tree dd53c56df047e5f71fc147c02d4fbd475b63282f
parent 28905821e7c91626aa61ef496b597029b0b25e0d
author sewardj <sewardj@8f6e269a-dfd6-0310-a8e1-e2731360e62c> 1163901947 +0000
committer sewardj <sewardj@8f6e269a-dfd6-0310-a8e1-e2731360e62c> 1163901947 +0000

On amd64, allow the register allocator to use %r10 which it previously
did not.  This gives a 0%-3% speedup, mostly closer to the 0% end.


git-svn-id: svn://svn.valgrind.org/vex/trunk@1680 8f6e269a-dfd6-0310-a8e1-e2731360e62c