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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Dan3 who wrote (74145)	10/5/1999 9:28:00 PM
From: Process Boy	Read Replies (1) \| Respond to of 1572632

Dan - <And Athlon already has a doubled (64 byte) cache line width and cache management architecture, so it might make some sense to call the current Athlon a hybrid 32/64 bit processor. > Intel quadrupled the 64 bit cache line to 256, on die. Does that make Coppermine a 32/256 processor? PB

To: Dan3 who wrote (74145)	10/6/1999 2:02:00 PM
From: Saturn V	Respond to of 1572632

Ref- <Aren't the ALU units already 80 bits? (in pretty much any modern processor)> The ALU is 80bits for floating point operations. I was talking about the integer registers and ALU which are only 32 bits for x86. Re thinking the 32 bit/64bit CPU chip size issue: A. The Floating Point Registers and ALU are the same for 32 or 64 bit. B. The Cache Area is probably the same. C. The Integer Registers obviously double in same. D. The Integer Arithmetic and Logic Unit[ALU] at least doubles. To have reasonable 64 bit performance, the Area would probably go up 4 fold. E. The Address Registers obviously double. So the AMD statement of a 10% penalty for 64 bit performance seems possible if the K-7 chip size is dominated by cache and Floating Point Unit, and the ALU has not been optimized for 64 bit operations.