Questions tagged [viennacl]

ViennaCL is, according to its website, a free open-source linear algebra library for computations on many-core architectures (GPUs, MIC) and multi-core CPUs. The library is written in C++ and supports CUDA, OpenCL, and OpenMP.

ViennaCL is, according to its website, a free open-source linear algebra library for computations on many-core architectures (GPUs, MIC) and multi-core CPUs. The library is written in C++ and supports CUDA, OpenCL, and OpenMP.

In addition to core functionality and many other features including BLAS level 1-3 support and iterative solvers, the latest release ViennaCL 1.4.1 now includes support for Intel's MIC platform (Xeon Phi) and features a GEMM kernel reaching more than 1.3 TFLOPs on an AMD HD7970.

17 questions
8
votes
1 answer

Differences between clBLAS and ViennaCL?

Looking at the OpenCL libraries out there I am trying to get a complete grasp of each one. One library in particular is clBLAS. Their website states that it implements BLAS level 1,2, & 3 methods. That is great but ViennaCL also has BLAS…
cdeterman
  • 19,630
  • 7
  • 76
  • 100
4
votes
0 answers

Measure custom kernel execution time in ViennaCL

I've got a custom kernel executing through ViennaCL with an OpenCL backend. While I know how to benchmark ViennaCL in general (provided in the docs) and how to execute an OpenCL kernel execution time when it is directly executed with events (both…
Pawel J. Wal
  • 1,166
  • 1
  • 11
  • 24
2
votes
0 answers

How to build a ViennaCl project using Visual C++ 2010?

I have successfully built ViennaCL using mingw32-make and run some of its generated tests on Windows 7 x64. When I try to build a new Viennacl project using Visual C++ 2010 Ultimate, the linker gives me the below answer: error LNK2019: riferimento…
Peter
  • 21
  • 2
1
vote
1 answer

Using RViennaCL for matrix multiplication

I'm a newbie using the RViennaCL package, trying to do GPU matrix multiplication. Trying a simple case I created a cpp file inside the src folder within the package I created (gpuUtils), with this code: #include "viennacl/ocl/backend.hpp" #include…
dan
  • 6,048
  • 10
  • 57
  • 125
1
vote
0 answers

OpenCL for signal processing

I'm looking to write signal processing code that will need the usual parallel primitives (e.g., scan(), reduce(), map(), and sort()) along with efficient routines for FFTs and dense vector/matrix operations to support stuff like principal component…
1
vote
1 answer

viennacl with complex numbers

I'm using viennacl to solve a linear system of equations (AX = B) with the graphic card. Also, the code uses armadillo. My system of equations have complex numbers. So the question is: Can I solve a system of equations (with complex numbers) using…
nunodsousa
  • 2,635
  • 4
  • 27
  • 49
1
vote
0 answers

PyViennaCL returns segfault

I have started programming with OpenCL, so far I used pyopencl package which is quite good for easy calculations but hard as heck to compute more advanced things. Idea was to use pyViennaCL, high-level alternative. I already installed ViennaCL and…
Cheshire
  • 5
  • 1
  • 3
1
vote
2 answers

C++ OpenCL matrix library with temporary elimination

The armadillo matrix library writes Armadillo employs a delayed evaluation approach to combine several operations into one and reduce (or eliminate) the need for temporaries. Where applicable, the order of operations is optimised. Delayed…
Jeremy Salwen
  • 8,061
  • 5
  • 50
  • 73
0
votes
1 answer

PyViennaCL installation using pip

I am trying to install PyViennaCL (https://github.com/viennacl/pyviennacl-dev) on Windows 10 64-bit and I am using Python 3.9.6. Using pip install pyviennacl, the error I received at first was that Visual C++ needed is version 14.0 or higher, I…
0
votes
1 answer

why I am getting this error "no instance of constructor", viennacl library in a CUDA optimizer, C++ console app

I am trying to run this C++ console app project using cmakefile and I am getting this error for a cuda optimizer which was written in this project. // wrap the existing CUDA CSR data in a viennacl::compressed_matrix: …
Ish Rj95
  • 45
  • 1
  • 7
0
votes
1 answer

Installing ViennaCL on Ubuntu

I have successfully built ViennaCL using cmake . and make and run some of its generated tests on Ubuntu 11.04. But how do I install it and how do I include and link it with my application? Shouldn't it generate headers and shared libraries that…
Nordlöw
  • 11,838
  • 10
  • 52
  • 99
0
votes
1 answer

Getting same result even after context switching

I am getting same result while running the matrix multiplication in both GPU and CPU. here is my code:. viennacl::ocl::set_context_platform_index(1, 1); viennacl::ocl::set_context_platform_index(0, 0); viennacl::ocl::switch_context(0); …
0
votes
1 answer

Mahout 0.13.0 spark-shell examples fails with "no jniViennaCL in java.library.path"

I'm Trying to make Mahout 0.13.0 works with spark 1.6.3, I already have spark 1.6.3 and Hadoop 2.7 working. I download the last build from the homepage mahout_download. Unpackage on /opt/mahout. try to execute the example on spark-shell from the…
0
votes
1 answer

Custom linear operators in ViennaCL

Is is possible to pass custom linear operators (like CUSP's http://cusplibrary.github.io/classcusp_1_1linear__operator.html) to ViennaCL's solvers? Thanks.
antony
  • 2,877
  • 4
  • 31
  • 43
0
votes
1 answer

ViennaCL: matrix-vector product fails

I'm trying to do a simple matrix-vector product with OpenCL, using the ViennaCL library. Here's my main: #include "viennacl/scalar.hpp" #include "viennacl/vector.hpp" #include "viennacl/matrix.hpp" #include "viennacl/linalg/prod.hpp" #include…
eyam
  • 139
  • 1
  • 8
1
2