auto vectorization on double and ffast-math

Posted by wiso on Stack Overflow See other posts from Stack Overflow or by wiso
Published on 2010-05-17T20:54:19Z Indexed on 2010/06/14 16:32 UTC
Read the original article Hit count: 507

Filed under:
|
|
|
|

Why is mandatory to use -ffast-math with g++ to achieve vectorization of loop using doubles? I don't like ffast-math because I don't want to loose precision.

© Stack Overflow or respective owner

Related posts about gcc

Related posts about g++