I have benchmarked both current gcc-4_7-branch and the release gcc 4.8.0 built with...
Using built-in specs. COLLECT_GCC=gcc-fsf-4.7 COLLECT_LTO_WRAPPER=/sw/lib/gcc4.7/libexec/gcc/x86_64-apple-darwin12.3.0/4.7.3/lto-wrapper Target: x86_64-apple-darwin12.3.0 Configured with: ../gcc-4.7-20130323/configure --prefix=/sw --prefix=/sw/lib/gcc4.7 --mandir=/sw/share/man --infodir=/sw/lib/gcc4.7/info --enable-languages=c,c++,fortran,lto,objc,obj-c++,java --with-gmp=/sw --with-libiconv-prefix=/sw --with-ppl=/sw --with-cloog=/sw --with-mpc=/sw --with-system-zlib --enable-checking=release --x-includes=/usr/X11R6/include --x-libraries=/usr/X11R6/lib --program-suffix=-fsf-4.7 --enable-cloog-backend=isl Thread model: posix gcc version 4.7.3 20130323 (prerelease) (GCC) Using built-in specs. COLLECT_GCC=gcc-fsf-4.8 COLLECT_LTO_WRAPPER=/sw/lib/gcc4.8/libexec/gcc/x86_64-apple-darwin12.3.0/4.8.0/lto-wrapper Target: x86_64-apple-darwin12.3.0 Configured with: ../gcc-4.8.0/configure --prefix=/sw --prefix=/sw/lib/gcc4.8 --mandir=/sw/share/man --infodir=/sw/lib/gcc4.8/info --enable-languages=c,c++,fortran,lto,objc,obj-c++,java --with-gmp=/sw --with-libiconv-prefix=/sw --with-isl=/sw --with-cloog=/sw --with-mpc=/sw --with-system-zlib --enable-checking=release --x-includes=/usr/X11R6/include --x-libraries=/usr/X11R6/lib --program-suffix=-fsf-4.8 Thread model: posix gcc version 4.8.0 (GCC) and see the following improvements and regressions between the two compilers. pb05 benchmark run with -Ofast -funroll-loops on x86_64-apple-darwin12 Run Time (sec) Benchmark gcc-4_7-branch gcc-4.8.0 % Change ac 8.16 8.03 -1.6 aermod 16.30 16.17 -0.8 air 5.84 5.73 -1.9 capacita 32.29 32.91 +1.9 channel 1.83 1.84 +0.5 dodoc 26.19 25.71 -1.8 fatigue 6.84 4.06 -40.6 gas_dyn 3.92 3.69 -5.9 induct 11.95 12.37 +3.5 linpk 15.38 15.66 +1.8 mdbx 11.17 11.45 +2.5 nf 19.76 19.75 -0.1 protein 31.55 30.89 -2.1 rnflow 24.49 21.00 -14.3 test_fpu 7.79 7.91 +1.5 tfft 1.86 1.90 +2.2 Mean Time 10.24 9.81 -4.2 Compile Time (sec) Benchmark gcc-4_7-branch gcc-4.8.0 % Change ac 2.14 2.01 -6.1 aermod 42.93 40.67 -5.3 air 4.45 4.15 -6.7 capacita 1.97 1.78 -9.6 channel 0.66 0.72 +9.1 dodoc 6.01 5.46 -9.2 fatigue 1.97 1.98 +0.5 gas_dyn 3.22 2.92 -9.3 induct 4.16 4.32 +3.8 linpk 0.91 1.21 +33.0 mdbx 2.22 1.83 -17.6 nf 2.13 1.60 -24.9 protein 4.41 3.49 -20.9 rnflow 6.47 5.40 -16.5 test_fpu 5.29 4.14 -21.7 tfft 0.60 0.75 +25.0 Executable Size (bytes) Benchmark gcc-4_7-branch gcc-4.8.0 % Change ac 59120 46856 -20.7 aermod 1396920 1290192 -7.6 air 114864 106656 -7.1 capacita 77920 73224 -6.0 channel 34704 34632 +0.2 dodoc 205320 189016 -7.9 fatigue 90240 77920 -13.7 gas_dyn 119584 111456 -6.8 induct 174984 170848 -2.4 linpk 42640 50912 +19.4 mdbx 90232 78008 -13.5 nf 84072 63624 -24.3 protein 131976 111568 -15.5 rnflow 205584 176888 -14.0 test_fpu 179464 142584 -20.6 tfft 30680 34808 +13.5
