Subject: Re: [boost] [gsoc] Interest check for 3d geometry proposal
From: Michael Fawcett (michael.fawcett_at_[hidden])
Date: 2009-03-27 11:55:21
On Fri, Mar 27, 2009 at 11:50 AM, Phil Endecott
> Kornel Kisielewicz wrote:
>> Also, in the case of 4d vectors, you'd have 5 values, which
>> doesn't scale well ( 4*32 bits = 128bits which is nice -- an addition
>> would ruin this niceness ).
> Multiplication by 4 faster than multiplication by 5? Â Maybe, but probably
> premature optimisation :-)
I think he meant that an array of four 4d vectors would fit nicely in
the 128 bit registers of a say, a Playstation, whereas an array of
four 4d vectors with an additional size member would not.