Polyhedron Fortran Benchmarks: 64-bit Linux on Intel Core i5 2500k

Absoft(AP)
15.0.0
Absoft
15.0.0
G95
0.93
GFortran
4.9
Intel(AP)
15.0
Intel
15.0
Lahey
8.10b
NAG
6.0
Oracle
8.6
PGI
14.9
AC 4.49 4.53 9.60 5.72 4.79 4.70 8.00 6.51 21.99 5.83
AERMOD 10.95 10.69 25.99 14.89 11.56 10.61 11.27 16.93 10.30 10.55
AIR 1.37 2.72 5.95 2.86 0.98 2.26 2.71 4.17 2.51 2.88
CAPACITA 16.98 17.82 26.83 17.65 17.92 16.79 19.94 20.48 21.56 14.48
CHANNEL2 81.85 81.14 272.72 82.98 85.58 84.03 122.19 117.59 84.83 84.08
DODUC 16.88 16.97 24.05 17.08 13.59 13.58 17.45 21.40 14.15 16.07
FATIGUE2 58.79 53.79 374.38 64.80 50.23 50.55 110.88 102.98 75.28 81.18
GAS_DYN2 73.20 68.06 320.04 82.46 54.69 53.62 107.03 152.29 84.39 78.13
INDUCT2 28.44 67.19 147.53 65.59 26.42 63.33 93.29 117.01 125.91 112.96
LINPK 5.22 5.20 6.21 4.95 4.84 4.84 5.67 5.72 5.11 5.56
MDBX 7.13 8.17 8.68 7.16 3.45 5.71 7.85 8.00 7.41 8.03
MP_PROP_DESIGN 23.82 71.65 419.95 129.64 18.98 56.55 126.05 218.65 161.97 78.57
NF 7.67 7.68 13.40 6.99 7.10 7.04 10.36 8.39 8.16 7.56
PROTEIN 19.44 18.96 27.43 18.87 17.85 17.81 35.68 17.97 20.44 20.38
RNFLOW 15.68 15.64 25.90 11.98 9.35 11.30 14.58 14.68 15.72 14.78
TEST_FPU2 33.56 47.66 103.38 42.00 29.98 38.13 61.17 71.33 57.41 41.51
TFFT2 52.81 53.21 60.04 42.15 53.38 53.52 55.74 57.13 55.07 54.21
Geometric Mean 16.85 20.08 43.13 20.89 14.40 17.72 26.07 27.97 25.04 21.49
Compiler Switches
Absoft(AP) af90 -m64 -mavx -O5 -speed_math=10 -march=core -xINTEGER (These settings enable auto-parallelization, see below)
Absoft af90 -m64 -mavx -O4 -speed_math=10 -march=core -xINTEGER
G95 g95 -march=nocona -ffast-math -funroll-loops -O3
GFortran gfortran -ffast-math -funroll-loops -O3
Intel(AP) ifort -O3 -fast -parallel -ipo (These settings enable auto-parallelization, see below)
Intel ifort -O3 -fast -ipo
Lahey lf95 –fast -static -x –
NAG nagfor -O4 -s -v -V
PGI pgf95 -V -fast -Mipa=fast,inline -Msmartalloc -Mfprelaxed -Mstack_arrays
Oracle
sunf95 -fast -xtarget=nehalem -xipo=2 -m64 -xvector=simd
Notes
All figures are Execution Times in Seconds – measured on a machine with a Core i5 2500k 3.30GHz processor, running at stock speed, with 16 GBytes memory, and running 64-bit Scientific Linux 6 (a near-clone of Red Hat Enterprise Linux 6). Each figure is the average over at least 10 runs (many more for some). Measurement error is typically <1%. Green cells highlight figures within 10% of the fastest. Red cells indicate figures which are more than 150% of the fastest.So far as possible, we have used the compiler switches which give the best overall results. We have not attempted to tune individual benchmarks, and, in particular cases, different switch settings may give better results.The settings used for the Intel and Absoft compilers enable autoparallelization. Autoparallelization settings are not used on any other compilers because we found that they produced no significant performance benefits on this benchmark set.Thanks are due to Jos Bergervoet for permission to use his CAPACITA benchmark, to Quetzal Associates for permission to use their CHANNEL, FATIGUE, GAS_DYN, INDUCT, PROTEIN and RNFLOW benchmarks, to David Frank for his TEST_FPU benchmark, to Anthony Falzone for the use of MP_PROP_DESIGN, and to Ted Addison of McVehil-Monnett Associates for permission to use AERMOD, an air quality model used by the US Environmental Protection Agency.All the benchmarks have been modified slightly to fit into our benchmarking harness.The NF benchmark uses “nested factorization”, a little known but very effective iterative linear solver for huge finite difference matrices. A paper describing nested factorization, and comparing it to other methods is available here.

Other benchmark sets:

Intel/Windows

AMD/Windows

AMD/Linux

 

 

Return to Fortran Compiler Comparisons homepage