Formerly About Advanced Micro Devices Message Board

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.

Politics : Formerly About Advanced Micro Devices

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Aaron Cooperband who wrote (55054)	4/10/1999 5:15:00 AM
From: Tenchusatsu	Read Replies (1) of 1582523

<Can you please explain to me why Intel would put a L2 cache on-chip rather than just increasing the L1 cache commensurately?> In general, the larger the cache or memory, the slower it is. That's why you have very small but fast L1 caches, bigger but slower L2 caches, and huge but very slow DRAM. That's your typical memory hierarchy. You want to keep your L1 cache as fast as possible, because that's where about 70 to 90% of your memory accesses are going to be serviced. Then of those accesses which miss the L1 cache, more than 50% will be serviced by the L2 cache. It will be slower than the L1 cache, but since only a fraction of the total memory accesses are going there anyway, the average performance won't be affected as much. But if you increase the size of the L1 cache, you could reduce the number of accesses which must be serviced by the L2 cache, but you pay the price with a slower L1 cache. You'll have to perform simulations to try and find the right balance between larger caches and faster caches. Tenchusatsu

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next