diff options
author | Richard Henderson | 2020-11-22 01:40:57 +0100 |
---|---|---|
committer | Richard Henderson | 2021-06-03 23:09:02 +0200 |
commit | c1b6299be12d744f3baeb53f84ab5e018ec642b8 (patch) | |
tree | 1b50ee5a679617bec182b3eb7d8db1f85c99e977 /fpu | |
parent | tests/fp/fp-test: Reverse order of floatx80 precision tests (diff) | |
download | qemu-c1b6299be12d744f3baeb53f84ab5e018ec642b8.tar.gz qemu-c1b6299be12d744f3baeb53f84ab5e018ec642b8.tar.xz qemu-c1b6299be12d744f3baeb53f84ab5e018ec642b8.zip |
softfloat: Convert floatx80_add/sub to FloatParts
Since this is the first such, this includes all of the
packing and unpacking routines as well.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'fpu')
-rw-r--r-- | fpu/softfloat.c | 339 |
1 files changed, 136 insertions, 203 deletions
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index b6a50e5e95..737f5d7701 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -578,14 +578,14 @@ typedef struct { } FloatFmt; /* Expand fields based on the size of exponent and fraction */ -#define FLOAT_PARAMS_(E, F) \ +#define FLOAT_PARAMS_(E) \ .exp_size = E, \ .exp_bias = ((1 << E) - 1) >> 1, \ - .exp_max = (1 << E) - 1, \ - .frac_size = F + .exp_max = (1 << E) - 1 #define FLOAT_PARAMS(E, F) \ - FLOAT_PARAMS_(E, F), \ + FLOAT_PARAMS_(E), \ + .frac_size = F, \ .frac_shift = (-F - 1) & 63, \ .round_mask = (1ull << ((-F - 1) & 63)) - 1 @@ -614,6 +614,18 @@ static const FloatFmt float128_params = { FLOAT_PARAMS(15, 112) }; +#define FLOATX80_PARAMS(R) \ + FLOAT_PARAMS_(15), \ + .frac_size = R == 64 ? 63 : R, \ + .frac_shift = 0, \ + .round_mask = R == 64 ? -1 : (1ull << ((-R - 1) & 63)) - 1 + +static const FloatFmt floatx80_params[3] = { + [floatx80_precision_s] = { FLOATX80_PARAMS(23) }, + [floatx80_precision_d] = { FLOATX80_PARAMS(52) }, + [floatx80_precision_x] = { FLOATX80_PARAMS(64) }, +}; + /* Unpack a float to parts, but do not canonicalize. */ static void unpack_raw64(FloatParts64 *r, const FloatFmt *fmt, uint64_t raw) { @@ -648,6 +660,16 @@ static inline void float64_unpack_raw(FloatParts64 *p, float64 f) unpack_raw64(p, &float64_params, f); } +static void floatx80_unpack_raw(FloatParts128 *p, floatx80 f) +{ + *p = (FloatParts128) { + .cls = float_class_unclassified, + .sign = extract32(f.high, 15, 1), + .exp = extract32(f.high, 0, 15), + .frac_hi = f.low + }; +} + static void float128_unpack_raw(FloatParts128 *p, float128 f) { const int f_size = float128_params.frac_size - 64; @@ -1536,6 +1558,92 @@ static float128 float128_round_pack_canonical(FloatParts128 *p, return float128_pack_raw(p); } +/* Returns false if the encoding is invalid. */ +static bool floatx80_unpack_canonical(FloatParts128 *p, floatx80 f, + float_status *s) +{ + /* Ensure rounding precision is set before beginning. */ + switch (s->floatx80_rounding_precision) { + case floatx80_precision_x: + case floatx80_precision_d: + case floatx80_precision_s: + break; + default: + g_assert_not_reached(); + } + + if (unlikely(floatx80_invalid_encoding(f))) { + float_raise(float_flag_invalid, s); + return false; + } + + floatx80_unpack_raw(p, f); + + if (likely(p->exp != floatx80_params[floatx80_precision_x].exp_max)) { + parts_canonicalize(p, s, &floatx80_params[floatx80_precision_x]); + } else { + /* The explicit integer bit is ignored, after invalid checks. */ + p->frac_hi &= MAKE_64BIT_MASK(0, 63); + p->cls = (p->frac_hi == 0 ? float_class_inf + : parts_is_snan_frac(p->frac_hi, s) + ? float_class_snan : float_class_qnan); + } + return true; +} + +static floatx80 floatx80_round_pack_canonical(FloatParts128 *p, + float_status *s) +{ + const FloatFmt *fmt = &floatx80_params[s->floatx80_rounding_precision]; + uint64_t frac; + int exp; + + switch (p->cls) { + case float_class_normal: + if (s->floatx80_rounding_precision == floatx80_precision_x) { + parts_uncanon_normal(p, s, fmt); + frac = p->frac_hi; + exp = p->exp; + } else { + FloatParts64 p64; + + p64.sign = p->sign; + p64.exp = p->exp; + frac_truncjam(&p64, p); + parts_uncanon_normal(&p64, s, fmt); + frac = p64.frac; + exp = p64.exp; + } + if (exp != fmt->exp_max) { + break; + } + /* rounded to inf -- fall through to set frac correctly */ + + case float_class_inf: + /* x86 and m68k differ in the setting of the integer bit. */ + frac = floatx80_infinity_low; + exp = fmt->exp_max; + break; + + case float_class_zero: + frac = 0; + exp = 0; + break; + + case float_class_snan: + case float_class_qnan: + /* NaNs have the integer bit set. */ + frac = p->frac_hi | (1ull << 63); + exp = fmt->exp_max; + break; + + default: + g_assert_not_reached(); + } + + return packFloatx80(p->sign, exp, frac); +} + /* * Addition and subtraction */ @@ -1725,6 +1833,30 @@ float128 float128_sub(float128 a, float128 b, float_status *status) return float128_addsub(a, b, status, true); } +static floatx80 QEMU_FLATTEN +floatx80_addsub(floatx80 a, floatx80 b, float_status *status, bool subtract) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_addsub(&pa, &pb, status, subtract); + return floatx80_round_pack_canonical(pr, status); +} + +floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, false); +} + +floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, true); +} + /* * Multiplication */ @@ -5732,205 +5864,6 @@ floatx80 floatx80_round_to_int(floatx80 a, float_status *status) } /*---------------------------------------------------------------------------- -| Returns the result of adding the absolute values of the extended double- -| precision floating-point values `a' and `b'. If `zSign' is 1, the sum is -| negated before being returned. `zSign' is ignored if the result is a NaN. -| The addition is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 addFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) { - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift64ExtraRightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - zExp = aExp; - } - else if ( expDiff < 0 ) { - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift64ExtraRightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - zExp = bExp; - } - else { - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - zSig1 = 0; - zSig0 = aSig + bSig; - if ( aExp == 0 ) { - if ((aSig | bSig) & UINT64_C(0x8000000000000000) && zSig0 < aSig) { - /* At least one of the values is a pseudo-denormal, - * and there is a carry out of the result. */ - zExp = 1; - goto shiftRight1; - } - if (zSig0 == 0) { - return packFloatx80(zSign, 0, 0); - } - normalizeFloatx80Subnormal( zSig0, &zExp, &zSig0 ); - goto roundAndPack; - } - zExp = aExp; - goto shiftRight1; - } - zSig0 = aSig + bSig; - if ( (int64_t) zSig0 < 0 ) goto roundAndPack; - shiftRight1: - shift64ExtraRightJamming( zSig0, zSig1, 1, &zSig0, &zSig1 ); - zSig0 |= UINT64_C(0x8000000000000000); - ++zExp; - roundAndPack: - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the absolute values of the extended -| double-precision floating-point values `a' and `b'. If `zSign' is 1, the -| difference is negated before being returned. `zSign' is ignored if the -| result is a NaN. The subtraction is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 subFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) goto aExpBigger; - if ( expDiff < 0 ) goto bExpBigger; - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - if ( aExp == 0 ) { - aExp = 1; - bExp = 1; - } - zSig1 = 0; - if ( bSig < aSig ) goto aBigger; - if ( aSig < bSig ) goto bBigger; - return packFloatx80(status->float_rounding_mode == float_round_down, 0, 0); - bExpBigger: - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign ^ 1, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift128RightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - bBigger: - sub128( bSig, 0, aSig, zSig1, &zSig0, &zSig1 ); - zExp = bExp; - zSign ^= 1; - goto normalizeRoundAndPack; - aExpBigger: - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift128RightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - aBigger: - sub128( aSig, 0, bSig, zSig1, &zSig0, &zSig1 ); - zExp = aExp; - normalizeRoundAndPack: - return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the extended double-precision floating-point -| values `a' and `b'. The operation is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return addFloatx80Sigs(a, b, aSign, status); - } - else { - return subFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the extended double-precision floating- -| point values `a' and `b'. The operation is performed according to the -| IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return subFloatx80Sigs(a, b, aSign, status); - } - else { - return addFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- | Returns the result of multiplying the extended double-precision floating- | point values `a' and `b'. The operation is performed according to the | IEC/IEEE Standard for Binary Floating-Point Arithmetic. |