diff options
Diffstat (limited to 'src/lib/softfloat/softfloat.c')
-rw-r--r-- | src/lib/softfloat/softfloat.c | 230 |
1 files changed, 1 insertions, 229 deletions
diff --git a/src/lib/softfloat/softfloat.c b/src/lib/softfloat/softfloat.c index 2bd5a73def6..f607feb27db 100644 --- a/src/lib/softfloat/softfloat.c +++ b/src/lib/softfloat/softfloat.c @@ -37,18 +37,12 @@ these four paragraphs for those parts of this code that are retained. | Floating-point rounding mode, extended double-precision rounding precision, | and exception flags. *----------------------------------------------------------------------------*/ -int8 float_rounding_mode = float_round_nearest_even; int8 float_exception_flags = 0; #ifdef FLOATX80 int8 floatx80_rounding_precision = 80; #endif -/*---------------------------------------------------------------------------- -| Primitive arithmetic functions, including multi-word arithmetic, and -| division and square root approximations. (Can be specialized to target if -| desired.) -*----------------------------------------------------------------------------*/ -#include "softfloat-macros" +int8 float_rounding_mode = float_round_nearest_even; /*---------------------------------------------------------------------------- | Functions and definitions to determine: (1) whether tininess for underflow @@ -489,42 +483,6 @@ static float64 #ifdef FLOATX80 /*---------------------------------------------------------------------------- -| Returns the fraction bits of the extended double-precision floating-point -| value `a'. -*----------------------------------------------------------------------------*/ - -INLINE bits64 extractFloatx80Frac( floatx80 a ) -{ - - return a.low; - -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the extended double-precision floating-point -| value `a'. -*----------------------------------------------------------------------------*/ - -INLINE int32 extractFloatx80Exp( floatx80 a ) -{ - - return a.high & 0x7FFF; - -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the extended double-precision floating-point value -| `a'. -*----------------------------------------------------------------------------*/ - -INLINE flag extractFloatx80Sign( floatx80 a ) -{ - - return a.high>>15; - -} - -/*---------------------------------------------------------------------------- | Normalizes the subnormal extended double-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 @@ -543,21 +501,6 @@ static void } /*---------------------------------------------------------------------------- -| Packs the sign `zSign', exponent `zExp', and significand `zSig' into an -| extended double-precision floating-point value, returning the result. -*----------------------------------------------------------------------------*/ - -INLINE floatx80 packFloatx80( flag zSign, int32 zExp, bits64 zSig ) -{ - floatx80 z; - - z.low = zSig; - z.high = ( ( (bits16) zSign )<<15 ) + zExp; - return z; - -} - -/*---------------------------------------------------------------------------- | Takes an abstract floating-point value having sign `zSign', exponent `zExp', | and extended significand formed by the concatenation of `zSig0' and `zSig1', | and returns the proper extended double-precision floating-point value @@ -861,177 +804,6 @@ static void } -/*---------------------------------------------------------------------------- -| Packs the sign `zSign', the exponent `zExp', and the significand formed -| by the concatenation of `zSig0' and `zSig1' into a quadruple-precision -| floating-point value, returning the result. After being shifted into the -| proper positions, the three fields `zSign', `zExp', and `zSig0' are simply -| added together to form the most significant 32 bits of the result. This -| means that any integer portion of `zSig0' will be added into the exponent. -| Since a properly normalized significand will have an integer portion equal -| to 1, the `zExp' input should be 1 less than the desired result exponent -| whenever `zSig0' and `zSig1' concatenated form a complete, normalized -| significand. -*----------------------------------------------------------------------------*/ - -INLINE float128 - packFloat128( flag zSign, int32 zExp, bits64 zSig0, bits64 zSig1 ) -{ - float128 z; - - z.low = zSig1; - z.high = ( ( (bits64) zSign )<<63 ) + ( ( (bits64) zExp )<<48 ) + zSig0; - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and extended significand formed by the concatenation of `zSig0', `zSig1', -| and `zSig2', and returns the proper quadruple-precision floating-point value -| corresponding to the abstract input. Ordinarily, the abstract value is -| simply rounded and packed into the quadruple-precision format, with the -| inexact exception raised if the abstract input cannot be represented -| exactly. However, if the abstract value is too large, the overflow and -| inexact exceptions are raised and an infinity or maximal finite value is -| returned. If the abstract value is too small, the input value is rounded to -| a subnormal number, and the underflow and inexact exceptions are raised if -| the abstract input cannot be represented exactly as a subnormal quadruple- -| precision floating-point number. -| The input significand must be normalized or smaller. If the input -| significand is not normalized, `zExp' must be 0; in that case, the result -| returned is a subnormal number, and it must not require rounding. In the -| usual case that the input significand is normalized, `zExp' must be 1 less -| than the ``true'' floating-point exponent. The handling of underflow and -| overflow follows the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float128 - roundAndPackFloat128( - flag zSign, int32 zExp, bits64 zSig0, bits64 zSig1, bits64 zSig2 ) -{ - int8 roundingMode; - flag roundNearestEven, increment, isTiny; - - roundingMode = float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - increment = ( (sbits64) zSig2 < 0 ); - if ( ! roundNearestEven ) { - if ( roundingMode == float_round_to_zero ) { - increment = 0; - } - else { - if ( zSign ) { - increment = ( roundingMode == float_round_down ) && zSig2; - } - else { - increment = ( roundingMode == float_round_up ) && zSig2; - } - } - } - if ( 0x7FFD <= (bits32) zExp ) { - if ( ( 0x7FFD < zExp ) - || ( ( zExp == 0x7FFD ) - && eq128( - LIT64( 0x0001FFFFFFFFFFFF ), - LIT64( 0xFFFFFFFFFFFFFFFF ), - zSig0, - zSig1 - ) - && increment - ) - ) { - float_raise( float_flag_overflow | float_flag_inexact ); - if ( ( roundingMode == float_round_to_zero ) - || ( zSign && ( roundingMode == float_round_up ) ) - || ( ! zSign && ( roundingMode == float_round_down ) ) - ) { - return - packFloat128( - zSign, - 0x7FFE, - LIT64( 0x0000FFFFFFFFFFFF ), - LIT64( 0xFFFFFFFFFFFFFFFF ) - ); - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( zExp < 0 ) { - isTiny = - ( float_detect_tininess == float_tininess_before_rounding ) - || ( zExp < -1 ) - || ! increment - || lt128( - zSig0, - zSig1, - LIT64( 0x0001FFFFFFFFFFFF ), - LIT64( 0xFFFFFFFFFFFFFFFF ) - ); - shift128ExtraRightJamming( - zSig0, zSig1, zSig2, - zExp, &zSig0, &zSig1, &zSig2 ); - zExp = 0; - if ( isTiny && zSig2 ) float_raise( float_flag_underflow ); - if ( roundNearestEven ) { - increment = ( (sbits64) zSig2 < 0 ); - } - else { - if ( zSign ) { - increment = ( roundingMode == float_round_down ) && zSig2; - } - else { - increment = ( roundingMode == float_round_up ) && zSig2; - } - } - } - } - if ( zSig2 ) float_exception_flags |= float_flag_inexact; - if ( increment ) { - add128( zSig0, zSig1, 0, 1, &zSig0, &zSig1 ); - zSig1 &= ~ ( ( zSig2 + zSig2 == 0 ) & roundNearestEven ); - } - else { - if ( ( zSig0 | zSig1 ) == 0 ) zExp = 0; - } - return packFloat128( zSign, zExp, zSig0, zSig1 ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand formed by the concatenation of `zSig0' and `zSig1', and -| returns the proper quadruple-precision floating-point value corresponding -| to the abstract input. This routine is just like `roundAndPackFloat128' -| except that the input significand has fewer bits and does not have to be -| normalized. In all cases, `zExp' must be 1 less than the ``true'' floating- -| point exponent. -*----------------------------------------------------------------------------*/ - -static float128 - normalizeRoundAndPackFloat128( - flag zSign, int32 zExp, bits64 zSig0, bits64 zSig1 ) -{ - int8 shiftCount; - bits64 zSig2; - - if ( zSig0 == 0 ) { - zSig0 = zSig1; - zSig1 = 0; - zExp -= 64; - } - shiftCount = countLeadingZeros64( zSig0 ) - 15; - if ( 0 <= shiftCount ) { - zSig2 = 0; - shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 ); - } - else { - shift128ExtraRightJamming( - zSig0, zSig1, 0, - shiftCount, &zSig0, &zSig1, &zSig2 ); - } - zExp -= shiftCount; - return roundAndPackFloat128( zSign, zExp, zSig0, zSig1, zSig2 ); - -} - #endif /*---------------------------------------------------------------------------- |