| Age | Commit message (Collapse) | Author |
|---|
|
|
|
results for Iris Pro
|
|
|
|
|
|
according to the C++11 standard
|
|
this makes the test work, it does not focus on good performance
|
|
|
|
|
|
|
|
|
|
preparation of per-kernel database overrides)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
TRSM
|
|
|
|
|
|
all devices
|
|
favour the regular kernel
|
|
|
|
|
|
|
|
|
|
Since the codebase is designed around proper C++ idioms such as RAII, it
makes sense to only use C++ exceptions internally instead of mixing
exceptions and error codes. The exceptions are now caught at top level
to preserve compatibility with the existing error code-based API.
Note that we deliberately do not catch C++ runtime errors (such as
`std::bad_alloc`) nor logic errors (aka failed assertions) because no
actual handling can ever happen for such errors.
However, in the C interface we do catch _all_ exceptions (...) and
convert them into a wild-card error code.
|
|
variable in a namespace and its container uses const-pointers to the actual data
|
|
|
|
|
|
|
|
|
|
Intel GPUs
|
|
|
|
|
|
GEMM kernels
|
|
|
|
NWGD and KWGD into one WGD parameter
|
|
indirect version
|
|
now automatically taken from 32-bit if there are no entries at all
|
|
and convienient plain JSON/dict data-type
|
|
M370X GPU
|
|
best-performing cases for a specific parameters combination
|
|
|
|
handle duplicate entries of different runs
|
|
method as for known device groups
|
|
tuning results common for a device/vendor type
|
|
couple of devices
|
|
|
|
|
