Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: MS compiler issue [OT]

Author: Gerd Isenberg

Date: 13:46:20 10/15/05

Go up one level in this thread


Thanks Jon,

except the instructions to sub the boolean (setb) and fastcall, almost the same
assembly than from msvc6 compiler. The reciprocal mul is fine, the three
lea-instructions are suboptimal - at least for amd, where a 3-cycle imul is
faster and shorter, while one lea has 2 cycles.

Cheers,
Gerd



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.