Author: Vincent Diepeveen
Date: 07:37:30 03/26/02
Go up one level in this thread
On March 26, 2002 at 10:08:17, Sune Fischer wrote: >On March 26, 2002 at 09:49:39, Vincent Diepeveen wrote: > >>On March 25, 2002 at 08:48:54, Sune Fischer wrote: >>> >>All i know from the hammer is that i can't buy it in the store coming >>year. I can buy right now an XP2000. >> >>If you wanna buy a hammer, i would by the way buy a McKinley instead >>with a compiler that produces optimal code for the mckinley. >> >>So let's focus upon processors that are for real and working right now. > >Why? >I responded to a post[*] that claimed the 64-bit Hammer chip would only bring >chess programs 10-15% speed increase. I said I expected a lot more. >My reasons are that the Hammer will be introduced at around 2 GHz, and if it can >deliver the same performance clock for clock as the Alpha, then is should be a >lot faster than those 15%. That is that, we'll see when it comes out who was >right. >You argument about what is presently the fastet chip is _irrelevant_ IMO. my argument is that the big and advanced branch prediction of the alpha and the 4 instructions versus 3 of the alpha and the huge L1 and L2 caches of it, add to that cheating on specbench; all that together brings 33% speedup compared to a 32 bits processor. I do not see the 32 to 64 bits speedup for the alpha at all. For sure not a factor 2 as claimed at some places. If you claim 10-15% that's already a far smaller claim than other claims i saw here, majority is still claiming factor 2 to my amazement. Truth is that it is way harder to clock a 64 bits processor at 3Ghz than it is to clock a 32 bits processor at 3Ghz. We will see when we can afford processors that are 64 bits AND doing that faster than 32 bits equivalents. >[*]http://www.talkchess.com/forums/1/message.html?219258 > >-S. > >>Let's not focus upon processors from which it is not sure whether they >>are fast and even less sure when they are in the shops. the step from K6 >>to K7 was big for AMD, but not nearly as big as from K7 to hammer >>(unless they have a sucking design for 64 bits). >> >>Also the P4 on paper was a great processor, when it was released it >>was a major failure. >> >>Nevertheless, let's focus upon what is in the shops of today. Hammer isn't >>there. Just like the K7 took many years before it was actually produced. > >>>-S.
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.