softfloat.c

說明FPU的演算法以及浮點運算式中的加減乘除

    if ( a == 0 ) return 0;
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros32( absA ) + 21;
    zSig = absA;
    return packFloat64( zSign, 0x432 - shiftCount, zSig<<shiftCount );

}

#ifdef FLOATX80

/*----------------------------------------------------------------------------
| Returns the result of converting the 32-bit two's complement integer `a'
| to the extended double-precision floating-point format.  The conversion
| is performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic.
*----------------------------------------------------------------------------*/

floatx80 int32_to_floatx80( int32 a )
{
    flag zSign;
    uint32 absA;
    int8 shiftCount;
    bits64 zSig;

    if ( a == 0 ) return packFloatx80( 0, 0, 0 );
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros32( absA ) + 32;
    zSig = absA;
    return packFloatx80( zSign, 0x403E - shiftCount, zSig<<shiftCount );

}

#endif

#ifdef FLOAT128

/*----------------------------------------------------------------------------
| Returns the result of converting the 32-bit two's complement integer `a' to
| the quadruple-precision floating-point format.  The conversion is performed
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/

float128 int32_to_float128( int32 a )
{
    flag zSign;
    uint32 absA;
    int8 shiftCount;
    bits64 zSig0;

    if ( a == 0 ) return packFloat128( 0, 0, 0, 0 );
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros32( absA ) + 17;
    zSig0 = absA;
    return packFloat128( zSign, 0x402E - shiftCount, zSig0<<shiftCount, 0 );

}

#endif

/*----------------------------------------------------------------------------
| Returns the result of converting the 64-bit two's complement integer `a'
| to the single-precision floating-point format.  The conversion is performed
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/

float32 int64_to_float32( int64 a )
{
    flag zSign;
    uint64 absA;
    int8 shiftCount;
    bits32 zSig;

    if ( a == 0 ) return 0;
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros64( absA ) - 40;
    if ( 0 <= shiftCount ) {
        return packFloat32( zSign, 0x95 - shiftCount, absA<<shiftCount );
    }
    else {
        shiftCount += 7;
        if ( shiftCount < 0 ) {
            shift64RightJamming( absA, - shiftCount, &absA );
        }
        else {
            absA <<= shiftCount;
        }
        return roundAndPackFloat32( zSign, 0x9C - shiftCount, absA );
    }

}

/*----------------------------------------------------------------------------
| Returns the result of converting the 64-bit two's complement integer `a'
| to the double-precision floating-point format.  The conversion is performed
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/

float64 int64_to_float64( int64 a )
{
    flag zSign;

    if ( a == 0 ) return 0;
    if ( a == (sbits64) LIT64( 0x8000000000000000 ) ) {
        return packFloat64( 1, 0x43E, 0 );
    }
    zSign = ( a < 0 );
    return normalizeRoundAndPackFloat64( zSign, 0x43C, zSign ? - a : a );

}

#ifdef FLOATX80

/*----------------------------------------------------------------------------
| Returns the result of converting the 64-bit two's complement integer `a'
| to the extended double-precision floating-point format.  The conversion
| is performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic.
*----------------------------------------------------------------------------*/

floatx80 int64_to_floatx80( int64 a )
{
    flag zSign;
    uint64 absA;
    int8 shiftCount;

    if ( a == 0 ) return packFloatx80( 0, 0, 0 );
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros64( absA );
    return packFloatx80( zSign, 0x403E - shiftCount, absA<<shiftCount );

}

#endif

#ifdef FLOAT128

/*----------------------------------------------------------------------------
| Returns the result of converting the 64-bit two's complement integer `a' to
| the quadruple-precision floating-point format.  The conversion is performed
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/

float128 int64_to_float128( int64 a )
{
    flag zSign;
    uint64 absA;
    int8 shiftCount;
    int32 zExp;
    bits64 zSig0, zSig1;

    if ( a == 0 ) return packFloat128( 0, 0, 0, 0 );
    zSign = ( a < 0 );
    absA = zSign ? - a : a;
    shiftCount = countLeadingZeros64( absA ) + 49;
    zExp = 0x406E - shiftCount;
    if ( 64 <= shiftCount ) {
        zSig1 = 0;
        zSig0 = absA;
        shiftCount -= 64;
    }
    else {
        zSig1 = absA;
        zSig0 = 0;
    }
    shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 );
    return packFloat128( zSign, zExp, zSig0, zSig1 );

}

#endif

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point value
| `a' to the 32-bit two's complement integer format.  The conversion is
| performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic---which means in particular that the conversion is rounded
| according to the current rounding mode.  If `a' is a NaN, the largest
| positive integer is returned.  Otherwise, if the conversion overflows, the
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/

int32 float32_to_int32( float32 a )
{
    flag aSign;
    int16 aExp, shiftCount;
    bits32 aSig;
    bits64 aSig64;

    aSig = extractFloat32Frac( a );
    aExp = extractFloat32Exp( a );
    aSign = extractFloat32Sign( a );
    if ( ( aExp == 0xFF ) && aSig ) aSign = 0;
    if ( aExp ) aSig |= 0x00800000;
    shiftCount = 0xAF - aExp;
    aSig64 = aSig;
    aSig64 <<= 32;
    if ( 0 < shiftCount ) shift64RightJamming( aSig64, shiftCount, &aSig64 );
    return roundAndPackInt32( aSign, aSig64 );

}

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point value
| `a' to the 32-bit two's complement integer format.  The conversion is
| performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic, except that the conversion is always rounded toward zero.
| If `a' is a NaN, the largest positive integer is returned.  Otherwise, if
| the conversion overflows, the largest integer with the same sign as `a' is
| returned.
*----------------------------------------------------------------------------*/

int32 float32_to_int32_round_to_zero( float32 a )
{
    flag aSign;
    int16 aExp, shiftCount;
    bits32 aSig;
    int32 z;

    aSig = extractFloat32Frac( a );
    aExp = extractFloat32Exp( a );
    aSign = extractFloat32Sign( a );
    shiftCount = aExp - 0x9E;
    if ( 0 <= shiftCount ) {
        if ( a != 0xCF000000 ) {
            float_raise( float_flag_invalid );
            if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) return 0x7FFFFFFF;
        }
        return (sbits32) 0x80000000;
    }
    else if ( aExp <= 0x7E ) {
        if ( aExp | aSig ) float_exception_flags |= float_flag_inexact;
        return 0;
    }
    aSig = ( aSig | 0x00800000 )<<8;
    z = aSig>>( - shiftCount );
    if ( (bits32) ( aSig<<( shiftCount & 31 ) ) ) {
        float_exception_flags |= float_flag_inexact;
    }
    if ( aSign ) z = - z;
    return z;

}

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point value
| `a' to the 64-bit two's complement integer format.  The conversion is
| performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic---which means in particular that the conversion is rounded
| according to the current rounding mode.  If `a' is a NaN, the largest
| positive integer is returned.  Otherwise, if the conversion overflows, the
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/

int64 float32_to_int64( float32 a )
{
    flag aSign;
    int16 aExp, shiftCount;
    bits32 aSig;
    bits64 aSig64, aSigExtra;

    aSig = extractFloat32Frac( a );
    aExp = extractFloat32Exp( a );
    aSign = extractFloat32Sign( a );
    shiftCount = 0xBE - aExp;
    if ( shiftCount < 0 ) {
        float_raise( float_flag_invalid );
        if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
            return LIT64( 0x7FFFFFFFFFFFFFFF );
        }
        return (sbits64) LIT64( 0x8000000000000000 );
    }
    if ( aExp ) aSig |= 0x00800000;
    aSig64 = aSig;
    aSig64 <<= 40;
    shift64ExtraRightJamming( aSig64, 0, shiftCount, &aSig64, &aSigExtra );
    return roundAndPackInt64( aSign, aSig64, aSigExtra );

}

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point value
| `a' to the 64-bit two's complement integer format.  The conversion is
| performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic, except that the conversion is always rounded toward zero.  If
| `a' is a NaN, the largest positive integer is returned.  Otherwise, if the
| conversion overflows, the largest integer with the same sign as `a' is
| returned.
*----------------------------------------------------------------------------*/

int64 float32_to_int64_round_to_zero( float32 a )
{
    flag aSign;
    int16 aExp, shiftCount;
    bits32 aSig;
    bits64 aSig64;
    int64 z;

    aSig = extractFloat32Frac( a );
    aExp = extractFloat32Exp( a );
    aSign = extractFloat32Sign( a );
    shiftCount = aExp - 0xBE;
    if ( 0 <= shiftCount ) {
        if ( a != 0xDF000000 ) {
            float_raise( float_flag_invalid );
            if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
                return LIT64( 0x7FFFFFFFFFFFFFFF );
            }
        }
        return (sbits64) LIT64( 0x8000000000000000 );
    }
    else if ( aExp <= 0x7E ) {
        if ( aExp | aSig ) float_exception_flags |= float_flag_inexact;
        return 0;
    }
    aSig64 = aSig | 0x00800000;
    aSig64 <<= 40;
    z = aSig64>>( - shiftCount );
    if ( (bits64) ( aSig64<<( shiftCount & 63 ) ) ) {
        float_exception_flags |= float_flag_inexact;
    }
    if ( aSign ) z = - z;
    return z;

}

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point value
| `a' to the double-precision floating-point format.  The conversion is
| performed according to the IEC/IEEE Standard for Binary Floating-Point
| Arithmetic.
*----------------------------------------------------------------------------*/

float64 float32_to_float64( float32 a )
{
    flag aSign;
    int16 aExp;
    bits32 aSig;

    aSig = extractFloat32Frac( a );
    aExp = extractFloat32Exp( a );
    aSign = extractFloat32Sign( a );
    if ( aExp == 0xFF ) {
        if ( aSig ) return commonNaNToFloat64( float32ToCommonNaN( a ) );
        return packFloat64( aSign, 0x7FF, 0 );
    }
    if ( aExp == 0 ) {
        if ( aSig == 0 ) return packFloat64( aSign, 0, 0 );
        normalizeFloat32Subnormal( aSig, &aExp, &aSig );
        --aExp;