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 : IDTI - an IC Play on Growth Markets -- Ignore unavailable to you. Want to Upgrade?

To: Frank Povoski who wrote (6951)	2/23/1998 8:10:00 AM
From: William B. Kohn	Read Replies (1) \| Respond to of 11555

What I read is that it could be any amount and it may be more than 512KB, they had room on the die for more, perhaps as much as 2MB.

To: Frank Povoski who wrote (6951)	2/23/1998 10:16:00 AM
From: Rob S.	Respond to of 11555

There are a lot of advantages of putting the L2 cache on-chip besides being able to run it at full uP speeds. They can take advantage of much finer addressing granularity - they can have multi-ported I/O and a much higher number of I/O paths. They won't need the line drivers and buffers to external memory. As the uP technology moves toward on-chip memories, IDTI should be in a very good position to take advantage of the trend. Intel's multi-chip module slot 1/2 approach is faulted for the sub $1000 market. You can't get around the need for buffering and driving I/O for the off-chip SRAM even though it is on the module. It helps, but is still plagued by many of the same limitations as conventional MB technology. On-chip memory has clear advantages, particularly if you can reduce the size of the memory cells. That's where the real battle may end up - who can put massive amounts of memory on chip to the most advantage? IDT has a lot of capability, let's hope they can put it to good use in the CX++++.