Online Help

The following constants are known to evalhf:

evalhf(Digits) returns the approximate number of digits of the hardware floating-point system in use, regardless of the actual setting of Digits. This constant takes into account the precision returned by the standard mathematical functions.

Inside evalhf, true has the value 1.0 and false has the value 0.0.

The following constants are taken from the ANSI-C definition of floating-point parameters of an IEEE-standard floating-point system.

FLT_RADIX: The base (or radix) of the floating-point number system.

DBL_MANT_DIG: The number of significant base digits.

DBL_DIG: The (approximate) equivalent number of significant decimal digits.

DBL_EPSILON: The smallest positive x such that $1.0+x\ne 1.0$

DBL_MIN_EXP: Minimum normalized exponent

DBL_MIN: Minimum normalized positive number

DBL_MIN_10_EXP: Minimum exponent of a representable power of 10

DBL_MAX_EXP: Maximum exponent

DBL_MAX: Maximum number

DBL_MAX_10_EXP: Maximum exponent of a representable power of 10

LNMAXFLOAT: A number slightly smaller than the largest number x such that evalhf(exp(x)) and evalhf(exp(-x)) both successfully compute, and such that the results of those computations can continue to be used in evalhf. On most machines, this value is set as evalhf(-ln(DBL_MIN)) truncated to 6 decimal places.