Visible to Intel only — GUID: GUID-E83BA59F-3868-47B3-B8FA-0E8915947350
Visible to Intel only — GUID: GUID-E83BA59F-3868-47B3-B8FA-0E8915947350
Floating-point Math Mode
Overview
// enums enum dnnl_fpmath_mode_t; enum dnnl::fpmath_mode; // global functions dnnl_fpmath_mode_t dnnl::convert_to_c(fpmath_mode mode); dnnl_status_t DNNL_API dnnl_get_default_fpmath_mode(dnnl_fpmath_mode_t* mode); dnnl_status_t DNNL_API dnnl_set_default_fpmath_mode(dnnl_fpmath_mode_t mode);
Detailed Documentation
Global Functions
dnnl_fpmath_mode_t dnnl::convert_to_c(fpmath_mode mode)
Converts an fpmath mode enum value from C++ API to C API type.
Parameters:
mode |
C++ API fpmath mode enum value. |
Returns:
Corresponding C API fpmath mode enum value.
dnnl_status_t DNNL_API dnnl_get_default_fpmath_mode(dnnl_fpmath_mode_t* mode)
Returns the floating-point math mode that will be used by default for all subsequently created primitives.
Parameters:
mode |
Output FP math mode. |
Returns:
dnnl_success on success and a status describing the error otherwise.
dnnl_status_t DNNL_API dnnl_set_default_fpmath_mode(dnnl_fpmath_mode_t mode)
Sets the floating-point math mode that will be used by default for all subsequently created primitives.
Parameters:
mode |
FP math mode. The possible values are: dnnl_fpmath_mode_strict, dnnl_fpmath_mode_bf16, dnnl_fpmath_mode_f16, dnnl_fpmath_mode_tf32, dnnl_fpmath_mode_any. |
Returns:
dnnl_success on success and a status describing the error otherwise.