-
Nishant Patel authored
* test bfloat16 with CPU maxpool * Move test to cpu_test * convert result from bfloat16 to float * Modify result op to support bfloat16 * Correct comment * Add a simple convolution test case * initialize floats with float literals * Guard bf16 tests with MKLDNN_VERSION_MAJOR >= 1
7ea34fc2
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| autodiff | Loading commit data... | |
| CMakeLists.txt | ||
| all_close.hpp | ||
| all_close_f.cpp | ||
| all_close_f.hpp | ||
| float_util.cpp | ||
| float_util.hpp | ||
| known_element_types.hpp | ||
| matcher.hpp | ||
| ndarray.hpp | ||
| random.hpp | ||
| test_case.cpp | ||
| test_case.hpp | ||
| test_control.cpp | ||
| test_control.hpp | ||
| test_tools.cpp | ||
| test_tools.hpp | ||
| type_prop.hpp |