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) -- Ignore unavailable to you. Want to Upgrade?


To: Ali Chen who wrote (86268)7/28/1999 1:56:00 PM
From: Scumbria  Read Replies (1) | Respond to of 186894
 
Ali,

You and Ten are both correct. A certain percentage of the time a computer spends doing a task is processing time, and a certain percentage is time spent waiting for memory/IO. Speeding up either of these decreases the total time required to complete the task.

Because of the mismatch between memory speeds and CPU speeds, system benchmark improvements no longer scale well with MHz, unless they are associated with improvements in the memory subsystem. Intel and AMD have both recognized this and are putting much larger caches on their high end CPU's.

Scumbria



To: Ali Chen who wrote (86268)7/28/1999 2:15:00 PM
From: Tenchusatsu  Respond to of 186894
 
Ali, we've been through this debate before, and I'm not surprised that you replied to my original message. Let me just say that application performance is dependent on CPU speed because my theories are correct. I'll let it stand there without further explanation.

<Maybe this is why this "ridiculous" Athlon lags in performance behind P-III/Xeon? Or it isn't?>

I think Athlon's performance is remarkable despite the limitations of the memory bottleneck. I've already said before that once Athlon systems start supporting DRDRAM or DDR SDRAM, Athlon's 200 MHz bus will take better advantage of the memory bandwidth compared to Coppermine's 133 MHz bus. As a so-called "Intel-a-bee," this concerns me somewhat.

Tenchusatsu