| Message ID | 1387397961-4894-3-git-send-email-tommusta@gmail.com |
|---|---|
| State | New |
| Headers | show |
On 18 December 2013 20:19, Tom Musta <tommusta@gmail.com> wrote: > This patch adds the float32_to_uint64() routine, which converts a > 32-bit floating point number to an unsigned 64 bit number. > > This contribution can be licensed under either the softfloat-2a or -2b > license. > > V2: Reduced patch to just this single routine per feedback from Peter > Maydell. > > V4: Now passing sign to roundAndPackUint64() > > Signed-off-by: Tom Musta <tommusta@gmail.com> > --- > fpu/softfloat.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ > include/fpu/softfloat.h | 1 + > 2 files changed, 46 insertions(+), 0 deletions(-) > > diff --git a/fpu/softfloat.c b/fpu/softfloat.c > index ec23908..1ff59d0 100644 > --- a/fpu/softfloat.c > +++ b/fpu/softfloat.c > @@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM ) > > /*---------------------------------------------------------------------------- > | Returns the result of converting the single-precision floating-point value > +| `a' to the 64-bit unsigned integer format. The conversion is > +| performed according to the IEC/IEEE Standard for Binary Floating-Point > +| Arithmetic---which means in particular that the conversion is rounded > +| according to the current rounding mode. If `a' is a NaN, the largest > +| unsigned integer is returned. Otherwise, if the conversion overflows, the > +| largest unsigned integer is returned. If the 'a' is negative, zero is > +| returned. > +*----------------------------------------------------------------------------*/ > + > +uint64 float32_to_uint64(float32 a STATUS_PARAM) > +{ > + flag aSign; > + int_fast16_t aExp, shiftCount; > + uint32_t aSig; > + uint64_t aSig64, aSigExtra; > + a = float32_squash_input_denormal(a STATUS_VAR); > + > + aSig = extractFloat32Frac(a); > + aExp = extractFloat32Exp(a); > + aSign = extractFloat32Sign(a); > + if (aSign) { > + if (aExp) { > + float_raise(float_flag_invalid STATUS_VAR); NaNs with the sign bit set will wind up in this case and return 0 rather than largest-unsigned-integer. Also it seems like this code says "negative inputs return zero if they're denormal or signal Invalid and return 0 if they're not". Are you sure this does the right thing for (a) values which are not denormal but are close enough to zero to round to it and (b) different rounding modes? > + } else if (aSig) { /* negative denormalized */ > + float_raise(float_flag_inexact STATUS_VAR); > + } > + return 0; > + } > + shiftCount = 0xBE - aExp; > + if (aExp) { > + aSig |= 0x00800000; > + } > + if (shiftCount < 0) { > + float_raise(float_flag_invalid STATUS_VAR); > + return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF); > + } > + > + aSig64 = aSig; > + aSig64 <<= 40; > + shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra); > + return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR); > +} thanks -- PMM
On 12/19/2013 3:31 PM, Peter Maydell wrote: > On 18 December 2013 20:19, Tom Musta <tommusta@gmail.com> wrote: >> This patch adds the float32_to_uint64() routine, which converts a >> 32-bit floating point number to an unsigned 64 bit number. >> >> This contribution can be licensed under either the softfloat-2a or -2b >> license. >> >> V2: Reduced patch to just this single routine per feedback from Peter >> Maydell. >> >> V4: Now passing sign to roundAndPackUint64() >> >> Signed-off-by: Tom Musta <tommusta@gmail.com> >> --- >> fpu/softfloat.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ >> include/fpu/softfloat.h | 1 + >> 2 files changed, 46 insertions(+), 0 deletions(-) >> >> diff --git a/fpu/softfloat.c b/fpu/softfloat.c >> index ec23908..1ff59d0 100644 >> --- a/fpu/softfloat.c >> +++ b/fpu/softfloat.c >> @@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM ) >> >> /*---------------------------------------------------------------------------- >> | Returns the result of converting the single-precision floating-point value >> +| `a' to the 64-bit unsigned integer format. The conversion is >> +| performed according to the IEC/IEEE Standard for Binary Floating-Point >> +| Arithmetic---which means in particular that the conversion is rounded >> +| according to the current rounding mode. If `a' is a NaN, the largest >> +| unsigned integer is returned. Otherwise, if the conversion overflows, the >> +| largest unsigned integer is returned. If the 'a' is negative, zero is >> +| returned. >> +*----------------------------------------------------------------------------*/ >> + >> +uint64 float32_to_uint64(float32 a STATUS_PARAM) >> +{ >> + flag aSign; >> + int_fast16_t aExp, shiftCount; >> + uint32_t aSig; >> + uint64_t aSig64, aSigExtra; >> + a = float32_squash_input_denormal(a STATUS_VAR); >> + >> + aSig = extractFloat32Frac(a); >> + aExp = extractFloat32Exp(a); >> + aSign = extractFloat32Sign(a); >> + if (aSign) { >> + if (aExp) { >> + float_raise(float_flag_invalid STATUS_VAR); > > NaNs with the sign bit set will wind up in this case and return 0 > rather than largest-unsigned-integer. > > Also it seems like this code says "negative inputs return > zero if they're denormal or signal Invalid and return 0 > if they're not". Are you sure this does the right thing for > (a) values which are not denormal but are close enough > to zero to round to it and (b) different rounding modes? > >> + } else if (aSig) { /* negative denormalized */ >> + float_raise(float_flag_inexact STATUS_VAR); >> + } >> + return 0; >> + } >> + shiftCount = 0xBE - aExp; >> + if (aExp) { >> + aSig |= 0x00800000; >> + } >> + if (shiftCount < 0) { >> + float_raise(float_flag_invalid STATUS_VAR); >> + return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF); >> + } >> + >> + aSig64 = aSig; >> + aSig64 <<= 40; >> + shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra); >> + return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR); >> +} > > thanks > -- PMM > Peter: I agree ... this still isn't quite right.
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index ec23908..1ff59d0 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -1558,6 +1558,51 @@ int64 float32_to_int64( float32 a STATUS_PARAM ) /*---------------------------------------------------------------------------- | Returns the result of converting the single-precision floating-point value +| `a' to the 64-bit unsigned integer format. The conversion is +| performed according to the IEC/IEEE Standard for Binary Floating-Point +| Arithmetic---which means in particular that the conversion is rounded +| according to the current rounding mode. If `a' is a NaN, the largest +| unsigned integer is returned. Otherwise, if the conversion overflows, the +| largest unsigned integer is returned. If the 'a' is negative, zero is +| returned. +*----------------------------------------------------------------------------*/ + +uint64 float32_to_uint64(float32 a STATUS_PARAM) +{ + flag aSign; + int_fast16_t aExp, shiftCount; + uint32_t aSig; + uint64_t aSig64, aSigExtra; + a = float32_squash_input_denormal(a STATUS_VAR); + + aSig = extractFloat32Frac(a); + aExp = extractFloat32Exp(a); + aSign = extractFloat32Sign(a); + if (aSign) { + if (aExp) { + float_raise(float_flag_invalid STATUS_VAR); + } else if (aSig) { /* negative denormalized */ + float_raise(float_flag_inexact STATUS_VAR); + } + return 0; + } + shiftCount = 0xBE - aExp; + if (aExp) { + aSig |= 0x00800000; + } + if (shiftCount < 0) { + float_raise(float_flag_invalid STATUS_VAR); + return (int64_t)LIT64(0xFFFFFFFFFFFFFFFF); + } + + aSig64 = aSig; + aSig64 <<= 40; + shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra); + return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR); +} + +/*---------------------------------------------------------------------------- +| Returns the result of converting the single-precision floating-point value | `a' to the 64-bit two's complement integer format. The conversion is | performed according to the IEC/IEEE Standard for Binary Floating-Point | Arithmetic, except that the conversion is always rounded toward zero. If diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 2365274..080b36d 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -272,6 +272,7 @@ int32 float32_to_int32_round_to_zero( float32 STATUS_PARAM ); uint32 float32_to_uint32( float32 STATUS_PARAM ); uint32 float32_to_uint32_round_to_zero( float32 STATUS_PARAM ); int64 float32_to_int64( float32 STATUS_PARAM ); +uint64 float32_to_uint64(float32 STATUS_PARAM); int64 float32_to_int64_round_to_zero( float32 STATUS_PARAM ); float64 float32_to_float64( float32 STATUS_PARAM ); floatx80 float32_to_floatx80( float32 STATUS_PARAM );
This patch adds the float32_to_uint64() routine, which converts a 32-bit floating point number to an unsigned 64 bit number. This contribution can be licensed under either the softfloat-2a or -2b license. V2: Reduced patch to just this single routine per feedback from Peter Maydell. V4: Now passing sign to roundAndPackUint64() Signed-off-by: Tom Musta <tommusta@gmail.com> --- fpu/softfloat.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/fpu/softfloat.h | 1 + 2 files changed, 46 insertions(+), 0 deletions(-)