Questions tagged [cusparse]
9 questions
0
votes
1 answer
How can I call the functions in the cuSPARSE library in a __device__ function?
I want to call the sparse matrix multiplication function in cuSPARSE library inside the kernel instead of directly calling it at the host side. I write a __device__ function to implement it.My CUDA is 11.3 and My hardware is V100.My code all follows…

ben286
- 1
- 1
0
votes
1 answer
function cusparseScsr2csc in cuSPARSE library return strange result
I want to test the cusparseScsr2csc which is a function used to convert a csr format matrix to a csc format matrix (or just say transpose a csr format matrix), so I write the code below to test it.
the wrapper:
CSR Csr2csc(int m, int n, int…

yys_c
- 15
- 6
0
votes
0 answers
Adding cusparse dependency in meson build
I am building an application with meson that uses NVIDIA cuSPARSE library. Currently, I have to hard code the cusparse version information into the dependency as shown below:
cusparse_dep = dependency('cusparse-10.3', version : '>=10.0')
The…

nahmad
- 41
- 2
0
votes
1 answer
Is it possible to use HYB or ELL sparse matrix multiplication(SPMV) in CUSPARSE 11?
I am updating my CUDA code with sparse matrix multiplication(SPMV). I found the HYB or ELL format sparse matrix related functions in cuSparse 11 are removed. But for my practical problem, HYB format SPMV runs better than CSR format. Is there any…

Wei Zhang
- 325
- 2
- 16
0
votes
1 answer
internal error when trying to perform matrix transpose using cusparseCsr2cscEx2() function of cuSPARSE
I am need to perform transpose of a matrix(CSR) using cuSPARSE, but get “internal error”. I write my code referring to How to transpose a sparse matrix in cuSparse? and https://docs.nvidia.com/cuda/cusparse/index.html#csr2cscEx2. To make it more…

hellohawaii
- 3,074
- 6
- 21
0
votes
1 answer
Meaning of 'i' in function names `cusparseaxpyi` and `cusparsedoti`
cusparseaxpyi and cusparsedoti are function names in cuSPARSE, the CUDA sparse matrix library.
The naming conventions section explains denotes data types, and axpyi, doti, roti all denote operations. However it does not further explain…

Jing Zhao
- 2,420
- 18
- 21
0
votes
1 answer
How to use cusparseXcoo2csr in cuSparse to convert from coo to csc?
In the documentation of cuSparse, it stated that the function cusparseXcoo2csr
can also be used to convert the array containing the uncompressed
column indices (corresponding to COO format) into an array of column
pointers (corresponding to CSC…

user3667089
- 2,996
- 5
- 30
- 56
0
votes
1 answer
How to get the diagonal of a sparse matrix in cuSparse?
I have a sparse matrix in cuSparse and I want to extract the diagonal. I can't seem to find a way to do it other than converting it back to CPU memory into Eigen SparseMatrix and use the .diagonal provided by Eigen to do it, and then copy the result…

user3667089
- 2,996
- 5
- 30
- 56
-2
votes
1 answer
Assemble COO matrix from a list of possibly repeated triplets in CUDA
Given a std::vector> its possible to create a Eigen::SparseMatrix using setFromTriplets function. This function, by default, accumulates repeated triplets.
I am trying to move my simulator code to CUDA and I have to…

jjcasmar
- 1,387
- 1
- 18
- 30