softfloat: Move round_to_uint_and_pack to softfloat-parts.c.inc

Rename to parts$N_float_to_uint.  Reimplement
float128_to_uint{32,64}{_round_to_zero} with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2020-11-14 14:21:16 -08:00
parent 453d9c61dd
commit 4ab4aef018
2 changed files with 147 additions and 278 deletions

View file

@ -763,7 +763,7 @@ static void partsN(round_to_int)(FloatPartsN *a, FloatRoundMode rmode,
* the largest positive integer is returned. Otherwise, if the
* conversion overflows, the largest integer with the same sign as `a'
* is returned.
*/
*/
static int64_t partsN(float_to_sint)(FloatPartsN *p, FloatRoundMode rmode,
int scale, int64_t min, int64_t max,
float_status *s)
@ -817,3 +817,69 @@ static int64_t partsN(float_to_sint)(FloatPartsN *p, FloatRoundMode rmode,
float_raise(flags, s);
return r;
}
/*
* Returns the result of converting the floating-point value `a' to
* the 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, the result is rounded and zero is returned;
* values that do not round to zero will raise the inexact exception
* flag.
*/
static uint64_t partsN(float_to_uint)(FloatPartsN *p, FloatRoundMode rmode,
int scale, uint64_t max, float_status *s)
{
int flags = 0;
uint64_t r;
switch (p->cls) {
case float_class_snan:
case float_class_qnan:
flags = float_flag_invalid;
r = max;
break;
case float_class_inf:
flags = float_flag_invalid;
r = p->sign ? 0 : max;
break;
case float_class_zero:
return 0;
case float_class_normal:
/* TODO: N - 2 is frac_size for rounding; could use input fmt. */
if (parts_round_to_int_normal(p, rmode, scale, N - 2)) {
flags = float_flag_inexact;
if (p->cls == float_class_zero) {
r = 0;
break;
}
}
if (p->sign) {
flags = float_flag_invalid;
r = 0;
} else if (p->exp > DECOMPOSED_BINARY_POINT) {
flags = float_flag_invalid;
r = max;
} else {
r = p->frac_hi >> (DECOMPOSED_BINARY_POINT - p->exp);
if (r > max) {
flags = float_flag_invalid;
r = max;
}
}
break;
default:
g_assert_not_reached();
}
float_raise(flags, s);
return r;
}

View file

@ -839,6 +839,16 @@ static int64_t parts128_float_to_sint(FloatParts128 *p, FloatRoundMode rmode,
#define parts_float_to_sint(P, R, Z, MN, MX, S) \
PARTS_GENERIC_64_128(float_to_sint, P)(P, R, Z, MN, MX, S)
static uint64_t parts64_float_to_uint(FloatParts64 *p, FloatRoundMode rmode,
int scale, uint64_t max,
float_status *s);
static uint64_t parts128_float_to_uint(FloatParts128 *p, FloatRoundMode rmode,
int scale, uint64_t max,
float_status *s);
#define parts_float_to_uint(P, R, Z, M, S) \
PARTS_GENERIC_64_128(float_to_uint, P)(P, R, Z, M, S)
/*
* Helper functions for softfloat-parts.c.inc, per-size operations.
*/
@ -2646,80 +2656,16 @@ int64_t bfloat16_to_int64_round_to_zero(bfloat16 a, float_status *s)
}
/*
* Returns the result of converting the floating-point value `a' to
* the 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, the result is rounded and zero is returned;
* values that do not round to zero will raise the inexact exception
* flag.
* Floating-point to unsigned integer conversions
*/
static uint64_t round_to_uint_and_pack(FloatParts64 p, FloatRoundMode rmode,
int scale, uint64_t max,
float_status *s)
{
int flags = 0;
uint64_t r;
switch (p.cls) {
case float_class_snan:
case float_class_qnan:
flags = float_flag_invalid;
r = max;
break;
case float_class_inf:
flags = float_flag_invalid;
r = p.sign ? 0 : max;
break;
case float_class_zero:
return 0;
case float_class_normal:
/* TODO: 62 = N - 2, frac_size for rounding */
if (parts_round_to_int_normal(&p, rmode, scale, 62)) {
flags = float_flag_inexact;
if (p.cls == float_class_zero) {
r = 0;
break;
}
}
if (p.sign) {
flags = float_flag_invalid;
r = 0;
} else if (p.exp > DECOMPOSED_BINARY_POINT) {
flags = float_flag_invalid;
r = max;
} else {
r = p.frac >> (DECOMPOSED_BINARY_POINT - p.exp);
if (r > max) {
flags = float_flag_invalid;
r = max;
}
}
break;
default:
g_assert_not_reached();
}
float_raise(flags, s);
return r;
}
uint8_t float16_to_uint8_scalbn(float16 a, FloatRoundMode rmode, int scale,
float_status *s)
{
FloatParts64 p;
float16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT8_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT8_MAX, s);
}
uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale,
@ -2728,7 +2674,7 @@ uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s);
}
uint32_t float16_to_uint32_scalbn(float16 a, FloatRoundMode rmode, int scale,
@ -2737,7 +2683,7 @@ uint32_t float16_to_uint32_scalbn(float16 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s);
}
uint64_t float16_to_uint64_scalbn(float16 a, FloatRoundMode rmode, int scale,
@ -2746,7 +2692,7 @@ uint64_t float16_to_uint64_scalbn(float16 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
}
uint16_t float32_to_uint16_scalbn(float32 a, FloatRoundMode rmode, int scale,
@ -2755,7 +2701,7 @@ uint16_t float32_to_uint16_scalbn(float32 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float32_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s);
}
uint32_t float32_to_uint32_scalbn(float32 a, FloatRoundMode rmode, int scale,
@ -2764,7 +2710,7 @@ uint32_t float32_to_uint32_scalbn(float32 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float32_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s);
}
uint64_t float32_to_uint64_scalbn(float32 a, FloatRoundMode rmode, int scale,
@ -2773,7 +2719,7 @@ uint64_t float32_to_uint64_scalbn(float32 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float32_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
}
uint16_t float64_to_uint16_scalbn(float64 a, FloatRoundMode rmode, int scale,
@ -2782,7 +2728,7 @@ uint16_t float64_to_uint16_scalbn(float64 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float64_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s);
}
uint32_t float64_to_uint32_scalbn(float64 a, FloatRoundMode rmode, int scale,
@ -2791,7 +2737,7 @@ uint32_t float64_to_uint32_scalbn(float64 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float64_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s);
}
uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale,
@ -2800,7 +2746,52 @@ uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale,
FloatParts64 p;
float64_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s);
return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
}
uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s);
}
uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s);
}
uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
}
static uint32_t float128_to_uint32_scalbn(float128 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts128 p;
float128_unpack_canonical(&p, a, s);
return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s);
}
static uint64_t float128_to_uint64_scalbn(float128 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts128 p;
float128_unpack_canonical(&p, a, s);
return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s);
}
uint8_t float16_to_uint8(float16 a, float_status *s)
@ -2853,6 +2844,16 @@ uint64_t float64_to_uint64(float64 a, float_status *s)
return float64_to_uint64_scalbn(a, s->float_rounding_mode, 0, s);
}
uint32_t float128_to_uint32(float128 a, float_status *s)
{
return float128_to_uint32_scalbn(a, s->float_rounding_mode, 0, s);
}
uint64_t float128_to_uint64(float128 a, float_status *s)
{
return float128_to_uint64_scalbn(a, s->float_rounding_mode, 0, s);
}
uint16_t float16_to_uint16_round_to_zero(float16 a, float_status *s)
{
return float16_to_uint16_scalbn(a, float_round_to_zero, 0, s);
@ -2898,36 +2899,14 @@ uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *s)
return float64_to_uint64_scalbn(a, float_round_to_zero, 0, s);
}
/*
* Returns the result of converting the bfloat16 value `a' to
* the unsigned integer format.
*/
uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s);
return float128_to_uint32_scalbn(a, float_round_to_zero, 0, s);
}
uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s);
}
uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode,
int scale, float_status *s)
{
FloatParts64 p;
bfloat16_unpack_canonical(&p, a, s);
return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s);
return float128_to_uint64_scalbn(a, float_round_to_zero, 0, s);
}
uint16_t bfloat16_to_uint16(bfloat16 a, float_status *s)
@ -4123,66 +4102,6 @@ static int64_t roundAndPackInt64(bool zSign, uint64_t absZ0, uint64_t absZ1,
}
/*----------------------------------------------------------------------------
| 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_t roundAndPackUint64(bool zSign, uint64_t absZ0,
uint64_t absZ1, float_status *status)
{
int8_t roundingMode;
bool roundNearestEven, increment;
roundingMode = status->float_rounding_mode;
roundNearestEven = (roundingMode == float_round_nearest_even);
switch (roundingMode) {
case float_round_nearest_even:
case float_round_ties_away:
increment = ((int64_t)absZ1 < 0);
break;
case float_round_to_zero:
increment = 0;
break;
case float_round_up:
increment = !zSign && absZ1;
break;
case float_round_down:
increment = zSign && absZ1;
break;
case float_round_to_odd:
increment = !(absZ0 & 1) && absZ1;
break;
default:
abort();
}
if (increment) {
++absZ0;
if (absZ0 == 0) {
float_raise(float_flag_invalid, status);
return UINT64_MAX;
}
if (!(absZ1 << 1) && roundNearestEven) {
absZ0 &= ~1;
}
}
if (zSign && absZ0) {
float_raise(float_flag_invalid, status);
return 0;
}
if (absZ1) {
float_raise(float_flag_inexact, status);
}
return absZ0;
}
/*----------------------------------------------------------------------------
| Normalizes the subnormal single-precision floating-point value represented
| by the denormalized significand `aSig'. The normalized exponent and
@ -6536,122 +6455,6 @@ floatx80 floatx80_sqrt(floatx80 a, float_status *status)
0, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-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, the value is
| rounded and zero is returned; negative values that do not round to zero
| will raise the inexact exception.
*----------------------------------------------------------------------------*/
uint64_t float128_to_uint64(float128 a, float_status *status)
{
bool aSign;
int aExp;
int shiftCount;
uint64_t aSig0, aSig1;
aSig0 = extractFloat128Frac0(a);
aSig1 = extractFloat128Frac1(a);
aExp = extractFloat128Exp(a);
aSign = extractFloat128Sign(a);
if (aSign && (aExp > 0x3FFE)) {
float_raise(float_flag_invalid, status);
if (float128_is_any_nan(a)) {
return UINT64_MAX;
} else {
return 0;
}
}
if (aExp) {
aSig0 |= UINT64_C(0x0001000000000000);
}
shiftCount = 0x402F - aExp;
if (shiftCount <= 0) {
if (0x403E < aExp) {
float_raise(float_flag_invalid, status);
return UINT64_MAX;
}
shortShift128Left(aSig0, aSig1, -shiftCount, &aSig0, &aSig1);
} else {
shift64ExtraRightJamming(aSig0, aSig1, shiftCount, &aSig0, &aSig1);
}
return roundAndPackUint64(aSign, aSig0, aSig1, status);
}
uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *status)
{
uint64_t v;
signed char current_rounding_mode = status->float_rounding_mode;
set_float_rounding_mode(float_round_to_zero, status);
v = float128_to_uint64(a, status);
set_float_rounding_mode(current_rounding_mode, status);
return v;
}
/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-precision floating-point
| value `a' to the 32-bit unsigned 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 `a' is a NaN, the largest positive integer is returned. Otherwise,
| if the conversion overflows, the largest unsigned integer is returned.
| If 'a' is negative, the value is rounded and zero is returned; negative
| values that do not round to zero will raise the inexact exception.
*----------------------------------------------------------------------------*/
uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *status)
{
uint64_t v;
uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
v = float128_to_uint64_round_to_zero(a, status);
if (v > 0xffffffff) {
res = 0xffffffff;
} else {
return v;
}
set_float_exception_flags(old_exc_flags, status);
float_raise(float_flag_invalid, status);
return res;
}
/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-precision floating-point value
| `a' to the 32-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, the value is
| rounded and zero is returned; negative values that do not round to zero
| will raise the inexact exception.
*----------------------------------------------------------------------------*/
uint32_t float128_to_uint32(float128 a, float_status *status)
{
uint64_t v;
uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
v = float128_to_uint64(a, status);
if (v > 0xffffffff) {
res = 0xffffffff;
} else {
return v;
}
set_float_exception_flags(old_exc_flags, status);
float_raise(float_flag_invalid, status);
return res;
}
/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-precision floating-point
| value `a' to the extended double-precision floating-point format. The