Joakim Tjernlund wrote:
Noticed while optimizing crc16 that gcc -O performed much better than gcc -O2 while doing crc16:
I have also seen -O1 beat -O2 when with a large FORTRAN program. http://www.hep.manchester.ac.uk/u/sam/zgoubi-optimise/ Sam
Joakim Tjernlund wrote:
Noticed while optimizing crc16 that gcc -O performed much better than gcc -O2 while doing crc16:
I have also seen -O1 beat -O2 when with a large FORTRAN program. http://www.hep.manchester.ac.uk/u/sam/zgoubi-optimise/ Sam