Rindow Math Matrix is the fundamental package for scientific matrix operation
- A powerful N-dimensional array object
- Sophisticated (broadcasting) functions
- A high-speed calculation library written in C/C++.
- Useful linear algebra and random number capabilities
- Parallel calculation with native multi-threading or OpenMP
You can call a high-speed calculation library written in C language to speed up matrix calculation processing. Rindow Matlib includes many matrix operations functions used in machine learning.
Please see the documents about rindow mathematics on Rindow Mathematics web pages.
- Windows(10/11) , Linux(Ubuntu 22.04-, Debian 12-), MacOS(13/14) or later
Download the pre-build binary file.
Unzip the file for Windows and copy rindowmatlib.dll to the directory set in PATH.
The standard DLLs in the Bin directory is the thread version. Subdirectories contain OpenMP and Serial versions.
C> PATH %PATH%;C:\path\to\binDownload the pre-build binary file.
Please install using the apt command.
$ sudo apt install ./rindow-matlib_X.X.X_amd64.debDownload the pre-build binary file.
Extract the tar.gz file to the tmp directory and navigate to the directory.
$ tar -xzf rindow-matlib-X.X.X-Darwin-XXX.tar.gz -C /tmp
$ cd /tmp/rindow-matlib-X.X.X-Darwin-XXXThe standard dylib in the Lib directory is the thread version. Subdirectories contain OpenMP and Serial versions.
Next, copy the include and lib directories to /usr/local.
$ sudo cp -r usr/include /usr/local/
$ sudo cp -r usr/lib /usr/local/If you want to use OpenMP Please type brew install libomp
Since rindow-matlib currently uses ptheads, so you should choose the pthread version for OpenBLAS as well. In version 1.0 of Rindow-matlib we recommended the OpenMP version, but now we have changed our policy and are recommending the pthread version.
Using the OpenMP version of OpenBLAS can cause conflicts and become unstable and slow. This issue does not occur on Windows.
If you have already installed the OpenMP version of OpenBLAS, you can delete it and install pthread version.
$ sudo apt install libopenblas0-pthread liblapacke
$ sudo apt remove libopenblas0-openmpBut if you can't remove it, you can switch to it using the update-alternatives command.
$ sudo update-alternatives --config libopenblas.so.0-x86_64-linux-gnu
$ sudo update-alternatives --config liblapack.so.3-x86_64-linux-gnuBut, If you really want to use the OpenMP version of OpenBLAS, please switch to the OpenMP version of rindow-matlib.
$ sudo update-alternatives --config librindowmatlib.so
There are 1 choices for the alternative librindowmatlib.so (providing /usr/lib/librindowmatlib.so).
Selection Path Priority Status
------------------------------------------------------------
* 0 /usr/lib/rindowmatlib-thread/librindowmatlib.so 100 auto mode
1 /usr/lib/rindowmatlib-openmp/librindowmatlib.so 95 manual mode
2 /usr/lib/rindowmatlib-serial/librindowmatlib.so 90 manual mode
3 /usr/lib/rindowmatlib-thread/librindowmatlib.so 100 manual mode
Press <enter> to keep the current choice[*], or type selection number: 1Choose the "rindowmatlib-serial".
You can also build and use from source code.
Download source code from release and unzip
Build with Visual Studio.
C> cd \path\to\here
C> cmake -S . -B build
C> cmake --build build --config Release
C> cd build
C> ctest -C Release
C> cpack -C Release
C> cd ..\packagesUnzip the package file from packages directory.
C> PATH %PATH%;C:\path\to\binYou can also build and use from source code.
Download source code from release and extract
Build with cmake.
$ sudo apt install build-essential cmake
$ cd \path\to\here
$ cmake -S . -B build
$ cmake --build build --config Release
$ (cd build; ctest -C Release)
$ (cd build; cpack -C Release)Install with apt command.
$ sudo apt install ./packages/rindow-matlib_X.X.X_amd64.debYou can also build and use from source code.
Download source code from release and extract
Install openmp library with brew before build with cmake.
$ brew install libomp
$ cd \path\to\here
$ cmake -S . -B build
$ cmake --build build --config Release
$ (cd build; ctest -C Release)
$ (cd build; cpack -C Release)#include <iostream>
#include <string>
#include <iomanip>
#include <rindow/matlib.h>
void printMatrix(int m, int n, void *matrix)
{
float *v = (float *)matrix;
for(int i=0; i<m; i++) {
for(int j=0; j<n; j++) {
std::cout << std::setw(4) << v[i*n+j] << ",";
}
std::cout << std::endl;
}
}
int main(int ac, char **av)
{
const int M = 2;
const int N = 3;
// float
float sX[N] = {1, 2, 3};
float sY[M][N] = {{1,10,100}, {-1,-10,-100}};
float alpha = 2.0;
std::cout << "X:" << std::endl;
printMatrix(1, N, sX);
std::cout << std::endl << "Y:" << std::endl;
printMatrix(M, N, sY);
std::cout << std::endl << "alpha:" << std::endl;
std::cout << std::setw(4) << alpha << std::endl;
rindow_matlib_s_add(
RINDOW_MATLIB_NO_TRANS, // int32_t trans,
M, // int32_t m,
N, // int32_t n,
alpha, // float alpha,
(float *)&sX, // float *x,
1, // int32_t incX,
(float *)&sY, // float *a,
N // int32_t ldA
);
std::cout << std::endl << "Results:" << std::endl;
printMatrix(M, N, sY);
std::string mode;
switch(rindow_matlib_common_get_parallel()) {
case RINDOW_MATLIB_SEQUENTIAL: {
mode = "SEQUENTIAL";
break;
}
case RINDOW_MATLIB_THREAD: {
mode = "THREAD";
break;
}
case RINDOW_MATLIB_OPENMP: {
mode = "OPENMP";
break;
} default: {
mode = "UNKOWN";
break;
}
}
std::cout << mode << std::endl;
return 0;
}C> cl /EHsc -I.\path\to\include sample.cpp \path\to\lib\rindowmatlib.lib$ g++ sample.cpp -lrindowmatlib -lm$ c++ sample.cpp -lrindowmatlib -lm