haraldwolff/qemu-patch-raspberry4
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

softfloat: Convert floatx80_sqrt to FloatParts

Browse source 
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2020-11-21 18:27:24 -08:00
parent 38db99e282
commit aa5e19ccbd
1 changed files with 11 additions and 71 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

82
fpu/softfloat.c
View file

@ -3881,6 +3881,17 @@ float128 QEMU_FLATTEN float128_sqrt(float128 a, float_status *status)
return float128_round_pack_canonical(&p, status);
}
floatx80 floatx80_sqrt(floatx80 a, float_status *s)
{
FloatParts128 p;
if (!floatx80_unpack_canonical(&p, a, s)) {
return floatx80_default_nan(s);
}
parts_sqrt(&p, s, &floatx80_params[s->floatx80_rounding_precision]);
return floatx80_round_pack_canonical(&p, s);
}
/*----------------------------------------------------------------------------
| The pattern for a default generated NaN.
*----------------------------------------------------------------------------*/
@ -6044,77 +6055,6 @@ floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status)
return floatx80_modrem(a, b, true, &quotient, status);
}
/*----------------------------------------------------------------------------
| Returns the square root of the extended double-precision floating-point
| value `a'. The operation is performed according to the IEC/IEEE Standard
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
floatx80 floatx80_sqrt(floatx80 a, float_status *status)
{
bool aSign;
int32_t aExp, zExp;
uint64_t aSig0, aSig1, zSig0, zSig1, doubleZSig0;
uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3;
if (floatx80_invalid_encoding(a)) {
float_raise(float_flag_invalid, status);
return floatx80_default_nan(status);
}
aSig0 = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( aExp == 0x7FFF ) {
if ((uint64_t)(aSig0 << 1)) {
return propagateFloatx80NaN(a, a, status);
}
if ( ! aSign ) return a;
goto invalid;
}
if ( aSign ) {
if ( ( aExp | aSig0 ) == 0 ) return a;
invalid:
float_raise(float_flag_invalid, status);
return floatx80_default_nan(status);
}
if ( aExp == 0 ) {
if ( aSig0 == 0 ) return packFloatx80( 0, 0, 0 );
normalizeFloatx80Subnormal( aSig0, &aExp, &aSig0 );
}
zExp = ( ( aExp - 0x3FFF )>>1 ) + 0x3FFF;
zSig0 = estimateSqrt32( aExp, aSig0>>32 );
shift128Right( aSig0, 0, 2 + ( aExp & 1 ), &aSig0, &aSig1 );
zSig0 = estimateDiv128To64( aSig0, aSig1, zSig0<<32 ) + ( zSig0<<30 );
doubleZSig0 = zSig0<<1;
mul64To128( zSig0, zSig0, &term0, &term1 );
sub128( aSig0, aSig1, term0, term1, &rem0, &rem1 );
while ( (int64_t) rem0 < 0 ) {
--zSig0;
doubleZSig0 -= 2;
add128( rem0, rem1, zSig0>>63, doubleZSig0 | 1, &rem0, &rem1 );
}
zSig1 = estimateDiv128To64( rem1, 0, doubleZSig0 );
if ( ( zSig1 & UINT64_C(0x3FFFFFFFFFFFFFFF) ) <= 5 ) {
if ( zSig1 == 0 ) zSig1 = 1;
mul64To128( doubleZSig0, zSig1, &term1, &term2 );
sub128( rem1, 0, term1, term2, &rem1, &rem2 );
mul64To128( zSig1, zSig1, &term2, &term3 );
sub192( rem1, rem2, 0, 0, term2, term3, &rem1, &rem2, &rem3 );
while ( (int64_t) rem1 < 0 ) {
--zSig1;
shortShift128Left( 0, zSig1, 1, &term2, &term3 );
term3 |= 1;
term2 |= doubleZSig0;
add192( rem1, rem2, rem3, 0, term2, term3, &rem1, &rem2, &rem3 );
}
zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 );
}
shortShift128Left( 0, zSig1, 1, &zSig0, &zSig1 );
zSig0 |= doubleZSig0;
return roundAndPackFloatx80(status->floatx80_rounding_precision,
0, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-precision floating-point
| value `a' to the extended double-precision floating-point format. The