Benchmarks report

Generated on 2011-08-04, 04:39 AM

CPU: Intel(R) Core(TM) i7-2600K CPU @ 3.40GHz

Total memory: 8173540 kB

Input file: /home/spiros/git/auto-numerical-bench/blastests.in
# GCC
openblas-gcc-threads sci-libs/openblas-0.1_alpha2 CC=gcc-4.6.1 CXX=g++-4.6.1 CFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" CXXFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" TARGET=NEHALEM USE="incblas threads -openmp"
openblas-gcc-openmp sci-libs/openblas-0.1_alpha2 CC=gcc-4.6.1 CXX=g++-4.6.1 CFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" CXXFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" TARGET=NEHALEM USE="incblas -threads openmp"
eigen-gcc dev-cpp/eigen-3.0.1-r1 CC=gcc-4.6.1 CXX=g++-4.6.1 CFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" CXXFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2"
atlas-gcc sci-libs/atlas-3.9.46 FC=gfortran-4.6.1 CC=gcc-4.6.1 FFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2" CFLAGS="-O3 -pipe -march=native -msse3 -mssse3 -msse4.1 -msse4.2"
Logs: /var/log/benchmarks/blas_2011-08-04

Summary

y = a*x + y

Apply Givens rotation

Matrix-Vector multiply

Transposed Matrix-Vector multiply (A' * x)

Symmetric Matrix-Vector multiply

Rank-1 update

Symmetric Rank-2 update

Triangular system solution

Matrix-Matrix multiply

Symmetric Rank-n update

Triangular system solution with n right hand side vectors

Triangular Matrix-Matrix multiply