Re: doubling time and singularity

From: Wei Dai (weidai@eskimo.com)
Date: Sun Dec 02 2001 - 01:39:12 MST


On Sat, Dec 01, 2001 at 09:29:08PM -0800, Spike Jones wrote:
> The Pentium4 is twice as fast as a similarly clocked P3 at doing
> Lucas-Lehmer testing. I dont know how George Woltman was
> able to take advantage of that updated instruction set of the P4, dont
> know enough about confusers to speculate. The P4 is also nearly
> twice as fast as a similarly clocked Athlon, again dont know
> why. I can research it and find out.

There's an SSE2 instruction in the P4 that lets you do 2 32x32->64 bit
multiplies at the same time and the instruction executes at a very high
throughput, much faster than the standard 32x32->64 bit multiply.

We'll probably get another big jump when 64-bit CPUs with 64x64->128 bit
multipliers become popular on the desktop.



This archive was generated by hypermail 2.1.5 : Sat Nov 02 2002 - 08:12:19 MST