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: Alan Bell who wrote (19556)	5/1/1999 2:53:00 PM
From: Tony Viola	Respond to of 93625

Alan, thanks for the summary on Rambus memory speeds, which are really getting up there. Oh well, someone has to do it (Rambus and Intel). Tony

To: Alan Bell who wrote (19556)	5/1/1999 5:03:00 PM
From: Tenchusatsu	Read Replies (2) \| Respond to of 93625

<The Rambus clock runs at 400Mhz (and is a differential signal.) Data is clocked on both edges. The data lines toggle at a max of 400Mhz (and are non-differential.) As you point out, the data rate is 800mb/sec even through no signal transitions faster than 400Mhz.> A little nit-picky thing here. If the data rate is 800 mega-transfers-per-second, the data lines will naturally toggle at 800 MHz. As you said, the data lines are latched on both the rising and falling edges of the clock, which is why the clock only needs to run at 400 MHz. It's just word-play, but it's kind of tough to define what a "hertz" is for data lines. It's easier to just say transfers-per-second. Traditional buses only transfer on the rising edge of the clock, meaning you have one transfer per clock. Newer buses like RDRAM and AGP transfers data on both the rising and falling edges of the clock, meaning you have two transfers per clock. (For those few who are wondering how you can get four transfers per clock, as in AGP-4X, ask me again later.) Tenchusatsu