Rejig the bottom-level loops in internal_mul_* to use pointers instead
authorsimon <simon@cda61777-01e9-0310-a592-d414129be87e>
Tue, 22 Feb 2011 19:09:27 +0000 (19:09 +0000)
committersimon <simon@cda61777-01e9-0310-a592-d414129be87e>
Tue, 22 Feb 2011 19:09:27 +0000 (19:09 +0000)
commit757b0110eae2f1224aadf8d421f2ccb764f5b5ee
tree931989f852a357ee9d39cdf5f03a00eda00e72d1
parent28caddba9d88eca9b654dcf17060942be7677f0d
Rejig the bottom-level loops in internal_mul_* to use pointers instead
of array indices. You'd hope that compilers could automatically turn
the one representation into the other if it was faster to do so, but
apparently not: even on gcc -O3, this source transformation gains over
15% performance.

git-svn-id: svn://svn.tartarus.org/sgt/putty@9105 cda61777-01e9-0310-a592-d414129be87e
sshbn.c