float8_e8m0
The APIs described in this section are reserved and may be changed or deprecated in the future. You are not advised to use these APIs.
API Definition |
Description |
|---|---|
FromBits() |
Returns the tag used to construct a Float8E8M0 object from a bit pattern. |
Float8E8M0() |
Default constructor of struct Float8E8M0, initialized to zero. |
Float8E8M0(uint8_t bits, FromBitsTag) |
Constructor of struct Float8E8M0, which constructs an object from the original bit pattern. |
Float8E8M0(float v) |
Constructor of struct Float8E8M0, which constructs an object from a float value. |
operator float() |
Converts Float8E8M0 to float. |
operator double() |
Converts Float8E8M0 to double. |
Epsilon() |
Returns the machine epsilon value of the Float8E8M0 data type. |
Highest() |
Returns the maximum value of the Float8E8M0 data type. |
Lowest() |
Returns the minimum positive value of the Float8E8M0 data type (unsigned format). |
MinPositive() |
Returns the minimum positive value of the Float8E8M0 data type. |
IsZero() |
Checks whether the current Float8E8M0 value is zero. |
IsNaN() |
Checks whether the current Float8E8M0 value is NaN. |
IsInf() |
Checks whether the current Float8E8M0 value is infinite. |
GetExponent() |
Obtains the unbiased exponent of the current Float8E8M0 value. |
isinf(const Float8E8M0 &a) |
Checks whether the given Float8E8M0 value a is infinite. |
isnan(const Float8E8M0 &a) |
Checks whether the given Float8E8M0 value a is NaN. |
isfinite(const Float8E8M0 &a) |
Checks whether the given Float8E8M0 value a is finite. |
min() |
Returns the minimum positive value of the Float8E8M0 data type. |
lowest() |
Returns the minimum positive value of the Float8E8M0 data type (unsigned format). |
max() |
Returns the maximum value of the Float8E8M0 data type. |
epsilon() |
Returns the machine epsilon value of the Float8E8M0 data type. |
round_error() |
Returns the maximum rounding error of the Float8E8M0 data type. |
infinity() |
Returns the maximum value of the Float8E8M0 data type (in the case of infinity, the maximum value is returned). |
quiet_NaN() |
Returns the quiet NaN value of the Float8E8M0 data type. |
signaling_NaN() |
Returns the signaling NaN value of the Float8E8M0 data type. |
denorm_min() |
Returns the minimum positive denormalized value of the Float8E8M0 data type. |