[Bug rtl-optimization/33928] [4.3/4.4/4.5/4.6 Regression] 30% performance slowdown in floating-point code caused by r118475

[lucier at math dot purdue.edu]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=33928

--- Comment #119 from lucier at math dot purdue.edu 2011-03-10 19:55:54 UTC ---
It's nearly impossible to examine the assembly code responsible for the FFT in
the package I set up in the previous comment.  If you want a runtime benchmark
for this PR where you can easily examine the code I'll have to do more work.