FloatingPoint8E4M3Value class

The E4M3 representation of a 8-bit floating point value as defined in FP8 Formats for Deep Learning.

Inheritance

Constructors

FloatingPoint8E4M3Value({required LogicValue sign, required LogicValue exponent, required LogicValue mantissa})
Constructor for a double precision floating point value
FloatingPoint8E4M3Value.getFloatingPointConstant(FloatingPointConstants constantFloatingPoint)
Return the FloatingPointValue representing the constant specified. Special case for 8E4M3 type.
factory
FloatingPoint8E4M3Value.ofBigInts(BigInt exponent, BigInt mantissa, {bool sign = false})
FloatingPoint8E4M3Value constructor from a set of BigInts of the binary representation
FloatingPoint8E4M3Value.ofBinaryStrings(String sign, String exponent, String mantissa)
FloatingPoint8E4M3Value constructor from string representation of individual bitfields
FloatingPoint8E4M3Value.ofDouble(double inDouble)
Numeric conversion of a FloatingPoint8E4M3Value from a host double
factory
FloatingPoint8E4M3Value.ofInts(int exponent, int mantissa, {bool sign = false})
FloatingPoint8E4M3Value constructor from a set of ints of the binary representation
FloatingPoint8E4M3Value.ofLogicValue(LogicValue val)
Construct a FloatingPoint8E4M3Value from a Logic word
factory
FloatingPoint8E4M3Value.ofSpacedBinaryString(String fp)
FloatingPoint8E4M3Value constructor from spaced string representation of individual bitfields
FloatingPoint8E4M3Value.ofString(String fp, {int radix = 2})
FloatingPoint8E4M3Value constructor from a single string representing space-separated bitfields

Properties

bias → int
Return the bias of this FloatingPointValue.
no setterinherited
constrainedExponentWidth → int
constrainedExponentWidth is the hard-coded exponent width of the sub-class of this floating-point value
no setteroverride
constrainedMantissaWidth → int
constrainedMantissaWidth is the hard-coded mantissa width of the sub-class of this floating-point value
no setteroverride
exponent → LogicValue
The exponent of the floating point: this is biased about a midpoint for positive and negative exponents
finalinherited
hashCode → int
The hash code for this object.
no setterinherited
infinity → FloatingPointValue
Abbreviation Functions for common constants Return the Infinity value for this FloatingPointValue size.
no setterinherited
isAnInfinity → bool
Inf is not representable in this format
no setteroverride
isExponentAllOnes → bool
Test if exponent is all '1's.
no setterinherited
isExponentAllZeros → bool
Test if exponent is all '0's.
no setterinherited
isMantissaAllZeroes → bool
Test if mantissa is all '0's.
no setterinherited
isNaN → bool
Return true if the represented floating point number is considered NaN or 'Not a Number'
no setteroverride
isZero → bool
Return true if the represented floating point number is zero. Note that the equality operator will treat FloatingPointConstants.positiveZero and FloatingPointConstants.negativeZero as equal.
no setterinherited
mantissa → LogicValue
The mantissa of the floating point
finalinherited
maxExponent → int
Return the maximum exponent of this FloatingPointValue.
no setterinherited
minExponent → int
Return the minimum exponent of this FloatingPointValue.
no setterinherited
nan → FloatingPointValue
Return the Negative Infinity value for this FloatingPointValue size.
no setterinherited
negativeInfinity → FloatingPointValue
Return the Negative Infinity value for this FloatingPointValue size.
no setterinherited
one → FloatingPointValue
Return the value one for this FloatingPointValue size.
no setterinherited
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
sign → LogicValue
The sign of the value: 1 means a negative value
finalinherited
value → LogicValue
The full floating point value bit storage
finalinherited
zero → FloatingPointValue
Return the Negative Infinity value for this FloatingPointValue size.
no setterinherited

Methods

abs() → FloatingPointValue
Absolute value operation for FloatingPointValue
inherited
compareTo(Object other) → int
Floating point comparison to implement Comparable<>
inherited
isNormal() → bool
Return a Logic true if this FloatingPointVa;ie contains a normal number, defined as having mantissa in the range [1,2)
inherited
isSubnormal() → bool
Return true if the represented floating point number is considered 'subnormal', including isZero.
inherited
negate() → FloatingPointValue
Negate operation for FloatingPointValue
inherited
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toDouble() → double
Override the toDouble to avoid NaN
override
toMappedSubtype() → FloatingPointValue
Converts this FloatingPointValue to a FloatingPointValue with the same sign, exponent, and mantissa using the constructor provided in subtypeConstructorMap if available, otherwise using the default constructor.
inherited
toString({bool integer = false}) → String
Return a string representation of FloatingPointValue. if integer is true, return sign, exponent, mantissa as integers. if integer is false, return sign, exponent, mantissa as ibinary strings.
inherited
ulp() → FloatingPointValue
Compute the unit in the last place for the given FloatingPointValue
inherited
withinRounding(FloatingPointValue other) → bool
Return true if the other FloatingPointValue is within a rounding error of this value.
inherited

Operators

operator *(FloatingPointValue multiplicand) → FloatingPointValue
Multiply operation for FloatingPointValue
inherited
operator +(FloatingPointValue addend) → FloatingPointValue
Addition operation for FloatingPointValue
inherited
operator -(FloatingPointValue subend) → FloatingPointValue
Subtract operation for FloatingPointValue
inherited
operator /(FloatingPointValue divisor) → FloatingPointValue
Divide operation for FloatingPointValue
inherited
operator ==(Object other) → bool
The equality operator.
inherited

Static Properties

maxValue → double
The maximum value representable by the E4M3 format
no setter
minValue → double
The minimum value representable by the E4M3 format
no setter

Constants

exponentWidth → const int
The exponent width
mantissaWidth → const int
The mantissa width