diff options
author | Alex Bennée <alex.bennee@linaro.org> | 2017-11-30 10:57:08 +0000 |
---|---|---|
committer | Alex Bennée <alex.bennee@linaro.org> | 2018-02-21 10:21:29 +0000 |
commit | c02e1fb80b553d47420f7492de4bc590c2461a86 (patch) | |
tree | b1409a84f1b87b1f1c2e87e2735dbdc35f8a9cb8 /fpu | |
parent | ab52f973a504f8de0c5df64631ba4caea70a7d9e (diff) |
fpu/softfloat: re-factor int/uint to float
These are considerably simpler as the lower order integers can just
use the higher order conversion function. As the decomposed fractional
part is a full 64 bit rounding and inexact handling comes from the
pack functions.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'fpu')
-rw-r--r-- | fpu/softfloat.c | 322 |
1 files changed, 163 insertions, 159 deletions
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index da0c43c0e7..4313d3a602 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -1500,6 +1500,169 @@ FLOAT_TO_UINT(64, 64) #undef FLOAT_TO_UINT +/* + * Integer to float conversions + * + * Returns the result of converting the two's complement integer `a' + * to the floating-point format. The conversion is performed according + * to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ + +static FloatParts int_to_float(int64_t a, float_status *status) +{ + FloatParts r; + if (a == 0) { + r.cls = float_class_zero; + r.sign = false; + } else if (a == (1ULL << 63)) { + r.cls = float_class_normal; + r.sign = true; + r.frac = DECOMPOSED_IMPLICIT_BIT; + r.exp = 63; + } else { + uint64_t f; + if (a < 0) { + f = -a; + r.sign = true; + } else { + f = a; + r.sign = false; + } + int shift = clz64(f) - 1; + r.cls = float_class_normal; + r.exp = (DECOMPOSED_BINARY_POINT - shift); + r.frac = f << shift; + } + + return r; +} + +float16 int64_to_float16(int64_t a, float_status *status) +{ + FloatParts pa = int_to_float(a, status); + return float16_round_pack_canonical(pa, status); +} + +float16 int32_to_float16(int32_t a, float_status *status) +{ + return int64_to_float16(a, status); +} + +float16 int16_to_float16(int16_t a, float_status *status) +{ + return int64_to_float16(a, status); +} + +float32 int64_to_float32(int64_t a, float_status *status) +{ + FloatParts pa = int_to_float(a, status); + return float32_round_pack_canonical(pa, status); +} + +float32 int32_to_float32(int32_t a, float_status *status) +{ + return int64_to_float32(a, status); +} + +float32 int16_to_float32(int16_t a, float_status *status) +{ + return int64_to_float32(a, status); +} + +float64 int64_to_float64(int64_t a, float_status *status) +{ + FloatParts pa = int_to_float(a, status); + return float64_round_pack_canonical(pa, status); +} + +float64 int32_to_float64(int32_t a, float_status *status) +{ + return int64_to_float64(a, status); +} + +float64 int16_to_float64(int16_t a, float_status *status) +{ + return int64_to_float64(a, status); +} + + +/* + * Unsigned Integer to float conversions + * + * Returns the result of converting the unsigned integer `a' to the + * floating-point format. The conversion is performed according to the + * IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ + +static FloatParts uint_to_float(uint64_t a, float_status *status) +{ + FloatParts r = { .sign = false}; + + if (a == 0) { + r.cls = float_class_zero; + } else { + int spare_bits = clz64(a) - 1; + r.cls = float_class_normal; + r.exp = DECOMPOSED_BINARY_POINT - spare_bits; + if (spare_bits < 0) { + shift64RightJamming(a, -spare_bits, &a); + r.frac = a; + } else { + r.frac = a << spare_bits; + } + } + + return r; +} + +float16 uint64_to_float16(uint64_t a, float_status *status) +{ + FloatParts pa = uint_to_float(a, status); + return float16_round_pack_canonical(pa, status); +} + +float16 uint32_to_float16(uint32_t a, float_status *status) +{ + return uint64_to_float16(a, status); +} + +float16 uint16_to_float16(uint16_t a, float_status *status) +{ + return uint64_to_float16(a, status); +} + +float32 uint64_to_float32(uint64_t a, float_status *status) +{ + FloatParts pa = uint_to_float(a, status); + return float32_round_pack_canonical(pa, status); +} + +float32 uint32_to_float32(uint32_t a, float_status *status) +{ + return uint64_to_float32(a, status); +} + +float32 uint16_to_float32(uint16_t a, float_status *status) +{ + return uint64_to_float32(a, status); +} + +float64 uint64_to_float64(uint64_t a, float_status *status) +{ + FloatParts pa = uint_to_float(a, status); + return float64_round_pack_canonical(pa, status); +} + +float64 uint32_to_float64(uint32_t a, float_status *status) +{ + return uint64_to_float64(a, status); +} + +float64 uint16_to_float64(uint16_t a, float_status *status) +{ + return uint64_to_float64(a, 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 @@ -2591,43 +2754,6 @@ static float128 normalizeRoundAndPackFloat128(flag zSign, int32_t zExp, } -/*---------------------------------------------------------------------------- -| Returns the result of converting the 32-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 int32_to_float32(int32_t a, float_status *status) -{ - flag zSign; - - if ( a == 0 ) return float32_zero; - if ( a == (int32_t) 0x80000000 ) return packFloat32( 1, 0x9E, 0 ); - zSign = ( a < 0 ); - return normalizeRoundAndPackFloat32(zSign, 0x9C, zSign ? -a : a, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 32-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 int32_to_float64(int32_t a, float_status *status) -{ - flag zSign; - uint32_t absA; - int8_t shiftCount; - uint64_t zSig; - - if ( a == 0 ) return float64_zero; - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = countLeadingZeros32( absA ) + 21; - zSig = absA; - return packFloat64( zSign, 0x432 - shiftCount, zSig<<shiftCount ); - -} /*---------------------------------------------------------------------------- | Returns the result of converting the 32-bit two's complement integer `a' @@ -2676,56 +2802,6 @@ float128 int32_to_float128(int32_t a, float_status *status) /*---------------------------------------------------------------------------- | 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_t a, float_status *status) -{ - flag zSign; - uint64_t absA; - int8_t shiftCount; - - if ( a == 0 ) return float32_zero; - 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, status); - } - -} - -/*---------------------------------------------------------------------------- -| 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_t a, float_status *status) -{ - flag zSign; - - if ( a == 0 ) return float64_zero; - if ( a == (int64_t) LIT64( 0x8000000000000000 ) ) { - return packFloat64( 1, 0x43E, 0 ); - } - zSign = ( a < 0 ); - return normalizeRoundAndPackFloat64(zSign, 0x43C, zSign ? -a : a, status); -} - -/*---------------------------------------------------------------------------- -| 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. @@ -2780,65 +2856,6 @@ float128 int64_to_float128(int64_t a, float_status *status) /*---------------------------------------------------------------------------- | Returns the result of converting the 64-bit unsigned 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 uint64_to_float32(uint64_t a, float_status *status) -{ - int shiftcount; - - if (a == 0) { - return float32_zero; - } - - /* Determine (left) shift needed to put first set bit into bit posn 23 - * (since packFloat32() expects the binary point between bits 23 and 22); - * this is the fast case for smallish numbers. - */ - shiftcount = countLeadingZeros64(a) - 40; - if (shiftcount >= 0) { - return packFloat32(0, 0x95 - shiftcount, a << shiftcount); - } - /* Otherwise we need to do a round-and-pack. roundAndPackFloat32() - * expects the binary point between bits 30 and 29, hence the + 7. - */ - shiftcount += 7; - if (shiftcount < 0) { - shift64RightJamming(a, -shiftcount, &a); - } else { - a <<= shiftcount; - } - - return roundAndPackFloat32(0, 0x9c - shiftcount, a, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 64-bit unsigned 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 uint64_to_float64(uint64_t a, float_status *status) -{ - int exp = 0x43C; - int shiftcount; - - if (a == 0) { - return float64_zero; - } - - shiftcount = countLeadingZeros64(a) - 1; - if (shiftcount < 0) { - shift64RightJamming(a, -shiftcount, &a); - } else { - a <<= shiftcount; - } - return roundAndPackFloat64(0, exp - shiftcount, a, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 64-bit unsigned integer `a' | to the quadruple-precision floating-point format. The conversion is performed | according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. *----------------------------------------------------------------------------*/ @@ -6714,19 +6731,6 @@ int float128_unordered_quiet(float128 a, float128 b, float_status *status) return 0; } -/* misc functions */ -float32 uint32_to_float32(uint32_t a, float_status *status) -{ - return int64_to_float32(a, status); -} - -float64 uint32_to_float64(uint32_t a, float_status *status) -{ - return int64_to_float64(a, status); -} - - - #define COMPARE(s, nan_exp) \ static inline int float ## s ## _compare_internal(float ## s a, float ## s b,\ int is_quiet, float_status *status) \ |