67d8199165
* Added infrastructure for implementation op lu for both cuda and cpu platforms. * Added implementation of helpers with lu op. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored LU decomposition to use vector of permutations instead. * Refactored helpers for lu op. * Fixed crash with determinant op. * Refactored cpu LU op heleper. * Added implementation for lu op. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed issue with argmax on column. * Added multithreaded behaviour for lu op helper. * Fixed multithreaded cpu implementation helpers for lu op. * Added cuda implementation for lu op helper. * Finished lu helper implementation for cuda platform. * Eliminated waste prints and comments. * Fixed race condition and multithreading issues. * Fixed memory leak with shape construction. * Corrected test for lu op to avoid near zero elements on the main diagonal." Signed-off-by: shugeo <sgazeos@gmail.com> * Improved test for adjust_constast op. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed issues with cuda implementation of resize_bicubic helpers. Signed-off-by: shugeo <sgazeos@gmail.com> |
||
|---|---|---|
| .. | ||
| activations | ||
| bitwise | ||
| blas | ||
| boolean | ||
| broadcastable | ||
| color_models | ||
| datatypes | ||
| flow | ||
| grad | ||
| helpers | ||
| kernels | ||
| list | ||
| loss | ||
| nlp | ||
| nn | ||
| parity_ops | ||
| random | ||
| recurrent | ||
| shape | ||
| tests | ||
| thrid_party | ||
| transforms | ||
| tsne | ||
| CustomOperations.cpp | ||
| README.md | ||
| parity_ops.cpp | ||
README.md
Generic ops
Put any cross platform operations here. Anything platform specific should be put in: in ops/helpers.