On Fri, Dec 08, 2006 at 01:02:27PM -0600, Menezes, Evandro wrote: > HJ, > > I'll run the three worst offenders below and get back to y'all. > > The full results will take longer.
Hi Evandro, I also saw similar issues on x86-64 with -O2 -ffast-math: gcc-4.2 rev 116820 gcc 4.3 rev 119497 410.bwaves 10.9 10.6 -2.75229% 416.gamess 15.0 15.6 4% 433.milc 13.0 12.9 -0.769231% 434.zeusmp 13.9 13.9 0% 435.gromacs 8.41 8.40 -0.118906% 436.cactusADM 10.3 10.2 -0.970874% 437.leslie3d 10.6 7.55 -28.7736% 444.namd 13.6 13.6 0% 447.dealII 23.7 23.8 0.421941% 450.soplex 15.5 15.4 -0.645161% 453.povray 17.7 18.7 5.64972% 454.calculix 6.96 7.04 1.14943% 459.GemsFDTD 12.3 9.87 -19.7561% 465.tonto 12.6 12.4 -1.5873% 470.lbm 15.9 16.0 0.628931% 481.wrf 10.3 9.97 -3.20388% 482.sphinx3 18.5 18.4 -0.540541% Est. SPECfp_base2006 12.9 12.5 -3.10078% Did you see it on AMD? H.J.