f67b19a884
From 68d431b4c14ad60a778ee93c1f59ecc4b931950e Mon Sep 17 00:00:00 2001 Found via `codespell -q 3 -I ../eigen-word-whitelist.txt` where the whitelists consists of: ``` als ans cas dum lastr lowd nd overfl pres preverse substraction te uint whch ``` --- CMakeLists.txt | 26 +++++++++---------- Eigen/src/Core/GenericPacketMath.h | 2 +- Eigen/src/SparseLU/SparseLU.h | 2 +- bench/bench_norm.cpp | 2 +- doc/HiPerformance.dox | 2 +- doc/QuickStartGuide.dox | 2 +- .../Eigen/CXX11/src/Tensor/TensorChipping.h | 6 ++--- .../Eigen/CXX11/src/Tensor/TensorDeviceGpu.h | 2 +- .../src/Tensor/TensorForwardDeclarations.h | 4 +-- .../src/Tensor/TensorGpuHipCudaDefines.h | 2 +- .../Eigen/CXX11/src/Tensor/TensorReduction.h | 2 +- .../CXX11/src/Tensor/TensorReductionGpu.h | 2 +- .../test/cxx11_tensor_concatenation.cpp | 2 +- unsupported/test/cxx11_tensor_executor.cpp | 2 +- 14 files changed, 29 insertions(+), 29 deletions(-) |
||
|---|---|---|
| .. | ||
| btl | ||
| perf_monitoring | ||
| spbench | ||
| tensors | ||
| analyze-blocking-sizes.cpp | ||
| basicbench.cxxlist | ||
| basicbenchmark.cpp | ||
| basicbenchmark.h | ||
| bench_gemm.cpp | ||
| bench_multi_compilers.sh | ||
| bench_norm.cpp | ||
| bench_reverse.cpp | ||
| bench_sum.cpp | ||
| bench_unrolling | ||
| benchBlasGemm.cpp | ||
| benchCholesky.cpp | ||
| benchEigenSolver.cpp | ||
| benchFFT.cpp | ||
| benchGeometry.cpp | ||
| benchmark_suite | ||
| benchmark-blocking-sizes.cpp | ||
| benchmark.cpp | ||
| benchmarkSlice.cpp | ||
| benchmarkX.cpp | ||
| benchmarkXcwise.cpp | ||
| BenchSparseUtil.h | ||
| BenchTimer.h | ||
| BenchUtil.h | ||
| benchVecAdd.cpp | ||
| check_cache_queries.cpp | ||
| dense_solvers.cpp | ||
| eig33.cpp | ||
| geometry.cpp | ||
| product_threshold.cpp | ||
| quat_slerp.cpp | ||
| quatmul.cpp | ||
| README.txt | ||
| sparse_cholesky.cpp | ||
| sparse_dense_product.cpp | ||
| sparse_lu.cpp | ||
| sparse_product.cpp | ||
| sparse_randomsetter.cpp | ||
| sparse_setter.cpp | ||
| sparse_transpose.cpp | ||
| sparse_trisolver.cpp | ||
| spmv.cpp | ||
| vdw_new.cpp | ||
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)