With the advent of dynamic parallelism in 3.5 and above CUDA architectures, is it possible to call linear algebra libraries from within __device__ functions?
Can the CUSOLVER library in CUDA 7 be called from a kernel (__global__) function?
0
votes
The one word answer is no. These libraries have excellent documentation, you could try reading them.
- talonmies
I just wanted to be sure of the answer. I used a C code to perform eigenvalues decomposition of several small matrices..each thread performs the decomposition of a matrix..but it was very slow (10 ms) I'm looking for a way to accelerate it
- Didon
1 Answers
4
votes
CUBLAS library functions can be called from device code.
Thrust algorithms can be called from device code.
Various CURAND functions can be called from device code.
Other libraries that are part of the CUDA toolkit at this time (i.e. CUDA 7) -- CUFFT, CUSPARSE, CUSOLVER -- can only be used from host code.
