[Bug tree-optimization/30032] sqrt(CGAMMA*PRES[j]/DENS[j]) much slower than compiting compiler

[burnus at gcc dot gnu dot org]

------- Comment #4 from burnus at gcc dot gnu dot org  2006-11-30 21:14 -------
> Also you are using VLAs so maybe ICC also converts those VLAs to normal 
> arrays.

Some tests with
void eos(const int NODES, const float CGAMMA, float CS[NODES], const float
PRES[NODES], const float DENS[NODES])

icc -O3 -xW -ipo -static
real: 0m1.879s 0m1.878s
gcc -march=opteron -ffast-math -funroll-loops -ftree-vectorize -msse3 -O3
real: 0m6.478s 0m6.791s
gcc -march=opteron -ffast-math -funroll-loops -ftree-vectorize -msse3 -O3
-mfpmath=sse,387
real: 0m6.907s 0m6.501s


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30032