Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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: Bilow who wrote (56488)	10/4/2000 1:48:14 AM
From: Tenchusatsu	Read Replies (1) \| Respond to of 93625

Carl, <I think that's stunningly good performance for a repeater, but the result is comparable to the effect of registering DDR.> Usually for systems that require repeaters, like servers, latency isn't a very big factor. In fact, DDR-based servers will also require repeaters, simply because you need many channels to support the gigabytes of DRAM necessary. A coworker I talked to mentioned that RDRAM would have been a better performing solution than DDR SDRAM for servers. However, the other benefits of DDR in servers (like cost, capacity, and chipkill) seemed to have outweighed the performance of RDRAM. Tenchusatsu

To: Bilow who wrote (56488)	10/4/2000 10:28:45 AM
From: Jdaasoc	Read Replies (1) \| Respond to of 93625

carL: RE RDRAM repeater latency this amounts to under 2ns to get on and off the chip, each way Thank you very much for pointing out this bit of information. For 1066 MHz RDRAM, that 2 nsec would be reduced to 1.6 nsec. That's what I mean by scability. My laymans understanding of the RamBus channel is like people skipping rope without tripping. My layman's understanding of DDR memory model is it is more like a wave pool where the faster the waves come the more buffeting you encounter. john