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: Win Smith who wrote (81218)5/31/2002 6:36:57 PM
From: TGPTNDRRead Replies (2) | Respond to of 275872
 
Win, Re: <Big numbers can be handled by other means than increasing the basic machine word.>

Yes, you're most likely right.

But my take on the subject is that increasing the machine word size is the easiest way to get the instructions and data through the CPU quickly.

But I'm a software guy. My function is to make the instructions and data as small as I can.

I would assume the hardware guy's job is, in part, to make the hardware eat data and instructions as fast as possible.

Increase rate and increase size.

In any case, when did 4 bit computing to to 8, 8 to 16, 16 to 32, and 32 to 64?

What's the trend?

tgptndr



To: Win Smith who wrote (81218)5/31/2002 11:46:18 PM
From: kapkan4uRead Replies (3) | Respond to of 275872
 
<128 bits can address, um, 10**38 bytes, which might conceivably be useful for a shared universal address space or capability based machines or something.>

The idea that we will ever need 128-bit byte addressing is preposterous. There are only about 10**42 atoms in the universe. Such computer can't be constructed.

128-bit IP addressing is a different story. The spammers would love to send junk e-mail to every single atom in the universe.

Kap