Author: Aart J.C. Bik
Date: 09:26:39 04/11/05
Go up one level in this thread
On April 09, 2005 at 04:23:02, Gerd Isenberg wrote: >My naive guess was that intel C produces an intermediate stream in a first pass >(like a preprozessor does) with XMM-intrinsics to target vectorisation - so that >the native compiler or code generator has only to deal with XMM-intrinsics as a >central instance for xmm-register allocation and code scheduling issues. Hi Gerd, Well, although all SIMD-flavored intrinsics and automatically vectorized code indeed share the same intermediate representation in the Intel compiler, the vectorizer is actually an integral part of the compiler, not just a preprocessor. This organization enables a much better interaction between optimizations that run before and after vectorization. But I guess I am getting a little of the chess topic here :-) Aart Bik http://www.aartbik.com/
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.