Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 23 Aug 2013 02:31:46 +0100
From: Rafael Waldo Delgado Doblas <lord.rafa@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: Parallella: Litecoin mining

Hello,


2013/8/23 Rafael Waldo Delgado Doblas <lord.rafa@...il.com>

> Sorry I forgot about it, but currently I don't understand.
>
> (x/6) = x * (1/6) = (x * (n/6)) / n, well I choose I nice power of 2 n the
> down division can be replaced by a m shift and the upper (n/6) can be
> computer and round it. for example if I say n = 16.
>
> (x/6) = (x * (16/6)) >> 4 ~ (x * 3) >> 4.
>
> I need to do a right shift by 1 how do you find the constant for right
> shift by 1
>
> Regards,
> Rafael.
>

Ok I have replaced the division and modules by :

// This function approximation works fine up to a = 32771
#define DIVTMTO(a) ((10923 * (a))>>16) // If TMTO_RATIO changes you need
redefine this macro

#define DIV2(a) ((a)>>1)
#define MOD2(a) ((a) - (DIV2(a) << 1)) // This can be optimised in ASM
using carry

#define DIV8(a) ((a)>>3)
#define MOD8(a) ((a) - (DIV8(a) << 3)) // This can be optimised in ASM
using carry

The performance still the same but now I drop almost 1K. I'm going to check
the segfault.

Regards,
Rafael.

Content of type "text/html" skipped

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ