Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: SSE2 bit[64] * byte[64] dot product

Author: Anthony Cozzie

Date: 09:39:17 07/20/04

Go up one level in this thread


On July 20, 2004 at 12:31:59, Anthony Cozzie wrote:

>What do you think of the following C code:
>
>int bb_dot_product(bitboard a, unsigned char *weights)
>{
>   bitboard t, t1, *_weights = weights;
>   static bitboard table[256] = {correct translations, e.g. 0xFF -> 0xffffffff}
>
>   //we count on the compiler to unroll this loop.
>   for(i = 0; i < 8; i++, a ) {
>      t = table[(a >> i*8) & 0xFF] & weights[i];
>      t1 = t;
>      t << 8;
>      sum += (t & 0x00FF00FF00FF00FF) + (t1 & 0x00FF00FF00FF00FF);
>   }
>
>   sum = (sum & 0x0000FFFF0000FFFF) + ((sum >> 16) & 0x0000FFFF0000FFFF);
>   sum = ((sum >> 32) + sum & 0x00000000FFFFFFFF);
>   return sum;
>}
>
>It has several advantages:  Can use full 0-255 for each weight, the table does
>not have to be rotated, and there is no penalty for moving between the integer
>and MMX pipes.
>
>OTOH, this solution is also much less cache friendly, requiring maybe 2x the
>number of instructions and also needed 2KB of data cache.
>
>anthony

Could someone with a 64-bit MSVC compile this code and post the assembly? (and
if they were really nice, benchmark it? :)

anthony



This page took 0.02 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.