Stack Overflow
Stack Overflow

Questions tagged [cusolver]

a library that is part of the NVIDIA CUDA toolkit to accelerate various dense and sparse LAPACK-like operations on GPUs

cusolver is a library included with CUDA 7.0 and beyond, to provide GPU acceleration for 3 categories of linear algebra problems:

  1. cuSolverDN deals with dense matrix factorization and solve routines such as LU, QR, SVD and LDLT

  2. cuSolverSP provides a set of sparse routines based on a sparse QR factorization

  3. cuSolverRF is a sparse re-factorization package for solving a sequence of matrices where only the coefficients are changed but the sparsity pattern remains the same

cusolver documentation is here.

56 questions
1
vote
1 answer

Eigen decomposition of Hermitian Matrix using CuSolver does not match the result with matlab

I am following the example of eigen decomposition from here, https://github.com/NVIDIA/CUDALibrarySamples/blob/master/cuSOLVER/syevd/cusolver_syevd_example.cu I need to do it for Hermatian complex matrix. The problem is the eigen vector is not…
Mirage1089
  • 31
  • 4
1
vote
1 answer

Trying to run a CusolverSSgels testcase, however it is not working

I'm busy working on a LS method, I manually implemented a conjugate gradient solver, but after updating my CUDA version, I saw that there is a new function (cusolverDnSSgels) which I assume is faster than my manual implementation. My first task was…
Taliebram
  • 91
  • 6
1
vote
1 answer

CUDA - CUBLAS: issues solving many (3x3) dense linear systems

I am trying to solve about 1200000 linear systems (3x3, Ax=B) with CUDA 10.1, in particular using the CUBLAS library. I took a cue from this (useful!) post and re-wrote the suggested code in a Unified Memory version. The algorithm firstly performs a…
Kosuke88kk
  • 57
  • 4
1
vote
1 answer

cuSOLVER - Device version of cusolverSpScsrlsvqr is much slower than host version

I have sparse 3-diagonal NxN matrix A built by some rule and want to solve the system Ax=b. For this I'm using cusolverSpScsrlsvqr() from cuSolverSp module. Is it ok to have device version many times slower than cusolverSpScsrlsvqrHost() for large…
Powercoder
  • 695
  • 1
  • 5
  • 25
1
vote
1 answer

How to batch cusolver cholesky inverse (potri)?

Cusolver has Cholesky decomposition, unlike CUBLAS. I see cusolverDnDpotrsBatched and cusolverDnDpotrfBatched, but unfortunately I can't seem to find cusolverDnDpotriBatched in the documentation. Is there any way I can batch cusolverDnDpotri…
Krupip
  • 4,404
  • 2
  • 32
  • 54
1
vote
1 answer

cuSOLVER automatically parallelizes computation on many matrices?

I have to make same computations (for example, get eigenvalues of A1, A2, ...) on many(>10^15) matrices, so I want use threads as many as possible. But I couldn't find cuBLAS or cuSOLVER codes stating number of threads. Does cuSOLVER automatically…
SIM2
  • 11
  • 4
1
vote
1 answer

Can you use the GPU QR factorization algorithm from cuSOLVER in tensorflow?

I can see it's referenced in https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/cuda_solvers.h (Geqrf), but the tensorflow QR op at https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/qr_op_float.cc…
DDD
  • 45
  • 3
1
vote
1 answer

interfacing cuSolver with MATLAB

I like to use cuSolver code for Eigen value decomposition of complex matrix in Matlab. I am using MATLAB CUDA kernel and it seems that its not possible to interface cuSolver with MATLAB as the cuSolver contains the code for host as well as for…
Hassan Shahzad
  • 11
  • 3
1
vote
1 answer

Status: execution failed, when invoking cusolverDnDgeqrf from CUDA library

I try to perform a QR factorization on GPU using the cusolver library from CUDA. I reduced my problem to the example below. Basically, the few steps are : I allocate memory and initialized a [5x3] matrix with 1s on the host, I allocate memory and…
Tikoloche
  • 351
  • 1
  • 14
1
vote
1 answer

CUDA : cuSolver raises an exception

I am trying to use cusolver library to solve a number of linear equations but instead an exception is raised which is very strange. the code is using only one function from the library and the rest is memory allocation and memory copy. the function…
Ehab AlBadawy
  • 3,065
  • 4
  • 19
  • 31
1
vote
1 answer

Use scikit-cuda to compute singular value decomposition with cuSOLVER

I am trying to use scikit-cuda's wrappers for the cuSOLVER functions, in particular I want to execute cusolverDnSgesvd to compute full-matrix single precision SVD on a matrix of real numbers. Using the code here and here as a reference, I managed to…
Vektor88
  • 4,841
  • 11
  • 59
  • 111
1
vote
1 answer

CUDA 7.0, cuSolver example: unresolved inclusion of cudense.h

I am going through the cuSolver example in the documentation and getting the following error: fatal error: cudense.h: No such file or directory Compilation and Linking, "make -n": nvcc -c -I/usr/local/cuda-7.0/include main.cpp nvcc -o…
w0rldeat3r
  • 89
  • 2
  • 8
1
vote
1 answer

cusolverSpDcsrlsvlu or QR method using CUDA

I have searched the whole world but unable to solve this problem! "Unhandled exception at 0x00007FFF3AD3D430 (cusolver64_70.dll) in cusolver test.exe: 0xC0000005: Access violation reading location 0x0000000400960004." i want to solve Ax=B using…
Taha Saeedkhan
  • 13
  • 2
1
vote
0 answers

Call multiple CUDA SVD (in cuSolver)

I would use the SVD routine of CUDA 7.0 (cuSolver), i need to perform the SVD on all parts where i split the matrix (for example, dividing the matrix into 2x2 blocks, I want to perform four times the SVD in parallel) . The idea would be to invoke…
sim186
  • 39
  • 3
  • 10
1
vote
1 answer

undefined reference to cusolverDn

I am trying to run the cuSolver library available in cuda 7.0. I have an issue with using the cuSolver library that must be very simple to fix, but here I am asking for some help. I have looked at quite a few examples posted around and I chose in…
SRH
  • 23
  • 1
  • 6
1
2
3 4