| Commit message (Collapse) | Author | Age |
|\
| |
| |
| | |
Disable vectorization on device only when compiling for sycl
|
| | |
|
| |
| |
| |
| | |
isn't available on MacOS
|
|\ \
| |/
|/| |
|
| | |
|
|\ \
| |/
|/|
| | |
Fixed the ambiguity in callig make_tuple for sycl backend.
|
|\ \ |
|
| | |
| | |
| | |
| | | |
Fix type in lgamma_impl<double>.
|
| |/ |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
|/ |
|
| |
|
| |
|
| |
|
| |
|
|\ |
|
| | |
|
| | |
|
| | |
|
|\ \ |
|
| | | |
|
| | | |
|
|\ \ \
| | |/
| |/| |
|
| | | |
|
| | | |
|
| | | |
|
|\ \ \
| | |/
| |/| |
|
| | | |
|
| |/
|/|
| |
| | |
CUDA by using scalar_sum_op and scalar_product_op instead of operator+ and operator*.
|
| | |
|
| |\ |
|
| | | |
|
| | | |
|
| | | |
|
| | | |
|
| | | |
|
| |/
|/| |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
| |
| |
| | |
numbers on cuda gpus.
|
| | |
|
| | |
|