Skip to main content
836 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
0 votes
1 answer
73 views

When converting a matrix from one library to another, is there a way to assign the data pointers of the respective structures of matrices from Eigen, glm and ipp libraries instead of copying them ...
Vectorizer's user avatar
  • 1,514
1 vote
0 answers
108 views

I have a c++ code that uses Eigen for linear algebra calculations. The code runs on a cluster where there is a module with Intel MKL. I am completely ignorant of how to do it but I wanted to try to ...
Ratman's user avatar
  • 111
0 votes
1 answer
83 views

Following this best practices guide, I have a module in my Fortran code that defines a double precision type, module kind_parameters implicit none public ! Double precision real numbers, ...
Jasper's user avatar
  • 199
0 votes
0 answers
42 views

I find that MKL and OpenBLAS give slightly different SVD decompositions. I have this declaration of dgesvd, extern "C" { void dgesvd_(char const& jobu, char const& jobvt, int ...
alfC's user avatar
  • 16.8k
0 votes
1 answer
74 views

I have installed Intel oneAPI Math Kernel Library (oneMKL) on Windows 10 and then used the trick described here to slip those DLL's to R without having to recompile R. The 7-fold speedup of matrix ...
Tomas's user avatar
  • 60.2k
0 votes
0 answers
23 views

I am running a Fortran code on HPC machines with a lot of cores (say 36). Using parallel MKL, I set the number of cores to be used with the environment variable MKL_NUM_THREADS, while the ...
Ivanodivano's user avatar
  • 33
1 vote
0 answers
125 views

I've been trying to build ngsolve in WSL and I'm facing the following problem, I've installed intel mkl ONEAPI but while executing cmake -DCMAKE_INSTALL_PREFIX=${BASEDIR}/ngsolve-install ${BASEDIR}/...
SEBASTIÁN FERRA's user avatar
  • 11
2 votes
0 answers
109 views

I have a very simple 3D in-place FFT transform code with FFTW and openmp multi-thread support. I tried to get the best performance in a linux machine (Ubuntu with AMD Genoa CPUs -2 sockets). I built ...
readonly's user avatar
  • 31
1 vote
0 answers
142 views

I am compiling Fortran code with the ifx compiler (version 2025.0.4) on Windows. I have the Intel MKL library downloaded as well and I am trying to compile a program using it, like this: ifx test.f90 ...
FusRoDah's user avatar
  • 149
0 votes
1 answer
39 views

I'd like to use Intel's Math Kernel Library (MKL) to do some calculations. I've figured this out for MFC programs, but I'm having trouble with C++/WinRT & WinUI 3 programs. For a repro, I took ...
dr_eck's user avatar
  • 215
0 votes
0 answers
45 views

This is my first time working with the MKL library. After referring to the official documentation, I obtained the latest version of the MKL library via the apt package manager in the WSL2 Ubuntu ...
hamster_watcher's user avatar
  • 11
0 votes
0 answers
143 views

I am working on a problem where I need the full spectrum of a Hamiltonian matrix. I order to have a better performance, I am using ScaLAPACK routine PDSYEV to compute the eigenstates and eigenvalues ...
FortranZT's user avatar
  • 1
0 votes
1 answer
188 views

I need to produce a static .exe to distribute to users that have no VisualStudio, no Intel Fortran/oneAPI, and no MKL. My code "UgensTester.f90" worked fine since 2010 with yearly updates, ...
Echeban's user avatar
  • 204
1 vote
2 answers
283 views

How do I get Visual Studio 2019 configured with Intel Fortran 2023 to link the MKL linrary code into an EXE that is generated by building a Fortran project? A few MKL routines have been used in this ...
Echeban's user avatar
  • 204
1 vote
1 answer
306 views

I'm using a binary (R) that dynamically links to a generic version of BLAS, for instance (and in a lot of cases) this is openBLAS. Now, inside R, I'm dynamically loading another shared library (...
Daniel Falbel's user avatar
  • 1,723
1 vote
1 answer
84 views

Armadillo code: #define ARMA_DONT_USE_WRAPPER #define ARMA_USE_BLAS #define ARMA_USE_LAPACK arma::mat A = { { 0.0013 , 0.1741 , 0.9885 , 0.1662 , 0.8760 } , { 0....
Dock's user avatar
  • 13
1 vote
1 answer
173 views

I'm trying to use Eigen3 frontend with Intel MKL backend. I'm optimizing the program for AVX2 instruction set. When I define AVX2, I get the error below. If I don't define AVX2, I get SSE and SSE2 ...
Dark Sorrow's user avatar
  • 2,041
2 votes
1 answer
183 views

My general task: I have a Fortran Tool which uses the functions dgemm, dgemv, dgesvx and dsyev from the MKL Library. I need to compile my code as a shared object (.so) to make it work on a different ...
Toni's user avatar
  • 23
0 votes
1 answer
90 views

When building my university project on two different machines I experienced issues with LAPACK and Intel's implementation in MKL. I already figured out the main problem: I used the LAPACK headers from ...
Moritz Sigg's user avatar
  • 3
0 votes
0 answers
108 views

After Installing MKL I can't find those dll files. And the error continues. Intel MKL FATAL ERROR: cannot load mkl_vml_avx2.1.dll or mkl_vml_def.1.dll, at runtime. Libtorch Distrib I'm using is: CUDA ...
David Huelves Ramos's user avatar
  • 1
0 votes
0 answers
352 views

Environment: CPU: AMD r5 5600h Memory: 16G GPU: rtx3050 Python: 3.9.19 Pytorch: 2.2.2 Numpy: 1.24.3 Errors: Intel MKL ERROR: Parameter 6 was incorrect on entry to SGELSY. Intel MKL ERROR: ...
manto's user avatar
  • 1
3 votes
1 answer
171 views

I am writing a program that uses Intel's MKL to do some matrix multiplications. I have a frustrating requirement that only a custom version of dynamic memory allocation is utilized. I'm aware this ...
daroo's user avatar
  • 2,036
0 votes
1 answer
214 views

When I try to cross-compile for macOS on arm64 for x86_64, I have a problem with linking MKL static libraries. ld: unknown file type in 'libmkl_core.a', 'libmkl_sequential.a', 'libmkl_intel_lp64.a' ...
Kirill Golikov's user avatar
  • 1,384
2 votes
2 answers
881 views

I have a C++ project and built it with CMake. I have no problem on Windows. However when I tried it on WSL I got symbol lookup error: /opt/intel/oneapi/mkl/latest/lib/libmkl_intel_thread.so.2: ...
Savrona's user avatar
  • 388
0 votes
1 answer
807 views

Update 3 Changed NUMA_PER_MPI to 4 Changed P and Q to 1 and 2. While the above config does launch and run, it is significantly outperformed by setting MPI_PROC_NUM=8 MPI_PER_NODE=2 NUMA_PER_MPI=1 P&...
Grant Curell's user avatar
  • 1,873
0 votes
1 answer
244 views

The arithmetic intensity of sgemv (or dgemv) is derived in this set of exercises (https://florian.world/wp-content/uploads/FM-High-Performance-Computing-I-Assignment-1.pdf) to be: 0.5 / (1+c), where c ...
velenos14's user avatar
  • 586
1 vote
1 answer
218 views

I ran an Intel MKL LINPACK test on an Intel Core i7-14700K processor and got a peak performance of 557 GFLOPS which seems quite unrealistic. Size LDA Align. Average Maximal 1000 1000 4 ...
Sogawa-sps's user avatar
  • 159
0 votes
0 answers
1k views

This is my first time posting, so I apologize if I am missing anything that is common practice. For the last month or so, whenever I import anything on Jupyter Notebook, I have been getting warnings ...
surfy_sam's user avatar
  • 1
0 votes
0 answers
104 views

In the dense and sparse module of mkl I can transpose or conjugate a matrix in the same function that calls the multiplication. I think (but I'm not sure) that means that it's just changing the ...
manne's user avatar
  • 61
0 votes
0 answers
146 views

I found these: http://eigen.tuxfamily.org/dox/unsupported/classEigen_1_1KroneckerProductSparse.html http://eigen.tuxfamily.org/dox/unsupported/classEigen_1_1KroneckerProductBase.html However I'm ...
manne's user avatar
  • 61
0 votes
0 answers
46 views

I am using MKL LAPACKE_sgelss to compute least square solution to $Ax = b_j$, where $j \in [0 , nrhs) $, A is $m \times n$ matrix and $n < m < nrhs$. I somehow managed to extract the solution ...
VojtaK's user avatar
  • 708
1 vote
2 answers
3k views

I was trying to install Intel® oneAPI on my Mac but it seams that Intel has discontinued the support for Mac. intel.com Can I somehow work around it? Or download an old Version of oneAPI? I was trying ...
Z1M0N's user avatar
  • 21
0 votes
0 answers
115 views

I read some threads, but I still am not sure. What is the gain of using MKL in Eigen, if you can use MKL only? I am interested in sparse matrix multiplication, but everything is fine.
Mitto's user avatar
  • 1
2 votes
1 answer
72 views

I wrote two simple functions to learn CPython's behaviour regarding numpy arrays. Python 3.12.1 and numpy version 1.26.2, compiled by mkl (conda default) def foo(): for i in range(100): H =...
Paradoxy's user avatar
  • 163
0 votes
1 answer
153 views

In my project I'm doing massive use of the blas subroutines under the mkl implementation, I have no problems in compiling the project thanks to the Intel Advisor, but I can't get fortls to recognize ...
VINCENZO BISOGNO's user avatar
  • 1
0 votes
1 answer
1k views

The title says it already: I downloaded the so called oneMKL library from Intel at oneMKL Download page with the intent of using it with a (professional) version of Visual Studio 2022 on a Windows 10 ...
Jürgen Böhm's user avatar
  • 421
0 votes
1 answer
210 views

I have a subroutine that builds sparse matrices, and I need to call it several times. However, it seems that if I call this subroutine a lot of times (and/or if the sparse matrices are very large), ...
Looper's user avatar
  • 364
0 votes
0 answers
78 views

I am currently updating a piece of Code that eventually should be used inside a loop for time evolution. I have encountered some problems thatseem to come down to the notorious pointer allocation and ...
Peter Sanctus's user avatar
  • 1
0 votes
1 answer
135 views

Below is a minimum working example of the problem I ran into recently: My source code: // main.cc #define EIGEN_USE_MKL_ALL #include <Eigen/Sparse> #include <Eigen/PardisoSupport> int ...
Hans's user avatar
  • 61
0 votes
1 answer
457 views

I am trying to compile this project in Ubuntu(wsl). Intel-mkl libraries should be installed (sudo apt install intel-mkl) and faiss has been built and installed without seemingly any issues. However, ...
Jakub Kudlej's user avatar
  • 85
0 votes
1 answer
156 views

I've boiled a long running function down to a "simple" series of matrix vector multiplications. The matrix does not change, but there are a a lot of vectors. I have put together a test ...
js1's user avatar
  • 3
0 votes
0 answers
186 views

I have been trying FFTPack from CControl. I C library that have a lot of math stuffs. At the fft.c example, I have been checking the difference between Intels Math Kernel Library, and just normally ...
euraad's user avatar
  • 2,887
1 vote
2 answers
1k views

I am trying to build a C-project where I use the Math Kernel Library (MKL) by Intel to accelerate matrix multiplication as follows: #define MKL #ifdef MKL #include <mkl.h> #endif void ...
SuperKogito's user avatar
  • 2,966
0 votes
0 answers
151 views

I am trying to solve a large sparse matrix system using the PARDISO subroutine in Intel MKL. I completed writing a code in gfortran and makefile. But when I execute the makefile, the error message ...
DRK's user avatar
  • 1
1 vote
0 answers
21 views

I currently have a class that have a contructor based on importing some values from npz to a double pointer A. StateSystem::StateSystem(std::string filename) { cnpy::NpyArray A_npy = cnpy::...
Metersquared's user avatar
  • 11
2 votes
1 answer
122 views

I have an existing R script that performs various operations, and I'm looking to create a C sub function to optimize a specific part of it. My goal is to integrate this C sub function within R Desktop ...
Anastasia's user avatar
  • 23
0 votes
0 answers
93 views

I have DFT(density functional theory) code written in Fortran. Inside this program I use zheev function from lapack to diagonalize overlap matrix (S). I compile the code in two different targets (a) ...
Prokop Hapala's user avatar
  • 2,474
0 votes
0 answers
49 views

I am working on debugging a code. Let me say up front that it is not my code and I do not have permission to share a single line of it. I know we all like to see code, but that's my situation. It ...
bob.sacamento's user avatar
  • 6,713
7 votes
0 answers
3k views

I've always happened to use Intel cpus in intel chipset based servers, as such have used Intel's MPI and MKL for the past 20 years that's all I kinda know. With their OneAPI I only need and use MPI, ...
ron's user avatar
  • 1,035
0 votes
1 answer
159 views

I'm trying to write a program that is going to use both Arpack-ng and MKL routines. I was testing the behavior by running a simple code which use a single call to the function dsaupd, which should ...
VINCENZO BISOGNO's user avatar
  • 1

1
2 3 4 5
…
17