Stack Overflow
Stack Overflow

Questions tagged [blas]

The Basic Linear Algebra Subprograms are a standard set of interfaces for low-level vector and matrix operations commonly used in scientific computing.

A reference implementation is available at NetLib; optimized implementations are also available for all high-performance computing architectures, for example:

The BLAS routines are divided into three levels:

  • Level 1: vector operations e.g. vector addition, dot product
  • Level 2: matrix-vector operations e.g. matrix-vector multiplication
  • Level 3: matrix-matrix operations e.g. matrix multiplication
906 questions
0
votes
1 answer

MKL dtrsv wrong output

I am trying to properly use 'cblas_dtrsv' however I do not get right output and I do not know why. Here is my example(dtrsv_example.c) #include #include #include "mkl.h" int main() { double *A, *b, *x; int m, n, k, i, j; …
Manolete
  • 3,431
  • 7
  • 54
  • 92
0
votes
1 answer

Inconsistent performance when multi-threading with Armadillo and OpenBLAS

Using Armadillo I wrote a matrix-vector multiplication and a linear system solve. Armadillo is compiled from source and uses OpenBLAS, also compiled from source. Unfortunately I am getting inconsistent results for single-threaded and multi-threaded…
Aeronaelius
  • 1,291
  • 3
  • 12
  • 31
0
votes
2 answers

How to install lapack++ on linux

I'm making a script on c++ that requires the resolution of linear systems. I've looked around and found that the LAPACK++ gives me functions to achieve that end. However I've been having a lot of trouble just getting them installed. I have the…
Daniel Jaló
  • 147
  • 1
  • 3
  • 11
0
votes
0 answers

numpy.dot stucks. Maybe linked with BLAS?

When I use numpy.dot in a python programm, my programm stucks. Not always, but sometimes. By stucking I mean, my programm stops to use CPU, doesn't return error, just do nothing, but doesn't crash. As I understand numpy.dot uses BLAS library. So to…
Pigeno
  • 1
  • 1
0
votes
2 answers

Anyone can show me an example of the function dspr in openblas

I am trying to use the function dspr in Openblas with Rcpp. the purpose of dspr is: A := alpha*x*x**T + A In my case, firstly I define A as a matrix with all the elements are 0, alpha=1, x=(1,3), so, the final matrix A should be {(1,3),(3,9)}, but…
Jason_C
  • 1
0
votes
1 answer

Efficient implementation of indirect daxpy operation

_axpy is a blas level one operation which implements following for i = 1:n a[i] = a[i]-$\alpha$ b[i] There are efficient implementation of such regular daxpy available through various blas libraries such as MKL. In my case I want to implement…
arbitUser1401
  • 575
  • 2
  • 8
  • 25
0
votes
1 answer

cblas_dgemm segmentation fault

I'm using cblass_dgemm to multiply two matrices It is supposed to calculate B = A' x A; row_train = 10304, col_train = 5; gsl_matrix *mean_centred_train = gsl_matrix_alloc(row_train, col_train); gsl_matrix * image_for_eigen =…
Tal_
  • 761
  • 2
  • 6
  • 13
0
votes
2 answers

Speedily create a random array

I have a for-loop: for (i=0; i
Scott
  • 2,568
  • 1
  • 27
  • 39
0
votes
1 answer

some trouble when install scikit-learn in Ubuntu

I just download the scikit-learn install package from https://pypi.python.org/pypi/scikit-learn/. Before install the package, I install several dependent package using apt-get: sudo apt-get install build-essential python-dev python-numpy…
Jun HU
  • 3,176
  • 6
  • 18
  • 21
0
votes
1 answer

Lower triangular solve using dtrsv() BLAS level 2

i m trying to solve L*u=u using blas level2 function dtrsv() for matrix(L) order 100 and vector(u) 100. i linked libraries with "-lblas" at compile time. but, it says undefined reference to dtrsv(). Also how do i calculate Gflops/sec for this.(i m…
user2530405
  • 3
  • 1
0
votes
1 answer

-framework Accelerate, where to include

I'm trying to compile someone else's code and there isn't a simple header file. I need to link the default lapack and blas libraries on osx, and after some searching I figured they're in the Accelerate framework, and in my make.inc I used something…
user2924321
  • 51
  • 1
  • 4
0
votes
1 answer

use DGEMM BLAS in windows eclipse

I am trying to execute this code in eclipse but i have no idea how to use dgemm. I know it is part of BLAS but i don't understand how to use it in windows. If ther are any other libraries o algorithms that can be use for high performance calculation…
Maik Xhani
  • 65
  • 8
0
votes
1 answer

Still the link errors about Intel-MKL

This is the configuration of QT project: unix { INCLUDEPATH += /opt/intel/mkl/include LIBS += -L/opt/intel/mkl/lib/intel64 \ -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -lmkl_def \ -liomp5 -lpthread -ldl -lm } And the…
mining
  • 3,557
  • 5
  • 39
  • 66
0
votes
1 answer

Huge sparse matrix - vector multiplication

I'm looking for a library to do huge Sparse Matrix x Vector multiplication. The matrix itself will almost fill the RAM. I've found Eigen3, OSKI and some basic Sparse BLAS implementations. Are there other options? How can I choose between them…
Łukasz Lew
  • 48,526
  • 41
  • 139
  • 208
0
votes
1 answer

How do I pull in unexpected build dependencies of standard libraries

I feel somewhat ridiculous, but I'm trying to import the OpenBLAS libraries into a project. They were built with gfortran as the Fortran compiler. My early builds had no issue just pulling libopenblas.so in, but on another system, it's choking on…
Sean Duggan
  • 1,105
  • 2
  • 18
  • 48
1 2 3
…
60 61