[PATCH] D20341: [CUDA] Enable fusing FP ops for CUDA by default.

Steve Canon via cfe-commits cfe-commits at lists.llvm.org
Tue May 17 16:29:05 PDT 2016

scanon added a comment.

`-ffp-contract=on` obeys the semantics of C's FP_CONTRACT pragma.  In particular, it will not fuse:

  float m = x*y;
  float a = m + z;

Whereas you probably want that to fuse for your purposes.  `-ffp-contract=fast` seems more in line with your needs.


More information about the cfe-commits mailing list