way to new technologies as the clock rates continue to climb.

:)



To: Scumbria who wrote (43892)6/10/2000 5:58:00 PM
From: Steve Lee  Read Replies (1) | Respond to of 93625
 
>>Me leprechuan says that bandwidth is the key to server performance. Maybe that is why servers use the highest bandwidth memory- DDR<<

The leprechaun is wrong. Servers often store many gigs of data. It is desirable that the data is read from RAM rather than disk. The quantity of RAM is what matters.

PC nased servers will typically have 256MB to 4GB of RAM. The amount of RAM makes far more difference to performance than the type of RAM.

It would take many RDRAM channels to provide multi gigabyte RAM capacity (which many customers wouldn't use anyway). So the obvious idea is to use an alternate type of RAM. When RDRAM is available in larger capacities, it will be used in servers.

But you know this. You are not as dumb as your biased posts make out. What is the reason for these half truths?