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 : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?


To: wanna_bmw who wrote (73249)3/4/2002 6:46:48 PM
From: Ali ChenRead Replies (2) | Respond to of 275872
 
"Sorry, but you're incorrect. I heard it from the horse's mouth. L2 Cache runs at full processor speed.
Of course it may totally blow your mind, but I thought I'd also mention that L1 data cache happens to run at 2x the processor speed (or 4.4GHz)."

If you don't understand the difference between clocking
of an SRAM cell and the rate of data multiplexing at an
interface point, I feel sorry for you.

You should read the _MARKETING BRIEF_ more carefully:

"Data clocked into and out of the cache every clock cycle"
and
"The Advanced Transfer Cache consists of a 256-bit (32-byte) interface that transfers data on each core clock."

Please note hints: "interface", "into and out of".
It speaks nada about internal design of the cache.
Try to comprehend the Rambus example too.

- Ali



To: wanna_bmw who wrote (73249)3/4/2002 8:50:46 PM
From: PetzRespond to of 275872
 
re:L2 Cache runs at full processor speed.
The L2 cache with two equal sections is a dead giveaway. Why would it be designed that way if it were not being interleaved? -- so that it would increase path delays?!

I think your horse's mouth is spouting the horse's party line - "The L2 cache runs at full speed because that is how we define 'full speed'"

Petz