Mj23366 e057be831f first commit 10 месяцев назад
..
btl e057be831f first commit 10 месяцев назад
perf_monitoring e057be831f first commit 10 месяцев назад
spbench e057be831f first commit 10 месяцев назад
tensors e057be831f first commit 10 месяцев назад
BenchSparseUtil.h e057be831f first commit 10 месяцев назад
BenchTimer.h e057be831f first commit 10 месяцев назад
BenchUtil.h e057be831f first commit 10 месяцев назад
README.txt e057be831f first commit 10 месяцев назад
analyze-blocking-sizes.cpp e057be831f first commit 10 месяцев назад
basicbench.cxxlist e057be831f first commit 10 месяцев назад
basicbenchmark.cpp e057be831f first commit 10 месяцев назад
basicbenchmark.h e057be831f first commit 10 месяцев назад
benchBlasGemm.cpp e057be831f first commit 10 месяцев назад
benchCholesky.cpp e057be831f first commit 10 месяцев назад
benchEigenSolver.cpp e057be831f first commit 10 месяцев назад
benchFFT.cpp e057be831f first commit 10 месяцев назад
benchGeometry.cpp e057be831f first commit 10 месяцев назад
benchVecAdd.cpp e057be831f first commit 10 месяцев назад
bench_gemm.cpp e057be831f first commit 10 месяцев назад
bench_move_semantics.cpp e057be831f first commit 10 месяцев назад
bench_multi_compilers.sh e057be831f first commit 10 месяцев назад
bench_norm.cpp e057be831f first commit 10 месяцев назад
bench_reverse.cpp e057be831f first commit 10 месяцев назад
bench_sum.cpp e057be831f first commit 10 месяцев назад
bench_unrolling e057be831f first commit 10 месяцев назад
benchmark-blocking-sizes.cpp e057be831f first commit 10 месяцев назад
benchmark.cpp e057be831f first commit 10 месяцев назад
benchmarkSlice.cpp e057be831f first commit 10 месяцев назад
benchmarkX.cpp e057be831f first commit 10 месяцев назад
benchmarkXcwise.cpp e057be831f first commit 10 месяцев назад
benchmark_suite e057be831f first commit 10 месяцев назад
check_cache_queries.cpp e057be831f first commit 10 месяцев назад
dense_solvers.cpp e057be831f first commit 10 месяцев назад
eig33.cpp e057be831f first commit 10 месяцев назад
geometry.cpp e057be831f first commit 10 месяцев назад
product_threshold.cpp e057be831f first commit 10 месяцев назад
quat_slerp.cpp e057be831f first commit 10 месяцев назад
quatmul.cpp e057be831f first commit 10 месяцев назад
sparse_cholesky.cpp e057be831f first commit 10 месяцев назад
sparse_dense_product.cpp e057be831f first commit 10 месяцев назад
sparse_lu.cpp e057be831f first commit 10 месяцев назад
sparse_product.cpp e057be831f first commit 10 месяцев назад
sparse_randomsetter.cpp e057be831f first commit 10 месяцев назад
sparse_setter.cpp e057be831f first commit 10 месяцев назад
sparse_transpose.cpp e057be831f first commit 10 месяцев назад
sparse_trisolver.cpp e057be831f first commit 10 месяцев назад
spmv.cpp e057be831f first commit 10 месяцев назад
vdw_new.cpp e057be831f first commit 10 месяцев назад

README.txt


This folder contains a couple of benchmark utities and Eigen benchmarks.

****************************
* bench_multi_compilers.sh *
****************************

This script allows to run a benchmark on a set of different compilers/compiler options.
It takes two arguments:
- a file defining the list of the compilers with their options
- the .cpp file of the benchmark

Examples:

$ ./bench_multi_compilers.sh basicbench.cxxlist basicbenchmark.cpp

g++-4.1 -O3 -DNDEBUG -finline-limit=10000
3d-3x3 / 4d-4x4 / Xd-4x4 / Xd-20x20 /
0.271102 0.131416 0.422322 0.198633
0.201658 0.102436 0.397566 0.207282

g++-4.2 -O3 -DNDEBUG -finline-limit=10000
3d-3x3 / 4d-4x4 / Xd-4x4 / Xd-20x20 /
0.107805 0.0890579 0.30265 0.161843
0.127157 0.0712581 0.278341 0.191029

g++-4.3 -O3 -DNDEBUG -finline-limit=10000
3d-3x3 / 4d-4x4 / Xd-4x4 / Xd-20x20 /
0.134318 0.105291 0.3704 0.180966
0.137703 0.0732472 0.31225 0.202204

icpc -fast -DNDEBUG -fno-exceptions -no-inline-max-size
3d-3x3 / 4d-4x4 / Xd-4x4 / Xd-20x20 /
0.226145 0.0941319 0.371873 0.159433
0.109302 0.0837538 0.328102 0.173891


$ ./bench_multi_compilers.sh ompbench.cxxlist ompbenchmark.cpp

g++-4.2 -O3 -DNDEBUG -finline-limit=10000 -fopenmp
double, fixed-size 4x4: 0.00165105s 0.0778739s
double, 32x32: 0.0654769s 0.075289s => x0.869674 (2)
double, 128x128: 0.054148s 0.0419669s => x1.29025 (2)
double, 512x512: 0.913799s 0.428533s => x2.13239 (2)
double, 1024x1024: 14.5972s 9.3542s => x1.5605 (2)

icpc -fast -DNDEBUG -fno-exceptions -no-inline-max-size -openmp
double, fixed-size 4x4: 0.000589848s 0.019949s
double, 32x32: 0.0682781s 0.0449722s => x1.51823 (2)
double, 128x128: 0.0547509s 0.0435519s => x1.25714 (2)
double, 512x512: 0.829436s 0.424438s => x1.9542 (2)
double, 1024x1024: 14.5243s 10.7735s => x1.34815 (2)