projects / platform / upstream / linaro-glibc.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 5695fc8) | patch
arm: Add optimized addmul_1
authorRichard Henderson <rth@twiddle.net>
Tue, 26 Feb 2013 23:45:57 +0000 (15:45 -0800)
committerRichard Henderson <rth@twiddle.net>
Wed, 6 Mar 2013 15:47:25 +0000 (07:47 -0800)
commit21e31515a694b966f5df11ec2aee6c51b3fd0a96
tree638a75c537fa476b67c2d2637f04797d0bbae0datree | snapshot
parent5695fc848fb3cd25fb528dada44f8bbdd113c04acommit | diff
arm: Add optimized addmul_1

Written from scratch rather than copied from GMP, due to LGPL 2.1 vs
GPL 3, but tested with the GMP testsuite.

This is 25% faster than the generic code as measured on Cortex-A15,
and the same speed as GMP on the same core.  It's probably slower
than GMP on the A8 and A9 cores though.
ports/ChangeLog.arm diff | blob | history
ports/sysdeps/arm/addmul_1.S [new file with mode: 0644] blob
Domain: System / Toolchain;