From 3272cf327e5030941dbffad44f1e5654139284d9 Mon Sep 17 00:00:00 2001 From: Tom Musta Date: Fri, 20 Dec 2013 11:15:49 +0000 Subject: softfloat: Fix float64_to_uint64 The comment preceding the float64_to_uint64 routine suggests that the implementation is broken. And this is, indeed, the case. This patch properly implements the conversion of a 64-bit floating point number to an unsigned, 64 bit integer. This contribution can be licensed under either the softfloat-2a or -2b license. V2: Added softfloat license statement. V3: Modified to meet QEMU coding conventions. V4: Fixed incorrect handling of small negatives, which, if rounded up to zero should not set the inexact flag. Signed-off-by: Tom Musta Message-id: 1387397961-4894-2-git-send-email-tommusta@gmail.com PMM notes: this looks like it gives the wrong answer for NaNs with the sign bit set. --- fpu/softfloat.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 89 insertions(+), 9 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index e078539410..afabb04ad8 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -161,7 +161,6 @@ static int32 roundAndPackInt32( flag zSign, uint64_t absZ STATUS_PARAM) | exception is raised and the largest positive or negative integer is | returned. *----------------------------------------------------------------------------*/ - static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATUS_PARAM) { int8 roundingMode; @@ -203,6 +202,56 @@ static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATU } +/*---------------------------------------------------------------------------- +| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and +| `absZ1', with binary point between bits 63 and 64 (between the input words), +| and returns the properly rounded 64-bit unsigned integer corresponding to the +| input. Ordinarily, the fixed-point input is simply rounded to an integer, +| with the inexact exception raised if the input cannot be represented exactly +| as an integer. However, if the fixed-point input is too large, the invalid +| exception is raised and the largest unsigned integer is returned. +*----------------------------------------------------------------------------*/ + +static int64 roundAndPackUint64(flag zSign, uint64_t absZ0, + uint64_t absZ1 STATUS_PARAM) +{ + int8 roundingMode; + flag roundNearestEven, increment; + + roundingMode = STATUS(float_rounding_mode); + roundNearestEven = (roundingMode == float_round_nearest_even); + increment = ((int64_t)absZ1 < 0); + if (!roundNearestEven) { + if (roundingMode == float_round_to_zero) { + increment = 0; + } else if (absZ1) { + if (zSign) { + increment = (roundingMode == float_round_down) && absZ1; + } else { + increment = (roundingMode == float_round_up) && absZ1; + } + } + } + if (increment) { + ++absZ0; + if (absZ0 == 0) { + float_raise(float_flag_invalid STATUS_VAR); + return LIT64(0xFFFFFFFFFFFFFFFF); + } + absZ0 &= ~(((uint64_t)(absZ1<<1) == 0) & roundNearestEven); + } + + if (zSign && absZ0) { + float_raise(float_flag_invalid STATUS_VAR); + return 0; + } + + if (absZ1) { + STATUS(float_exception_flags) |= float_flag_inexact; + } + return absZ0; +} + /*---------------------------------------------------------------------------- | Returns the fraction bits of the single-precision floating-point value `a'. *----------------------------------------------------------------------------*/ @@ -6643,18 +6692,49 @@ uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM) return res; } -/* FIXME: This looks broken. */ -uint64_t float64_to_uint64 (float64 a STATUS_PARAM) -{ - int64_t v; +/*---------------------------------------------------------------------------- +| Returns the result of converting the double-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 +| positive integer is returned. If the conversion overflows, the +| largest unsigned integer is returned. If 'a' is negative, zero is +| returned. +*----------------------------------------------------------------------------*/ - v = float64_val(int64_to_float64(INT64_MIN STATUS_VAR)); - v += float64_val(a); - v = float64_to_int64(make_float64(v) STATUS_VAR); +uint64_t float64_to_uint64(float64 a STATUS_PARAM) +{ + flag aSign; + int_fast16_t aExp, shiftCount; + uint64_t aSig, aSigExtra; + a = float64_squash_input_denormal(a STATUS_VAR); - return v - INT64_MIN; + aSig = extractFloat64Frac(a); + aExp = extractFloat64Exp(a); + aSign = extractFloat64Sign(a); + if (aSign && (aExp > 1022)) { + float_raise(float_flag_invalid STATUS_VAR); + return 0; + } + if (aExp) { + aSig |= LIT64(0x0010000000000000); + } + shiftCount = 0x433 - aExp; + if (shiftCount <= 0) { + if (0x43E < aExp) { + float_raise(float_flag_invalid STATUS_VAR); + return LIT64(0xFFFFFFFFFFFFFFFF); + } + aSigExtra = 0; + aSig <<= -shiftCount; + } else { + shift64ExtraRightJamming(aSig, 0, shiftCount, &aSig, &aSigExtra); + } + return roundAndPackUint64(aSign, aSig, aSigExtra STATUS_VAR); } + uint64_t float64_to_uint64_round_to_zero (float64 a STATUS_PARAM) { int64_t v; -- cgit v1.2.3