-
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 |
|---|---|---|
| .. | ||
| contrib/mlir | ||
| ngraph | ||
| resource | ||
| tools | ||
| CMakeLists.txt |