MadSci Network: Computer Science

Subject: How fast will conventional desktop computers eventually go?

Date: Sun Apr 22 13:09:28 2001
Posted by Chris
Grade level: grad (science) School: University of Manchester
City: Manchester State/Province: No state entered. Country: England
Area of science: Computer Science
ID: 987959368.Cs

I have a degree in Systems Engineering, but haven't done any VLSI stuff for a 
couple of years. I was wondering how "fast" a conventional desktop computer 
(such as would appear on the average office desk) will eventually run - is 
there a limit.

I know that increasing the processing performance can be achieved by increasing 
the CPU's clock speed, adding on-chip cache, speeding up the bus to the system 
memory, increasing the amount of system memory, moving to RISC, adding 
pipelining, doing speculative branch execution, introducing a SIMD architecture 
etc., and what I really want to know is just how much faster our PCs (etc.) 
will get - is the limit to how fast a computer can go ultimately dictated by 
the frequency of the signals used in the system - presumably regular PCB tracks 
have a frequency response that has a cut-off point at a high frequency. What 
technologies exist or are in development to address such issues. I have read in 
the past that room-temperature superconductors could herald a new phase in 
computing - how does such a technology help? Are there any quentum effects that 
may ultimately limit the speed of computers?

Finally, what tasks could such super-fast computers be used for by the regular 



Re: How fast will conventional desktop computers eventually go?

Current Queue | Current Queue for Computer Science | Computer Science archives

Try the links in the MadSci Library for more information on Computer Science.

MadSci Home | Information | Search | Random Knowledge Generator | MadSci Archives | Mad Library | MAD Labs | MAD FAQs | Ask a ? | Join Us! | Help Support MadSci

MadSci Network,
© 1995-2001. All rights reserved.