diff options
-rw-r--r-- | fpu/softfloat.c | 336 |
1 files changed, 42 insertions, 294 deletions
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index acaab6a..5a2a872 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -2829,6 +2829,28 @@ static int64_t float128_to_int64_scalbn(float128 a, FloatRoundMode rmode, return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); } +static int32_t floatx80_to_int32_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); +} + +static int64_t floatx80_to_int64_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); +} + int8_t float16_to_int8(float16 a, float_status *s) { return float16_to_int8_scalbn(a, s->float_rounding_mode, 0, s); @@ -2889,6 +2911,16 @@ int64_t float128_to_int64(float128 a, float_status *s) return float128_to_int64_scalbn(a, s->float_rounding_mode, 0, s); } +int32_t floatx80_to_int32(floatx80 a, float_status *s) +{ + return floatx80_to_int32_scalbn(a, s->float_rounding_mode, 0, s); +} + +int64_t floatx80_to_int64(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, s->float_rounding_mode, 0, s); +} + int16_t float16_to_int16_round_to_zero(float16 a, float_status *s) { return float16_to_int16_scalbn(a, float_round_to_zero, 0, s); @@ -2944,6 +2976,16 @@ int64_t float128_to_int64_round_to_zero(float128 a, float_status *s) return float128_to_int64_scalbn(a, float_round_to_zero, 0, s); } +int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *s) +{ + return floatx80_to_int32_scalbn(a, float_round_to_zero, 0, s); +} + +int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, float_round_to_zero, 0, s); +} + int16_t bfloat16_to_int16(bfloat16 a, float_status *s) { return bfloat16_to_int16_scalbn(a, s->float_rounding_mode, 0, s); @@ -4161,127 +4203,6 @@ bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status) } /*---------------------------------------------------------------------------- -| Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 -| and 7, and returns the properly rounded 32-bit integer corresponding to the -| input. If `zSign' is 1, the input is negated before being converted to an -| integer. Bit 63 of `absZ' must be zero. Ordinarily, the fixed-point input -| is simply rounded to an integer, with the inexact exception raised if the -| input cannot be represented exactly as an integer. However, if the fixed- -| point input is too large, the invalid exception is raised and the largest -| positive or negative integer is returned. -*----------------------------------------------------------------------------*/ - -static int32_t roundAndPackInt32(bool zSign, uint64_t absZ, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven; - int8_t roundIncrement, roundBits; - int32_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x40; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x7f; - break; - case float_round_down: - roundIncrement = zSign ? 0x7f : 0; - break; - case float_round_to_odd: - roundIncrement = absZ & 0x80 ? 0 : 0x7f; - break; - default: - abort(); - } - roundBits = absZ & 0x7F; - absZ = ( absZ + roundIncrement )>>7; - if (!(roundBits ^ 0x40) && roundNearestEven) { - absZ &= ~1; - } - z = absZ; - if ( zSign ) z = - z; - if ( ( absZ>>32 ) || ( z && ( ( z < 0 ) ^ zSign ) ) ) { - float_raise(float_flag_invalid, status); - return zSign ? INT32_MIN : INT32_MAX; - } - if (roundBits) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and -| `absZ1', with binary point between bits 63 and 64 (between the input words), -| and returns the properly rounded 64-bit integer corresponding to the input. -| If `zSign' is 1, the input is negated before being converted to an integer. -| Ordinarily, the fixed-point input is simply rounded to an integer, with -| the inexact exception raised if the input cannot be represented exactly as -| an integer. However, if the fixed-point input is too large, the invalid -| exception is raised and the largest positive or negative integer is -| returned. -*----------------------------------------------------------------------------*/ - -static int64_t roundAndPackInt64(bool zSign, uint64_t absZ0, uint64_t absZ1, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment; - int64_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t) absZ1 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && absZ1; - break; - case float_round_down: - increment = zSign && absZ1; - break; - case float_round_to_odd: - increment = !(absZ0 & 1) && absZ1; - break; - default: - abort(); - } - if ( increment ) { - ++absZ0; - if ( absZ0 == 0 ) goto overflow; - if (!(absZ1 << 1) && roundNearestEven) { - absZ0 &= ~1; - } - } - z = absZ0; - if ( zSign ) z = - z; - if ( z && ( ( z < 0 ) ^ zSign ) ) { - overflow: - float_raise(float_flag_invalid, status); - return zSign ? INT64_MIN : INT64_MAX; - } - if (absZ1) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- | Normalizes the subnormal single-precision floating-point value represented | by the denormalized significand `aSig'. The normalized exponent and | significand are stored at the locations pointed to by `zExpPtr' and @@ -5487,179 +5408,6 @@ float64 float64_log2(float64 a, float_status *status) } /*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-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_t floatx80_to_int32(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - shiftCount = 0x4037 - aExp; - if ( shiftCount <= 0 ) shiftCount = 1; - shift64RightJamming( aSig, shiftCount, &aSig ); - return roundAndPackInt32(aSign, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-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_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, savedASig; - int32_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( 0x401E < aExp ) { - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - goto invalid; - } - else if ( aExp < 0x3FFF ) { - if (aExp || aSig) { - float_raise(float_flag_inexact, status); - } - return 0; - } - shiftCount = 0x403E - aExp; - savedASig = aSig; - aSig >>= shiftCount; - z = aSig; - if ( aSign ) z = - z; - if ( ( z < 0 ) ^ aSign ) { - invalid: - float_raise(float_flag_invalid, status); - return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF; - } - if ( ( aSig<<shiftCount ) != savedASig ) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-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_t floatx80_to_int64(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, aSigExtra; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = 0x403E - aExp; - if ( shiftCount <= 0 ) { - if ( shiftCount ) { - float_raise(float_flag_invalid, status); - if (!aSign || floatx80_is_any_nan(a)) { - return INT64_MAX; - } - return INT64_MIN; - } - aSigExtra = 0; - } - else { - shift64ExtraRightJamming( aSig, 0, shiftCount, &aSig, &aSigExtra ); - } - return roundAndPackInt64(aSign, aSig, aSigExtra, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-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_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - int64_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = aExp - 0x403E; - if ( 0 <= shiftCount ) { - aSig &= UINT64_C(0x7FFFFFFFFFFFFFFF); - if ( ( a.high != 0xC03E ) || aSig ) { - float_raise(float_flag_invalid, status); - if ( ! aSign || ( ( aExp == 0x7FFF ) && aSig ) ) { - return INT64_MAX; - } - } - return INT64_MIN; - } - else if ( aExp < 0x3FFF ) { - if (aExp | aSig) { - float_raise(float_flag_inexact, status); - } - return 0; - } - z = aSig>>( - shiftCount ); - if ( (uint64_t) ( aSig<<( shiftCount & 63 ) ) ) { - float_raise(float_flag_inexact, status); - } - if ( aSign ) z = - z; - return z; - -} - -/*---------------------------------------------------------------------------- | Rounds the extended double-precision floating-point value `a' | to the precision provided by floatx80_rounding_precision and returns the | result as an extended double-precision floating-point value. |