Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
inline PTX to support subgroup shuffle for Nvidia GPUs
|
|
|
|
|
|
|
|
|
|
and standard-deviation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results based on kernel pre-processor
|
|
|
|
|
|
|
|
|
|
support for multi-kernel routines
|
|
|
|
|
|
the CLBlast library
|
|
|
|
|
|
|
|
|
|
|
|
GEMM kernel selection tuner
|
|
results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
it belongs
|
|
|
|
|
|
|