Author: Robert Hyatt
Date: 07:46:17 01/26/03
Go up one level in this thread
On January 26, 2003 at 05:31:12, Sune Fischer wrote: >On January 25, 2003 at 21:28:54, Robert Hyatt wrote: > >>On January 25, 2003 at 16:31:25, Sune Fischer wrote: >> >>>On January 24, 2003 at 23:20:58, Robert Hyatt wrote: >>> >>>[snipped a huge amout, that should have been snipped looong ago so people don't >>>have to scroll for half an our to read 5 lines] >>> >>>>>I think that they forgot the fact that the hardware is not twice faster every >>>>>year and the progress in hardware is going to stop sometime in the future. >>>>> >>>>>300 Mhz were used in the end of 97 in the microcomputer world championship in >>>>>paris (Today, more than 5 years later we do not have 300*32=9600Mhz. >>>>> >>>>>Uri >>>> >>>> >>>>Moore's law is running on a roughly 18 month cycle. 1.5 years. 5 years == >>>>three doublings. 8 * 300 is 2400, which is a bit behind, since we are at 3.0+ >>>>today. >>> >>>Actually I believe Moore's law was about the number of transistors, and not >>>about speed (common misconception). >>> >>>http://www.intel.com/research/silicon/mooreslaw.htm >>> >>>-S. >> >>Yes, but if you look carefully, density and speed are proportional, hence >>the common usage about doubling speed... > >Yes, that is probably not far off. >But measuring speed is not as simple as merely looking to the MHz, the P4 vs K7 >is a prime example of that :) > >-S. Yep.. but compare a PIV with rambus to the K7, when the benchmark is streaming data from / to memory and nothing else. IE a large numerical computation on a huge array. You will get a _completely_ different "winner" in that case. One problem is comparing mhz. In the same processor generation, mhz is a good way to compare. But the PIV has a new core, distinct from the PIII, so that comparing mhz there is interesting from Moore's law perspective, but not from a raw performance perspective...
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.