diff options
Diffstat (limited to 'fpu/softfloat.c')
| -rw-r--r-- | fpu/softfloat.c | 130 |
1 files changed, 81 insertions, 49 deletions
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 17842f43da..30b07e9b44 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -67,6 +67,33 @@ void set_floatx80_rounding_precision(int val STATUS_PARAM) #endif /*---------------------------------------------------------------------------- +| Returns the fraction bits of the half-precision floating-point value `a'. +*----------------------------------------------------------------------------*/ + +INLINE uint32_t extractFloat16Frac(float16 a) +{ + return float16_val(a) & 0x3ff; +} + +/*---------------------------------------------------------------------------- +| Returns the exponent bits of the half-precision floating-point value `a'. +*----------------------------------------------------------------------------*/ + +INLINE int16 extractFloat16Exp(float16 a) +{ + return (float16_val(a) >> 10) & 0x1f; +} + +/*---------------------------------------------------------------------------- +| Returns the sign bit of the single-precision floating-point value `a'. +*----------------------------------------------------------------------------*/ + +INLINE flag extractFloat16Sign(float16 a) +{ + return float16_val(a)>>15; +} + +/*---------------------------------------------------------------------------- | 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 @@ -1534,7 +1561,7 @@ float64 float32_to_float64( float32 a STATUS_PARAM ) aExp = extractFloat32Exp( a ); aSign = extractFloat32Sign( a ); if ( aExp == 0xFF ) { - if ( aSig ) return commonNaNToFloat64( float32ToCommonNaN( a STATUS_VAR )); + if ( aSig ) return commonNaNToFloat64( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloat64( aSign, 0x7FF, 0 ); } if ( aExp == 0 ) { @@ -1566,7 +1593,7 @@ floatx80 float32_to_floatx80( float32 a STATUS_PARAM ) aExp = extractFloat32Exp( a ); aSign = extractFloat32Sign( a ); if ( aExp == 0xFF ) { - if ( aSig ) return commonNaNToFloatx80( float32ToCommonNaN( a STATUS_VAR ) ); + if ( aSig ) return commonNaNToFloatx80( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); } if ( aExp == 0 ) { @@ -1600,7 +1627,7 @@ float128 float32_to_float128( float32 a STATUS_PARAM ) aExp = extractFloat32Exp( a ); aSign = extractFloat32Sign( a ); if ( aExp == 0xFF ) { - if ( aSig ) return commonNaNToFloat128( float32ToCommonNaN( a STATUS_VAR ) ); + if ( aSig ) return commonNaNToFloat128( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloat128( aSign, 0x7FFF, 0, 0 ); } if ( aExp == 0 ) { @@ -2172,21 +2199,21 @@ float32 float32_sqrt( float32 a STATUS_PARAM ) static const float64 float32_exp2_coefficients[15] = { - make_float64( 0x3ff0000000000000ll ), /* 1 */ - make_float64( 0x3fe0000000000000ll ), /* 2 */ - make_float64( 0x3fc5555555555555ll ), /* 3 */ - make_float64( 0x3fa5555555555555ll ), /* 4 */ - make_float64( 0x3f81111111111111ll ), /* 5 */ - make_float64( 0x3f56c16c16c16c17ll ), /* 6 */ - make_float64( 0x3f2a01a01a01a01all ), /* 7 */ - make_float64( 0x3efa01a01a01a01all ), /* 8 */ - make_float64( 0x3ec71de3a556c734ll ), /* 9 */ - make_float64( 0x3e927e4fb7789f5cll ), /* 10 */ - make_float64( 0x3e5ae64567f544e4ll ), /* 11 */ - make_float64( 0x3e21eed8eff8d898ll ), /* 12 */ - make_float64( 0x3de6124613a86d09ll ), /* 13 */ - make_float64( 0x3da93974a8c07c9dll ), /* 14 */ - make_float64( 0x3d6ae7f3e733b81fll ), /* 15 */ + const_float64( 0x3ff0000000000000ll ), /* 1 */ + const_float64( 0x3fe0000000000000ll ), /* 2 */ + const_float64( 0x3fc5555555555555ll ), /* 3 */ + const_float64( 0x3fa5555555555555ll ), /* 4 */ + const_float64( 0x3f81111111111111ll ), /* 5 */ + const_float64( 0x3f56c16c16c16c17ll ), /* 6 */ + const_float64( 0x3f2a01a01a01a01all ), /* 7 */ + const_float64( 0x3efa01a01a01a01all ), /* 8 */ + const_float64( 0x3ec71de3a556c734ll ), /* 9 */ + const_float64( 0x3e927e4fb7789f5cll ), /* 10 */ + const_float64( 0x3e5ae64567f544e4ll ), /* 11 */ + const_float64( 0x3e21eed8eff8d898ll ), /* 12 */ + const_float64( 0x3de6124613a86d09ll ), /* 13 */ + const_float64( 0x3da93974a8c07c9dll ), /* 14 */ + const_float64( 0x3d6ae7f3e733b81fll ), /* 15 */ }; float32 float32_exp2( float32 a STATUS_PARAM ) @@ -2689,7 +2716,7 @@ float32 float64_to_float32( float64 a STATUS_PARAM ) aExp = extractFloat64Exp( a ); aSign = extractFloat64Sign( a ); if ( aExp == 0x7FF ) { - if ( aSig ) return commonNaNToFloat32( float64ToCommonNaN( a STATUS_VAR ) ); + if ( aSig ) return commonNaNToFloat32( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloat32( aSign, 0xFF, 0 ); } shift64RightJamming( aSig, 22, &aSig ); @@ -2713,29 +2740,28 @@ float32 float64_to_float32( float64 a STATUS_PARAM ) | than the desired result exponent whenever `zSig' is a complete, normalized | significand. *----------------------------------------------------------------------------*/ -static bits16 packFloat16(flag zSign, int16 zExp, bits16 zSig) +static float16 packFloat16(flag zSign, int16 zExp, bits16 zSig) { - return (((bits32)zSign) << 15) + (((bits32)zExp) << 10) + zSig; + return make_float16( + (((bits32)zSign) << 15) + (((bits32)zExp) << 10) + zSig); } /* Half precision floats come in two formats: standard IEEE and "ARM" format. The latter gains extra exponent range by omitting the NaN/Inf encodings. */ - -float32 float16_to_float32( bits16 a, flag ieee STATUS_PARAM ) + +float32 float16_to_float32(float16 a, flag ieee STATUS_PARAM) { flag aSign; int16 aExp; bits32 aSig; - aSign = a >> 15; - aExp = (a >> 10) & 0x1f; - aSig = a & 0x3ff; + aSign = extractFloat16Sign(a); + aExp = extractFloat16Exp(a); + aSig = extractFloat16Frac(a); if (aExp == 0x1f && ieee) { if (aSig) { - /* Make sure correct exceptions are raised. */ - float32ToCommonNaN(a STATUS_VAR); - aSig |= 0x200; + return commonNaNToFloat32(float16ToCommonNaN(a STATUS_VAR) STATUS_VAR); } return packFloat32(aSign, 0xff, aSig << 13); } @@ -2753,7 +2779,7 @@ float32 float16_to_float32( bits16 a, flag ieee STATUS_PARAM ) return packFloat32( aSign, aExp + 0x70, aSig << 13); } -bits16 float32_to_float16( float32 a, flag ieee STATUS_PARAM) +float16 float32_to_float16(float32 a, flag ieee STATUS_PARAM) { flag aSign; int16 aExp; @@ -2768,24 +2794,30 @@ bits16 float32_to_float16( float32 a, flag ieee STATUS_PARAM) aSign = extractFloat32Sign( a ); if ( aExp == 0xFF ) { if (aSig) { - /* Make sure correct exceptions are raised. */ - float32ToCommonNaN(a STATUS_VAR); - aSig |= 0x00400000; + /* Input is a NaN */ + float16 r = commonNaNToFloat16( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); + if (!ieee) { + return packFloat16(aSign, 0, 0); + } + return r; + } + /* Infinity */ + if (!ieee) { + float_raise(float_flag_invalid STATUS_VAR); + return packFloat16(aSign, 0x1f, 0x3ff); } - return packFloat16(aSign, 0x1f, aSig >> 13); + return packFloat16(aSign, 0x1f, 0); } - if (aExp == 0 && aSign == 0) { + if (aExp == 0 && aSig == 0) { return packFloat16(aSign, 0, 0); } /* Decimal point between bits 22 and 23. */ aSig |= 0x00800000; aExp -= 0x7f; if (aExp < -14) { - mask = 0x007fffff; - if (aExp < -24) { - aExp = -25; - } else { - mask >>= 24 + aExp; + mask = 0x00ffffff; + if (aExp >= -24) { + mask >>= 25 + aExp; } } else { mask = 0x00001fff; @@ -2827,7 +2859,7 @@ bits16 float32_to_float16( float32 a, flag ieee STATUS_PARAM) } } else { if (aExp > 16) { - float_raise( float_flag_overflow | float_flag_inexact STATUS_VAR); + float_raise(float_flag_invalid | float_flag_inexact STATUS_VAR); return packFloat16(aSign, 0x1f, 0x3ff); } } @@ -2861,7 +2893,7 @@ floatx80 float64_to_floatx80( float64 a STATUS_PARAM ) aExp = extractFloat64Exp( a ); aSign = extractFloat64Sign( a ); if ( aExp == 0x7FF ) { - if ( aSig ) return commonNaNToFloatx80( float64ToCommonNaN( a STATUS_VAR ) ); + if ( aSig ) return commonNaNToFloatx80( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); } if ( aExp == 0 ) { @@ -2896,7 +2928,7 @@ float128 float64_to_float128( float64 a STATUS_PARAM ) aExp = extractFloat64Exp( a ); aSign = extractFloat64Sign( a ); if ( aExp == 0x7FF ) { - if ( aSig ) return commonNaNToFloat128( float64ToCommonNaN( a STATUS_VAR ) ); + if ( aSig ) return commonNaNToFloat128( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); return packFloat128( aSign, 0x7FFF, 0, 0 ); } if ( aExp == 0 ) { @@ -3843,7 +3875,7 @@ float32 floatx80_to_float32( floatx80 a STATUS_PARAM ) aSign = extractFloatx80Sign( a ); if ( aExp == 0x7FFF ) { if ( (bits64) ( aSig<<1 ) ) { - return commonNaNToFloat32( floatx80ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloat32( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } return packFloat32( aSign, 0xFF, 0 ); } @@ -3871,7 +3903,7 @@ float64 floatx80_to_float64( floatx80 a STATUS_PARAM ) aSign = extractFloatx80Sign( a ); if ( aExp == 0x7FFF ) { if ( (bits64) ( aSig<<1 ) ) { - return commonNaNToFloat64( floatx80ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloat64( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } return packFloat64( aSign, 0x7FF, 0 ); } @@ -3900,7 +3932,7 @@ float128 floatx80_to_float128( floatx80 a STATUS_PARAM ) aExp = extractFloatx80Exp( a ); aSign = extractFloatx80Sign( a ); if ( ( aExp == 0x7FFF ) && (bits64) ( aSig<<1 ) ) { - return commonNaNToFloat128( floatx80ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloat128( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } shift128Right( aSig<<1, 0, 16, &zSig0, &zSig1 ); return packFloat128( aSign, aExp, zSig0, zSig1 ); @@ -4863,7 +4895,7 @@ float32 float128_to_float32( float128 a STATUS_PARAM ) aSign = extractFloat128Sign( a ); if ( aExp == 0x7FFF ) { if ( aSig0 | aSig1 ) { - return commonNaNToFloat32( float128ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloat32( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } return packFloat32( aSign, 0xFF, 0 ); } @@ -4897,7 +4929,7 @@ float64 float128_to_float64( float128 a STATUS_PARAM ) aSign = extractFloat128Sign( a ); if ( aExp == 0x7FFF ) { if ( aSig0 | aSig1 ) { - return commonNaNToFloat64( float128ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloat64( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } return packFloat64( aSign, 0x7FF, 0 ); } @@ -4932,7 +4964,7 @@ floatx80 float128_to_floatx80( float128 a STATUS_PARAM ) aSign = extractFloat128Sign( a ); if ( aExp == 0x7FFF ) { if ( aSig0 | aSig1 ) { - return commonNaNToFloatx80( float128ToCommonNaN( a STATUS_VAR ) ); + return commonNaNToFloatx80( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR ); } return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); } |