Optimization comparison: 3.3, 3.4, mainline, tree-ssa

[Andi Kleen]

Scott Robert Ladd <coyote@coyotegulch.com> writes:
>
> Questions to be answered: Why does gcc-tree-ssa do so well /without/
> -D__NO_MATH_INLINES on Opteron? Is the code being generated correctly
> with both compilers and switch sets?

Most likely because nobody bothered to write a lot of SSE2 inlines for glibc
yet. x86-64 defaults to SSE2 for floating point; x87 is only used
for long double.

-Andi