/*
* QEMU float support
*
- * Derived from SoftFloat.
+ * The code in this source file is derived from release 2a of the SoftFloat
+ * IEC/IEEE Floating-point Arithmetic Package. Those parts of the code (and
+ * some later contributions) are provided under that license, as detailed below.
+ * It has subsequently been modified by contributors to the QEMU Project,
+ * so some portions are provided under:
+ * the SoftFloat-2a license
+ * the BSD license
+ * GPL-v2-or-later
+ *
+ * Any future contributions to this file after December 1st 2014 will be
+ * taken to be licensed under the Softfloat-2a license unless specifically
+ * indicated otherwise.
*/
-/*============================================================================
-
-This C source file is part of the SoftFloat IEC/IEEE Floating-point Arithmetic
-Package, Release 2b.
+/*
+===============================================================================
+This C source file is part of the SoftFloat IEC/IEEE Floating-point
+Arithmetic Package, Release 2a.
Written by John R. Hauser. This work was made possible in part by the
International Computer Science Institute, located at Suite 600, 1947 Center
of this code was written as part of a project to build a fixed-point vector
processor in collaboration with the University of California at Berkeley,
overseen by Profs. Nelson Morgan and John Wawrzynek. More information
-is available through the Web page `http://www.cs.berkeley.edu/~jhauser/
+is available through the Web page `http://HTTP.CS.Berkeley.EDU/~jhauser/
arithmetic/SoftFloat.html'.
-THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE. Although reasonable effort has
-been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT TIMES
-RESULT IN INCORRECT BEHAVIOR. USE OF THIS SOFTWARE IS RESTRICTED TO PERSONS
-AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ALL LOSSES,
-COSTS, OR OTHER PROBLEMS THEY INCUR DUE TO THE SOFTWARE, AND WHO FURTHERMORE
-EFFECTIVELY INDEMNIFY JOHN HAUSER AND THE INTERNATIONAL COMPUTER SCIENCE
-INSTITUTE (possibly via similar legal warning) AGAINST ALL LOSSES, COSTS, OR
-OTHER PROBLEMS INCURRED BY THEIR CUSTOMERS AND CLIENTS DUE TO THE SOFTWARE.
+THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE. Although reasonable effort
+has been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT
+TIMES RESULT IN INCORRECT BEHAVIOR. USE OF THIS SOFTWARE IS RESTRICTED TO
+PERSONS AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ANY
+AND ALL LOSSES, COSTS, OR OTHER PROBLEMS ARISING FROM ITS USE.
Derivative works are acceptable, even for commercial purposes, so long as
-(1) the source code for the derivative work includes prominent notice that
-the work is derivative, and (2) the source code includes prominent notice with
-these four paragraphs for those parts of this code that are retained.
+(1) they include prominent notice that the work is derivative, and (2) they
+include prominent notice akin to these four paragraphs for those parts of
+this code that are retained.
+
+===============================================================================
+*/
+
+/* BSD licensing:
+ * Copyright (c) 2006, Fabrice Bellard
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * 3. Neither the name of the copyright holder nor the names of its contributors
+ * may be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
-=============================================================================*/
+/* Portions of this work are licensed under the terms of the GNU GPL,
+ * version 2 or later. See the COPYING file in the top-level directory.
+ */
/* softfloat (and in particular the code in softfloat-specialize.h) is
* target-dependent and needs the TARGET_* macros.
*/
-#include "config.h"
+#include "qemu/osdep.h"
#include "fpu/softfloat.h"
/* We only need stdlib for abort() */
-#include <stdlib.h>
/*----------------------------------------------------------------------------
| Primitive arithmetic functions, including multi-word arithmetic, and
| Returns the fraction bits of the half-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint32_t extractFloat16Frac(float16 a)
+static inline uint32_t extractFloat16Frac(float16 a)
{
return float16_val(a) & 0x3ff;
}
| Returns the exponent bits of the half-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE int_fast16_t extractFloat16Exp(float16 a)
+static inline int extractFloat16Exp(float16 a)
{
return (float16_val(a) >> 10) & 0x1f;
}
| Returns the sign bit of the single-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE flag extractFloat16Sign(float16 a)
+static inline flag extractFloat16Sign(float16 a)
{
return float16_val(a)>>15;
}
| positive or negative integer is returned.
*----------------------------------------------------------------------------*/
-static int32 roundAndPackInt32( flag zSign, uint64_t absZ STATUS_PARAM)
+static int32_t roundAndPackInt32(flag zSign, uint64_t absZ, float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven;
- int8 roundIncrement, roundBits;
+ int8_t roundIncrement, roundBits;
int32_t z;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
switch (roundingMode) {
case float_round_nearest_even:
z = absZ;
if ( zSign ) z = - z;
if ( ( absZ>>32 ) || ( z && ( ( z < 0 ) ^ zSign ) ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return zSign ? (int32_t) 0x80000000 : 0x7FFFFFFF;
}
- if ( roundBits ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (roundBits) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return z;
}
| returned.
*----------------------------------------------------------------------------*/
-static int64 roundAndPackInt64( flag zSign, uint64_t absZ0, uint64_t absZ1 STATUS_PARAM)
+static int64_t roundAndPackInt64(flag zSign, uint64_t absZ0, uint64_t absZ1,
+ float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven, increment;
int64_t z;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
switch (roundingMode) {
case float_round_nearest_even:
if ( zSign ) z = - z;
if ( z && ( ( z < 0 ) ^ zSign ) ) {
overflow:
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return
zSign ? (int64_t) LIT64( 0x8000000000000000 )
: LIT64( 0x7FFFFFFFFFFFFFFF );
}
- if ( absZ1 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (absZ1) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return z;
}
| exception is raised and the largest unsigned integer is returned.
*----------------------------------------------------------------------------*/
-static int64 roundAndPackUint64(flag zSign, uint64_t absZ0,
- uint64_t absZ1 STATUS_PARAM)
+static int64_t roundAndPackUint64(flag zSign, uint64_t absZ0,
+ uint64_t absZ1, float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven, increment;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = (roundingMode == float_round_nearest_even);
switch (roundingMode) {
case float_round_nearest_even:
if (increment) {
++absZ0;
if (absZ0 == 0) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return LIT64(0xFFFFFFFFFFFFFFFF);
}
absZ0 &= ~(((uint64_t)(absZ1<<1) == 0) & roundNearestEven);
}
if (zSign && absZ0) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
if (absZ1) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return absZ0;
}
| Returns the fraction bits of the single-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint32_t extractFloat32Frac( float32 a )
+static inline uint32_t extractFloat32Frac( float32 a )
{
return float32_val(a) & 0x007FFFFF;
| Returns the exponent bits of the single-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE int_fast16_t extractFloat32Exp(float32 a)
+static inline int extractFloat32Exp(float32 a)
{
return ( float32_val(a)>>23 ) & 0xFF;
| Returns the sign bit of the single-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE flag extractFloat32Sign( float32 a )
+static inline flag extractFloat32Sign( float32 a )
{
return float32_val(a)>>31;
| If `a' is denormal and we are in flush-to-zero mode then set the
| input-denormal exception and return zero. Otherwise just return the value.
*----------------------------------------------------------------------------*/
-static float32 float32_squash_input_denormal(float32 a STATUS_PARAM)
+float32 float32_squash_input_denormal(float32 a, float_status *status)
{
- if (STATUS(flush_inputs_to_zero)) {
+ if (status->flush_inputs_to_zero) {
if (extractFloat32Exp(a) == 0 && extractFloat32Frac(a) != 0) {
- float_raise(float_flag_input_denormal STATUS_VAR);
+ float_raise(float_flag_input_denormal, status);
return make_float32(float32_val(a) & 0x80000000);
}
}
*----------------------------------------------------------------------------*/
static void
- normalizeFloat32Subnormal(uint32_t aSig, int_fast16_t *zExpPtr, uint32_t *zSigPtr)
+ normalizeFloat32Subnormal(uint32_t aSig, int *zExpPtr, uint32_t *zSigPtr)
{
- int8 shiftCount;
+ int8_t shiftCount;
shiftCount = countLeadingZeros32( aSig ) - 8;
*zSigPtr = aSig<<shiftCount;
| significand.
*----------------------------------------------------------------------------*/
-INLINE float32 packFloat32(flag zSign, int_fast16_t zExp, uint32_t zSig)
+static inline float32 packFloat32(flag zSign, int zExp, uint32_t zSig)
{
return make_float32(
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float32 roundAndPackFloat32(flag zSign, int_fast16_t zExp, uint32_t zSig STATUS_PARAM)
+static float32 roundAndPackFloat32(flag zSign, int zExp, uint32_t zSig,
+ float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven;
- int8 roundIncrement, roundBits;
+ int8_t roundIncrement, roundBits;
flag isTiny;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
switch (roundingMode) {
case float_round_nearest_even:
|| ( ( zExp == 0xFD )
&& ( (int32_t) ( zSig + roundIncrement ) < 0 ) )
) {
- float_raise( float_flag_overflow | float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_overflow | float_flag_inexact, status);
return packFloat32( zSign, 0xFF, - ( roundIncrement == 0 ));
}
if ( zExp < 0 ) {
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloat32(zSign, 0, 0);
}
isTiny =
- ( STATUS(float_detect_tininess) == float_tininess_before_rounding )
+ (status->float_detect_tininess
+ == float_tininess_before_rounding)
|| ( zExp < -1 )
|| ( zSig + roundIncrement < 0x80000000 );
shift32RightJamming( zSig, - zExp, &zSig );
zExp = 0;
roundBits = zSig & 0x7F;
- if ( isTiny && roundBits ) float_raise( float_flag_underflow STATUS_VAR);
+ if (isTiny && roundBits) {
+ float_raise(float_flag_underflow, status);
+ }
}
}
- if ( roundBits ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (roundBits) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
zSig = ( zSig + roundIncrement )>>7;
zSig &= ~ ( ( ( roundBits ^ 0x40 ) == 0 ) & roundNearestEven );
if ( zSig == 0 ) zExp = 0;
*----------------------------------------------------------------------------*/
static float32
- normalizeRoundAndPackFloat32(flag zSign, int_fast16_t zExp, uint32_t zSig STATUS_PARAM)
+ normalizeRoundAndPackFloat32(flag zSign, int zExp, uint32_t zSig,
+ float_status *status)
{
- int8 shiftCount;
+ int8_t shiftCount;
shiftCount = countLeadingZeros32( zSig ) - 1;
- return roundAndPackFloat32( zSign, zExp - shiftCount, zSig<<shiftCount STATUS_VAR);
+ return roundAndPackFloat32(zSign, zExp - shiftCount, zSig<<shiftCount,
+ status);
}
| Returns the fraction bits of the double-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint64_t extractFloat64Frac( float64 a )
+static inline uint64_t extractFloat64Frac( float64 a )
{
return float64_val(a) & LIT64( 0x000FFFFFFFFFFFFF );
| Returns the exponent bits of the double-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE int_fast16_t extractFloat64Exp(float64 a)
+static inline int extractFloat64Exp(float64 a)
{
return ( float64_val(a)>>52 ) & 0x7FF;
| Returns the sign bit of the double-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE flag extractFloat64Sign( float64 a )
+static inline flag extractFloat64Sign( float64 a )
{
return float64_val(a)>>63;
| If `a' is denormal and we are in flush-to-zero mode then set the
| input-denormal exception and return zero. Otherwise just return the value.
*----------------------------------------------------------------------------*/
-static float64 float64_squash_input_denormal(float64 a STATUS_PARAM)
+float64 float64_squash_input_denormal(float64 a, float_status *status)
{
- if (STATUS(flush_inputs_to_zero)) {
+ if (status->flush_inputs_to_zero) {
if (extractFloat64Exp(a) == 0 && extractFloat64Frac(a) != 0) {
- float_raise(float_flag_input_denormal STATUS_VAR);
+ float_raise(float_flag_input_denormal, status);
return make_float64(float64_val(a) & (1ULL << 63));
}
}
*----------------------------------------------------------------------------*/
static void
- normalizeFloat64Subnormal(uint64_t aSig, int_fast16_t *zExpPtr, uint64_t *zSigPtr)
+ normalizeFloat64Subnormal(uint64_t aSig, int *zExpPtr, uint64_t *zSigPtr)
{
- int8 shiftCount;
+ int8_t shiftCount;
shiftCount = countLeadingZeros64( aSig ) - 11;
*zSigPtr = aSig<<shiftCount;
| significand.
*----------------------------------------------------------------------------*/
-INLINE float64 packFloat64(flag zSign, int_fast16_t zExp, uint64_t zSig)
+static inline float64 packFloat64(flag zSign, int zExp, uint64_t zSig)
{
return make_float64(
| the inexact exception raised if the abstract input cannot be represented
| exactly. However, if the abstract value is too large, the overflow and
| inexact exceptions are raised and an infinity or maximal finite value is
-| returned. If the abstract value is too small, the input value is rounded
-| to a subnormal number, and the underflow and inexact exceptions are raised
-| if the abstract input cannot be represented exactly as a subnormal double-
+| returned. If the abstract value is too small, the input value is rounded to
+| a subnormal number, and the underflow and inexact exceptions are raised if
+| the abstract input cannot be represented exactly as a subnormal double-
| precision floating-point number.
| The input significand `zSig' has its binary point between bits 62
| and 61, which is 10 bits to the left of the usual location. This shifted
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float64 roundAndPackFloat64(flag zSign, int_fast16_t zExp, uint64_t zSig STATUS_PARAM)
+static float64 roundAndPackFloat64(flag zSign, int zExp, uint64_t zSig,
+ float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven;
- int_fast16_t roundIncrement, roundBits;
+ int roundIncrement, roundBits;
flag isTiny;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
switch (roundingMode) {
case float_round_nearest_even:
case float_round_down:
roundIncrement = zSign ? 0x3ff : 0;
break;
+ case float_round_to_odd:
+ roundIncrement = (zSig & 0x400) ? 0 : 0x3ff;
+ break;
default:
abort();
}
|| ( ( zExp == 0x7FD )
&& ( (int64_t) ( zSig + roundIncrement ) < 0 ) )
) {
- float_raise( float_flag_overflow | float_flag_inexact STATUS_VAR);
- return packFloat64( zSign, 0x7FF, - ( roundIncrement == 0 ));
+ bool overflow_to_inf = roundingMode != float_round_to_odd &&
+ roundIncrement != 0;
+ float_raise(float_flag_overflow | float_flag_inexact, status);
+ return packFloat64(zSign, 0x7FF, -(!overflow_to_inf));
}
if ( zExp < 0 ) {
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloat64(zSign, 0, 0);
}
isTiny =
- ( STATUS(float_detect_tininess) == float_tininess_before_rounding )
+ (status->float_detect_tininess
+ == float_tininess_before_rounding)
|| ( zExp < -1 )
|| ( zSig + roundIncrement < LIT64( 0x8000000000000000 ) );
shift64RightJamming( zSig, - zExp, &zSig );
zExp = 0;
roundBits = zSig & 0x3FF;
- if ( isTiny && roundBits ) float_raise( float_flag_underflow STATUS_VAR);
+ if (isTiny && roundBits) {
+ float_raise(float_flag_underflow, status);
+ }
+ if (roundingMode == float_round_to_odd) {
+ /*
+ * For round-to-odd case, the roundIncrement depends on
+ * zSig which just changed.
+ */
+ roundIncrement = (zSig & 0x400) ? 0 : 0x3ff;
+ }
}
}
- if ( roundBits ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (roundBits) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
zSig = ( zSig + roundIncrement )>>10;
zSig &= ~ ( ( ( roundBits ^ 0x200 ) == 0 ) & roundNearestEven );
if ( zSig == 0 ) zExp = 0;
*----------------------------------------------------------------------------*/
static float64
- normalizeRoundAndPackFloat64(flag zSign, int_fast16_t zExp, uint64_t zSig STATUS_PARAM)
+ normalizeRoundAndPackFloat64(flag zSign, int zExp, uint64_t zSig,
+ float_status *status)
{
- int8 shiftCount;
+ int8_t shiftCount;
shiftCount = countLeadingZeros64( zSig ) - 1;
- return roundAndPackFloat64( zSign, zExp - shiftCount, zSig<<shiftCount STATUS_VAR);
+ return roundAndPackFloat64(zSign, zExp - shiftCount, zSig<<shiftCount,
+ status);
}
| value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint64_t extractFloatx80Frac( floatx80 a )
+static inline uint64_t extractFloatx80Frac( floatx80 a )
{
return a.low;
| value `a'.
*----------------------------------------------------------------------------*/
-INLINE int32 extractFloatx80Exp( floatx80 a )
+static inline int32_t extractFloatx80Exp( floatx80 a )
{
return a.high & 0x7FFF;
| `a'.
*----------------------------------------------------------------------------*/
-INLINE flag extractFloatx80Sign( floatx80 a )
+static inline flag extractFloatx80Sign( floatx80 a )
{
return a.high>>15;
*----------------------------------------------------------------------------*/
static void
- normalizeFloatx80Subnormal( uint64_t aSig, int32 *zExpPtr, uint64_t *zSigPtr )
+ normalizeFloatx80Subnormal( uint64_t aSig, int32_t *zExpPtr, uint64_t *zSigPtr )
{
- int8 shiftCount;
+ int8_t shiftCount;
shiftCount = countLeadingZeros64( aSig );
*zSigPtr = aSig<<shiftCount;
| extended double-precision floating-point value, returning the result.
*----------------------------------------------------------------------------*/
-INLINE floatx80 packFloatx80( flag zSign, int32 zExp, uint64_t zSig )
+static inline floatx80 packFloatx80( flag zSign, int32_t zExp, uint64_t zSig )
{
floatx80 z;
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static floatx80
- roundAndPackFloatx80(
- int8 roundingPrecision, flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1
- STATUS_PARAM)
+static floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign,
+ int32_t zExp, uint64_t zSig0, uint64_t zSig1,
+ float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven, increment, isTiny;
- int64 roundIncrement, roundMask, roundBits;
+ int64_t roundIncrement, roundMask, roundBits;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
if ( roundingPrecision == 80 ) goto precision80;
if ( roundingPrecision == 64 ) {
goto overflow;
}
if ( zExp <= 0 ) {
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloatx80(zSign, 0, 0);
}
isTiny =
- ( STATUS(float_detect_tininess) == float_tininess_before_rounding )
+ (status->float_detect_tininess
+ == float_tininess_before_rounding)
|| ( zExp < 0 )
|| ( zSig0 <= zSig0 + roundIncrement );
shift64RightJamming( zSig0, 1 - zExp, &zSig0 );
zExp = 0;
roundBits = zSig0 & roundMask;
- if ( isTiny && roundBits ) float_raise( float_flag_underflow STATUS_VAR);
- if ( roundBits ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (isTiny && roundBits) {
+ float_raise(float_flag_underflow, status);
+ }
+ if (roundBits) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
zSig0 += roundIncrement;
if ( (int64_t) zSig0 < 0 ) zExp = 1;
roundIncrement = roundMask + 1;
return packFloatx80( zSign, zExp, zSig0 );
}
}
- if ( roundBits ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (roundBits) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
zSig0 += roundIncrement;
if ( zSig0 < roundIncrement ) {
++zExp;
) {
roundMask = 0;
overflow:
- float_raise( float_flag_overflow | float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_overflow | float_flag_inexact, status);
if ( ( roundingMode == float_round_to_zero )
|| ( zSign && ( roundingMode == float_round_up ) )
|| ( ! zSign && ( roundingMode == float_round_down ) )
}
if ( zExp <= 0 ) {
isTiny =
- ( STATUS(float_detect_tininess) == float_tininess_before_rounding )
+ (status->float_detect_tininess
+ == float_tininess_before_rounding)
|| ( zExp < 0 )
|| ! increment
|| ( zSig0 < LIT64( 0xFFFFFFFFFFFFFFFF ) );
shift64ExtraRightJamming( zSig0, zSig1, 1 - zExp, &zSig0, &zSig1 );
zExp = 0;
- if ( isTiny && zSig1 ) float_raise( float_flag_underflow STATUS_VAR);
- if ( zSig1 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (isTiny && zSig1) {
+ float_raise(float_flag_underflow, status);
+ }
+ if (zSig1) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
switch (roundingMode) {
case float_round_nearest_even:
case float_round_ties_away:
return packFloatx80( zSign, zExp, zSig0 );
}
}
- if ( zSig1 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (zSig1) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
if ( increment ) {
++zSig0;
if ( zSig0 == 0 ) {
| normalized.
*----------------------------------------------------------------------------*/
-static floatx80
- normalizeRoundAndPackFloatx80(
- int8 roundingPrecision, flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1
- STATUS_PARAM)
+static floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision,
+ flag zSign, int32_t zExp,
+ uint64_t zSig0, uint64_t zSig1,
+ float_status *status)
{
- int8 shiftCount;
+ int8_t shiftCount;
if ( zSig0 == 0 ) {
zSig0 = zSig1;
shiftCount = countLeadingZeros64( zSig0 );
shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 );
zExp -= shiftCount;
- return
- roundAndPackFloatx80( roundingPrecision, zSign, zExp, zSig0, zSig1 STATUS_VAR);
+ return roundAndPackFloatx80(roundingPrecision, zSign, zExp,
+ zSig0, zSig1, status);
}
| floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint64_t extractFloat128Frac1( float128 a )
+static inline uint64_t extractFloat128Frac1( float128 a )
{
return a.low;
| floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE uint64_t extractFloat128Frac0( float128 a )
+static inline uint64_t extractFloat128Frac0( float128 a )
{
return a.high & LIT64( 0x0000FFFFFFFFFFFF );
| `a'.
*----------------------------------------------------------------------------*/
-INLINE int32 extractFloat128Exp( float128 a )
+static inline int32_t extractFloat128Exp( float128 a )
{
return ( a.high>>48 ) & 0x7FFF;
| Returns the sign bit of the quadruple-precision floating-point value `a'.
*----------------------------------------------------------------------------*/
-INLINE flag extractFloat128Sign( float128 a )
+static inline flag extractFloat128Sign( float128 a )
{
return a.high>>63;
normalizeFloat128Subnormal(
uint64_t aSig0,
uint64_t aSig1,
- int32 *zExpPtr,
+ int32_t *zExpPtr,
uint64_t *zSig0Ptr,
uint64_t *zSig1Ptr
)
{
- int8 shiftCount;
+ int8_t shiftCount;
if ( aSig0 == 0 ) {
shiftCount = countLeadingZeros64( aSig1 ) - 15;
| significand.
*----------------------------------------------------------------------------*/
-INLINE float128
- packFloat128( flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1 )
+static inline float128
+ packFloat128( flag zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1 )
{
float128 z;
| overflow follows the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float128
- roundAndPackFloat128(
- flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1, uint64_t zSig2 STATUS_PARAM)
+static float128 roundAndPackFloat128(flag zSign, int32_t zExp,
+ uint64_t zSig0, uint64_t zSig1,
+ uint64_t zSig2, float_status *status)
{
- int8 roundingMode;
+ int8_t roundingMode;
flag roundNearestEven, increment, isTiny;
- roundingMode = STATUS(float_rounding_mode);
+ roundingMode = status->float_rounding_mode;
roundNearestEven = ( roundingMode == float_round_nearest_even );
switch (roundingMode) {
case float_round_nearest_even:
case float_round_down:
increment = zSign && zSig2;
break;
+ case float_round_to_odd:
+ increment = !(zSig1 & 0x1) && zSig2;
+ break;
default:
abort();
}
&& increment
)
) {
- float_raise( float_flag_overflow | float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_overflow | float_flag_inexact, status);
if ( ( roundingMode == float_round_to_zero )
|| ( zSign && ( roundingMode == float_round_up ) )
|| ( ! zSign && ( roundingMode == float_round_down ) )
+ || (roundingMode == float_round_to_odd)
) {
return
packFloat128(
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
if ( zExp < 0 ) {
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloat128(zSign, 0, 0, 0);
}
isTiny =
- ( STATUS(float_detect_tininess) == float_tininess_before_rounding )
+ (status->float_detect_tininess
+ == float_tininess_before_rounding)
|| ( zExp < -1 )
|| ! increment
|| lt128(
shift128ExtraRightJamming(
zSig0, zSig1, zSig2, - zExp, &zSig0, &zSig1, &zSig2 );
zExp = 0;
- if ( isTiny && zSig2 ) float_raise( float_flag_underflow STATUS_VAR);
+ if (isTiny && zSig2) {
+ float_raise(float_flag_underflow, status);
+ }
switch (roundingMode) {
case float_round_nearest_even:
case float_round_ties_away:
case float_round_down:
increment = zSign && zSig2;
break;
+ case float_round_to_odd:
+ increment = !(zSig1 & 0x1) && zSig2;
+ break;
default:
abort();
}
}
}
- if ( zSig2 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (zSig2) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
if ( increment ) {
add128( zSig0, zSig1, 0, 1, &zSig0, &zSig1 );
zSig1 &= ~ ( ( zSig2 + zSig2 == 0 ) & roundNearestEven );
| point exponent.
*----------------------------------------------------------------------------*/
-static float128
- normalizeRoundAndPackFloat128(
- flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1 STATUS_PARAM)
+static float128 normalizeRoundAndPackFloat128(flag zSign, int32_t zExp,
+ uint64_t zSig0, uint64_t zSig1,
+ float_status *status)
{
- int8 shiftCount;
+ int8_t shiftCount;
uint64_t zSig2;
if ( zSig0 == 0 ) {
zSig0, zSig1, 0, - shiftCount, &zSig0, &zSig1, &zSig2 );
}
zExp -= shiftCount;
- return roundAndPackFloat128( zSign, zExp, zSig0, zSig1, zSig2 STATUS_VAR);
+ return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status);
}
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 int32_to_float32(int32_t a STATUS_PARAM)
+float32 int32_to_float32(int32_t a, float_status *status)
{
flag zSign;
if ( a == 0 ) return float32_zero;
if ( a == (int32_t) 0x80000000 ) return packFloat32( 1, 0x9E, 0 );
zSign = ( a < 0 );
- return normalizeRoundAndPackFloat32( zSign, 0x9C, zSign ? - a : a STATUS_VAR );
-
+ return normalizeRoundAndPackFloat32(zSign, 0x9C, zSign ? -a : a, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 int32_to_float64(int32_t a STATUS_PARAM)
+float64 int32_to_float64(int32_t a, float_status *status)
{
flag zSign;
- uint32 absA;
- int8 shiftCount;
+ uint32_t absA;
+ int8_t shiftCount;
uint64_t zSig;
if ( a == 0 ) return float64_zero;
| Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 int32_to_floatx80(int32_t a STATUS_PARAM)
+floatx80 int32_to_floatx80(int32_t a, float_status *status)
{
flag zSign;
- uint32 absA;
- int8 shiftCount;
+ uint32_t absA;
+ int8_t shiftCount;
uint64_t zSig;
if ( a == 0 ) return packFloatx80( 0, 0, 0 );
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 int32_to_float128(int32_t a STATUS_PARAM)
+float128 int32_to_float128(int32_t a, float_status *status)
{
flag zSign;
- uint32 absA;
- int8 shiftCount;
+ uint32_t absA;
+ int8_t shiftCount;
uint64_t zSig0;
if ( a == 0 ) return packFloat128( 0, 0, 0, 0 );
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 int64_to_float32(int64_t a STATUS_PARAM)
+float32 int64_to_float32(int64_t a, float_status *status)
{
flag zSign;
- uint64 absA;
- int8 shiftCount;
+ uint64_t absA;
+ int8_t shiftCount;
if ( a == 0 ) return float32_zero;
zSign = ( a < 0 );
else {
absA <<= shiftCount;
}
- return roundAndPackFloat32( zSign, 0x9C - shiftCount, absA STATUS_VAR );
+ return roundAndPackFloat32(zSign, 0x9C - shiftCount, absA, status);
}
}
-float32 uint64_to_float32(uint64_t a STATUS_PARAM)
-{
- int8 shiftCount;
-
- if ( a == 0 ) return float32_zero;
- shiftCount = countLeadingZeros64( a ) - 40;
- if ( 0 <= shiftCount ) {
- return packFloat32(0, 0x95 - shiftCount, a<<shiftCount);
- }
- else {
- shiftCount += 7;
- if ( shiftCount < 0 ) {
- shift64RightJamming( a, - shiftCount, &a );
- }
- else {
- a <<= shiftCount;
- }
- return roundAndPackFloat32(0, 0x9C - shiftCount, a STATUS_VAR);
- }
-}
-
/*----------------------------------------------------------------------------
| Returns the result of converting the 64-bit two's complement integer `a'
| to the double-precision floating-point format. The conversion is performed
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 int64_to_float64(int64_t a STATUS_PARAM)
+float64 int64_to_float64(int64_t a, float_status *status)
{
flag zSign;
return packFloat64( 1, 0x43E, 0 );
}
zSign = ( a < 0 );
- return normalizeRoundAndPackFloat64( zSign, 0x43C, zSign ? - a : a STATUS_VAR );
-
-}
-
-float64 uint64_to_float64(uint64_t a STATUS_PARAM)
-{
- int exp = 0x43C;
-
- if (a == 0) {
- return float64_zero;
- }
- if ((int64_t)a < 0) {
- shift64RightJamming(a, 1, &a);
- exp += 1;
- }
- return normalizeRoundAndPackFloat64(0, exp, a STATUS_VAR);
+ return normalizeRoundAndPackFloat64(zSign, 0x43C, zSign ? -a : a, status);
}
/*----------------------------------------------------------------------------
| Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 int64_to_floatx80(int64_t a STATUS_PARAM)
+floatx80 int64_to_floatx80(int64_t a, float_status *status)
{
flag zSign;
- uint64 absA;
- int8 shiftCount;
+ uint64_t absA;
+ int8_t shiftCount;
if ( a == 0 ) return packFloatx80( 0, 0, 0 );
zSign = ( a < 0 );
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 int64_to_float128(int64_t a STATUS_PARAM)
+float128 int64_to_float128(int64_t a, float_status *status)
{
flag zSign;
- uint64 absA;
- int8 shiftCount;
- int32 zExp;
+ uint64_t absA;
+ int8_t shiftCount;
+ int32_t zExp;
uint64_t zSig0, zSig1;
if ( a == 0 ) return packFloat128( 0, 0, 0, 0 );
}
-float128 uint64_to_float128(uint64_t a STATUS_PARAM)
+/*----------------------------------------------------------------------------
+| Returns the result of converting the 64-bit unsigned integer `a'
+| to the single-precision floating-point format. The conversion is performed
+| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
+*----------------------------------------------------------------------------*/
+
+float32 uint64_to_float32(uint64_t a, float_status *status)
+{
+ int shiftcount;
+
+ if (a == 0) {
+ return float32_zero;
+ }
+
+ /* Determine (left) shift needed to put first set bit into bit posn 23
+ * (since packFloat32() expects the binary point between bits 23 and 22);
+ * this is the fast case for smallish numbers.
+ */
+ shiftcount = countLeadingZeros64(a) - 40;
+ if (shiftcount >= 0) {
+ return packFloat32(0, 0x95 - shiftcount, a << shiftcount);
+ }
+ /* Otherwise we need to do a round-and-pack. roundAndPackFloat32()
+ * expects the binary point between bits 30 and 29, hence the + 7.
+ */
+ shiftcount += 7;
+ if (shiftcount < 0) {
+ shift64RightJamming(a, -shiftcount, &a);
+ } else {
+ a <<= shiftcount;
+ }
+
+ return roundAndPackFloat32(0, 0x9c - shiftcount, a, status);
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the 64-bit unsigned integer `a'
+| to the double-precision floating-point format. The conversion is performed
+| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
+*----------------------------------------------------------------------------*/
+
+float64 uint64_to_float64(uint64_t a, float_status *status)
+{
+ int exp = 0x43C;
+ int shiftcount;
+
+ if (a == 0) {
+ return float64_zero;
+ }
+
+ shiftcount = countLeadingZeros64(a) - 1;
+ if (shiftcount < 0) {
+ shift64RightJamming(a, -shiftcount, &a);
+ } else {
+ a <<= shiftcount;
+ }
+ return roundAndPackFloat64(0, exp - shiftcount, a, status);
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the 64-bit unsigned integer `a'
+| to the quadruple-precision floating-point format. The conversion is performed
+| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
+*----------------------------------------------------------------------------*/
+
+float128 uint64_to_float128(uint64_t a, float_status *status)
{
if (a == 0) {
return float128_zero;
}
- return normalizeRoundAndPackFloat128(0, 0x406E, a, 0 STATUS_VAR);
+ return normalizeRoundAndPackFloat128(0, 0x406E, a, 0, status);
}
/*----------------------------------------------------------------------------
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int32 float32_to_int32( float32 a STATUS_PARAM )
+int32_t float32_to_int32(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
uint64_t aSig64;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
aSig64 = aSig;
aSig64 <<= 32;
if ( 0 < shiftCount ) shift64RightJamming( aSig64, shiftCount, &aSig64 );
- return roundAndPackInt32( aSign, aSig64 STATUS_VAR );
+ return roundAndPackInt32(aSign, aSig64, status);
}
| returned.
*----------------------------------------------------------------------------*/
-int32 float32_to_int32_round_to_zero( float32 a STATUS_PARAM )
+int32_t float32_to_int32_round_to_zero(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
int32_t z;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
shiftCount = aExp - 0x9E;
if ( 0 <= shiftCount ) {
if ( float32_val(a) != 0xCF000000 ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) return 0x7FFFFFFF;
}
return (int32_t) 0x80000000;
}
else if ( aExp <= 0x7E ) {
- if ( aExp | aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp | aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
aSig = ( aSig | 0x00800000 )<<8;
z = aSig>>( - shiftCount );
if ( (uint32_t) ( aSig<<( shiftCount & 31 ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
if ( aSign ) z = - z;
return z;
| returned.
*----------------------------------------------------------------------------*/
-int_fast16_t float32_to_int16_round_to_zero(float32 a STATUS_PARAM)
+int16_t float32_to_int16_round_to_zero(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
- int32 z;
+ int32_t z;
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
shiftCount = aExp - 0x8E;
if ( 0 <= shiftCount ) {
if ( float32_val(a) != 0xC7000000 ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
return 0x7FFF;
}
}
else if ( aExp <= 0x7E ) {
if ( aExp | aSig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return 0;
}
aSig = ( aSig | 0x00800000 )<<8;
z = aSig>>( - shiftCount );
if ( (uint32_t) ( aSig<<( shiftCount & 31 ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
if ( aSign ) {
z = - z;
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int64 float32_to_int64( float32 a STATUS_PARAM )
+int64_t float32_to_int64(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
uint64_t aSig64, aSigExtra;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
shiftCount = 0xBE - aExp;
if ( shiftCount < 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
return LIT64( 0x7FFFFFFFFFFFFFFF );
}
aSig64 = aSig;
aSig64 <<= 40;
shift64ExtraRightJamming( aSig64, 0, shiftCount, &aSig64, &aSigExtra );
- return roundAndPackInt64( aSign, aSig64, aSigExtra STATUS_VAR );
+ return roundAndPackInt64(aSign, aSig64, aSigExtra, status);
}
| raise the inexact exception flag.
*----------------------------------------------------------------------------*/
-uint64 float32_to_uint64(float32 a STATUS_PARAM)
+uint64_t float32_to_uint64(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
uint64_t aSig64, aSigExtra;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac(a);
aExp = extractFloat32Exp(a);
aSign = extractFloat32Sign(a);
if ((aSign) && (aExp > 126)) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if (float32_is_any_nan(a)) {
return LIT64(0xFFFFFFFFFFFFFFFF);
} else {
aSig |= 0x00800000;
}
if (shiftCount < 0) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return LIT64(0xFFFFFFFFFFFFFFFF);
}
aSig64 = aSig;
aSig64 <<= 40;
shift64ExtraRightJamming(aSig64, 0, shiftCount, &aSig64, &aSigExtra);
- return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR);
+ return roundAndPackUint64(aSign, aSig64, aSigExtra, status);
+}
+
+/*----------------------------------------------------------------------------
+| 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, except that the conversion is always rounded toward zero. 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 flag.
+*----------------------------------------------------------------------------*/
+
+uint64_t float32_to_uint64_round_to_zero(float32 a, float_status *status)
+{
+ signed char current_rounding_mode = status->float_rounding_mode;
+ set_float_rounding_mode(float_round_to_zero, status);
+ int64_t v = float32_to_uint64(a, status);
+ set_float_rounding_mode(current_rounding_mode, status);
+ return v;
}
/*----------------------------------------------------------------------------
| returned.
*----------------------------------------------------------------------------*/
-int64 float32_to_int64_round_to_zero( float32 a STATUS_PARAM )
+int64_t float32_to_int64_round_to_zero(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint32_t aSig;
uint64_t aSig64;
- int64 z;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ int64_t z;
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
shiftCount = aExp - 0xBE;
if ( 0 <= shiftCount ) {
if ( float32_val(a) != 0xDF000000 ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
return LIT64( 0x7FFFFFFFFFFFFFFF );
}
return (int64_t) LIT64( 0x8000000000000000 );
}
else if ( aExp <= 0x7E ) {
- if ( aExp | aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp | aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
aSig64 = aSig | 0x00800000;
aSig64 <<= 40;
z = aSig64>>( - shiftCount );
if ( (uint64_t) ( aSig64<<( shiftCount & 63 ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
if ( aSign ) z = - z;
return z;
| Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float32_to_float64( float32 a STATUS_PARAM )
+float64 float32_to_float64(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF ) {
- if ( aSig ) return commonNaNToFloat64( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloat64(float32ToCommonNaN(a, status), status);
+ }
return packFloat64( aSign, 0x7FF, 0 );
}
if ( aExp == 0 ) {
| Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 float32_to_floatx80( float32 a STATUS_PARAM )
+floatx80 float32_to_floatx80(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF ) {
- if ( aSig ) return commonNaNToFloatx80( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloatx80(float32ToCommonNaN(a, status), status);
+ }
return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( aExp == 0 ) {
| Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float32_to_float128( float32 a STATUS_PARAM )
+float128 float32_to_float128(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF ) {
- if ( aSig ) return commonNaNToFloat128( float32ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloat128(float32ToCommonNaN(a, status), status);
+ }
return packFloat128( aSign, 0x7FFF, 0, 0 );
}
if ( aExp == 0 ) {
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_round_to_int( float32 a STATUS_PARAM)
+float32 float32_round_to_int(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t lastBitMask, roundBitsMask;
uint32_t z;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aExp = extractFloat32Exp( a );
if ( 0x96 <= aExp ) {
if ( ( aExp == 0xFF ) && extractFloat32Frac( a ) ) {
- return propagateFloat32NaN( a, a STATUS_VAR );
+ return propagateFloat32NaN(a, a, status);
}
return a;
}
if ( aExp <= 0x7E ) {
if ( (uint32_t) ( float32_val(a)<<1 ) == 0 ) return a;
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
aSign = extractFloat32Sign( a );
- switch ( STATUS(float_rounding_mode) ) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
if ( ( aExp == 0x7E ) && extractFloat32Frac( a ) ) {
return packFloat32( aSign, 0x7F, 0 );
lastBitMask <<= 0x96 - aExp;
roundBitsMask = lastBitMask - 1;
z = float32_val(a);
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
z += lastBitMask>>1;
if ((z & roundBitsMask) == 0) {
abort();
}
z &= ~ roundBitsMask;
- if ( z != float32_val(a) ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (z != float32_val(a)) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return make_float32(z);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float32 addFloat32Sigs( float32 a, float32 b, flag zSign STATUS_PARAM)
+static float32 addFloat32Sigs(float32 a, float32 b, flag zSign,
+ float_status *status)
{
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint32_t aSig, bSig, zSig;
- int_fast16_t expDiff;
+ int expDiff;
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
bSig <<= 6;
if ( 0 < expDiff ) {
if ( aExp == 0xFF ) {
- if ( aSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
}
else if ( expDiff < 0 ) {
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return packFloat32( zSign, 0xFF, 0 );
}
if ( aExp == 0 ) {
}
else {
if ( aExp == 0xFF ) {
- if ( aSig | bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (aSig | bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return a;
}
if ( aExp == 0 ) {
- if (STATUS(flush_to_zero)) {
+ if (status->flush_to_zero) {
if (aSig | bSig) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ float_raise(float_flag_output_denormal, status);
}
return packFloat32(zSign, 0, 0);
}
++zExp;
}
roundAndPack:
- return roundAndPackFloat32( zSign, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(zSign, zExp, zSig, status);
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float32 subFloat32Sigs( float32 a, float32 b, flag zSign STATUS_PARAM)
+static float32 subFloat32Sigs(float32 a, float32 b, flag zSign,
+ float_status *status)
{
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint32_t aSig, bSig, zSig;
- int_fast16_t expDiff;
+ int expDiff;
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
if ( 0 < expDiff ) goto aExpBigger;
if ( expDiff < 0 ) goto bExpBigger;
if ( aExp == 0xFF ) {
- if ( aSig | bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ if (aSig | bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if ( aExp == 0 ) {
aExp = 1;
}
if ( bSig < aSig ) goto aBigger;
if ( aSig < bSig ) goto bBigger;
- return packFloat32( STATUS(float_rounding_mode) == float_round_down, 0, 0 );
+ return packFloat32(status->float_rounding_mode == float_round_down, 0, 0);
bExpBigger:
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return packFloat32( zSign ^ 1, 0xFF, 0 );
}
if ( aExp == 0 ) {
goto normalizeRoundAndPack;
aExpBigger:
if ( aExp == 0xFF ) {
- if ( aSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
zExp = aExp;
normalizeRoundAndPack:
--zExp;
- return normalizeRoundAndPackFloat32( zSign, zExp, zSig STATUS_VAR );
+ return normalizeRoundAndPackFloat32(zSign, zExp, zSig, status);
}
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_add( float32 a, float32 b STATUS_PARAM )
+float32 float32_add(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
aSign = extractFloat32Sign( a );
bSign = extractFloat32Sign( b );
if ( aSign == bSign ) {
- return addFloat32Sigs( a, b, aSign STATUS_VAR);
+ return addFloat32Sigs(a, b, aSign, status);
}
else {
- return subFloat32Sigs( a, b, aSign STATUS_VAR );
+ return subFloat32Sigs(a, b, aSign, status);
}
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_sub( float32 a, float32 b STATUS_PARAM )
+float32 float32_sub(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
aSign = extractFloat32Sign( a );
bSign = extractFloat32Sign( b );
if ( aSign == bSign ) {
- return subFloat32Sigs( a, b, aSign STATUS_VAR );
+ return subFloat32Sigs(a, b, aSign, status);
}
else {
- return addFloat32Sigs( a, b, aSign STATUS_VAR );
+ return addFloat32Sigs(a, b, aSign, status);
}
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_mul( float32 a, float32 b STATUS_PARAM )
+float32 float32_mul(float32 a, float32 b, float_status *status)
{
flag aSign, bSign, zSign;
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint32_t aSig, bSig;
uint64_t zSig64;
uint32_t zSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
zSign = aSign ^ bSign;
if ( aExp == 0xFF ) {
if ( aSig || ( ( bExp == 0xFF ) && bSig ) ) {
- return propagateFloat32NaN( a, b STATUS_VAR );
+ return propagateFloat32NaN(a, b, status);
}
if ( ( bExp | bSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
return packFloat32( zSign, 0xFF, 0 );
}
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
if ( ( aExp | aSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
return packFloat32( zSign, 0xFF, 0 );
}
zSig <<= 1;
--zExp;
}
- return roundAndPackFloat32( zSign, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(zSign, zExp, zSig, status);
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_div( float32 a, float32 b STATUS_PARAM )
+float32 float32_div(float32 a, float32 b, float_status *status)
{
flag aSign, bSign, zSign;
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint32_t aSig, bSig, zSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
bSign = extractFloat32Sign( b );
zSign = aSign ^ bSign;
if ( aExp == 0xFF ) {
- if ( aSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
return packFloat32( zSign, 0xFF, 0 );
}
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return packFloat32( zSign, 0, 0 );
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
if ( ( aExp | aSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
- float_raise( float_flag_divbyzero STATUS_VAR);
+ float_raise(float_flag_divbyzero, status);
return packFloat32( zSign, 0xFF, 0 );
}
normalizeFloat32Subnormal( bSig, &bExp, &bSig );
if ( ( zSig & 0x3F ) == 0 ) {
zSig |= ( (uint64_t) bSig * zSig != ( (uint64_t) aSig )<<32 );
}
- return roundAndPackFloat32( zSign, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(zSign, zExp, zSig, status);
}
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_rem( float32 a, float32 b STATUS_PARAM )
+float32 float32_rem(float32 a, float32 b, float_status *status)
{
flag aSign, zSign;
- int_fast16_t aExp, bExp, expDiff;
+ int aExp, bExp, expDiff;
uint32_t aSig, bSig;
uint32_t q;
uint64_t aSig64, bSig64, q64;
uint32_t alternateASig;
int32_t sigMean;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
bExp = extractFloat32Exp( b );
if ( aExp == 0xFF ) {
if ( aSig || ( ( bExp == 0xFF ) && bSig ) ) {
- return propagateFloat32NaN( a, b STATUS_VAR );
+ return propagateFloat32NaN(a, b, status);
}
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if ( bExp == 0xFF ) {
- if ( bSig ) return propagateFloat32NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat32NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
normalizeFloat32Subnormal( bSig, &bExp, &bSig );
}
}
zSign = ( (int32_t) aSig < 0 );
if ( zSign ) aSig = - aSig;
- return normalizeRoundAndPackFloat32( aSign ^ zSign, bExp, aSig STATUS_VAR );
-
+ return normalizeRoundAndPackFloat32(aSign ^ zSign, bExp, aSig, status);
}
/*----------------------------------------------------------------------------
| externally will flip the sign bit on NaNs.)
*----------------------------------------------------------------------------*/
-float32 float32_muladd(float32 a, float32 b, float32 c, int flags STATUS_PARAM)
+float32 float32_muladd(float32 a, float32 b, float32 c, int flags,
+ float_status *status)
{
flag aSign, bSign, cSign, zSign;
- int_fast16_t aExp, bExp, cExp, pExp, zExp, expDiff;
+ int aExp, bExp, cExp, pExp, zExp, expDiff;
uint32_t aSig, bSig, cSig;
flag pInf, pZero, pSign;
uint64_t pSig64, cSig64, zSig64;
int shiftcount;
flag signflip, infzero;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
- c = float32_squash_input_denormal(c STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
+ c = float32_squash_input_denormal(c, status);
aSig = extractFloat32Frac(a);
aExp = extractFloat32Exp(a);
aSign = extractFloat32Sign(a);
if (((aExp == 0xff) && aSig) ||
((bExp == 0xff) && bSig) ||
((cExp == 0xff) && cSig)) {
- return propagateFloat32MulAddNaN(a, b, c, infzero STATUS_VAR);
+ return propagateFloat32MulAddNaN(a, b, c, infzero, status);
}
if (infzero) {
- float_raise(float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if (flags & float_muladd_negate_c) {
if (cExp == 0xff) {
if (pInf && (pSign ^ cSign)) {
/* addition of opposite-signed infinities => InvalidOperation */
- float_raise(float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
/* Otherwise generate an infinity of the same sign */
return packFloat32(cSign ^ signflip, 0xff, 0);
/* Adding two exact zeroes */
if (pSign == cSign) {
zSign = pSign;
- } else if (STATUS(float_rounding_mode) == float_round_down) {
+ } else if (status->float_rounding_mode == float_round_down) {
zSign = 1;
} else {
zSign = 0;
return packFloat32(zSign ^ signflip, 0, 0);
}
/* Exact zero plus a denorm */
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloat32(cSign ^ signflip, 0, 0);
}
}
/* Zero plus something non-zero : just return the something */
+ if (flags & float_muladd_halve_result) {
+ if (cExp == 0) {
+ normalizeFloat32Subnormal(cSig, &cExp, &cSig);
+ }
+ /* Subtract one to halve, and one again because roundAndPackFloat32
+ * wants one less than the true exponent.
+ */
+ cExp -= 2;
+ cSig = (cSig | 0x00800000) << 7;
+ return roundAndPackFloat32(cSign ^ signflip, cExp, cSig, status);
+ }
return packFloat32(cSign ^ signflip, cExp, cSig);
}
/* Throw out the special case of c being an exact zero now */
shift64RightJamming(pSig64, 32, &pSig64);
pSig = pSig64;
+ if (flags & float_muladd_halve_result) {
+ pExp--;
+ }
return roundAndPackFloat32(zSign, pExp - 1,
- pSig STATUS_VAR);
+ pSig, status);
}
normalizeFloat32Subnormal(cSig, &cExp, &cSig);
}
} else {
/* Exact zero */
zSign = signflip;
- if (STATUS(float_rounding_mode) == float_round_down) {
+ if (status->float_rounding_mode == float_round_down) {
zSign ^= 1;
}
return packFloat32(zSign, 0, 0);
zSig64 <<= shiftcount;
zExp -= shiftcount;
}
+ if (flags & float_muladd_halve_result) {
+ zExp--;
+ }
+
shift64RightJamming(zSig64, 32, &zSig64);
- return roundAndPackFloat32(zSign, zExp, zSig64 STATUS_VAR);
+ return roundAndPackFloat32(zSign, zExp, zSig64, status);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_sqrt( float32 a STATUS_PARAM )
+float32 float32_sqrt(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, zExp;
+ int aExp, zExp;
uint32_t aSig, zSig;
uint64_t rem, term;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF ) {
- if ( aSig ) return propagateFloat32NaN( a, float32_zero STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, float32_zero, status);
+ }
if ( ! aSign ) return a;
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if ( aSign ) {
if ( ( aExp | aSig ) == 0 ) return a;
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if ( aExp == 0 ) {
if ( aSig == 0 ) return float32_zero;
}
shift32RightJamming( zSig, 1, &zSig );
roundAndPack:
- return roundAndPackFloat32( 0, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(0, zExp, zSig, status);
}
const_float64( 0x3d6ae7f3e733b81fll ), /* 15 */
};
-float32 float32_exp2( float32 a STATUS_PARAM )
+float32 float32_exp2(float32 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
float64 r, x, xn;
int i;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF) {
- if ( aSig ) return propagateFloat32NaN( a, float32_zero STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, float32_zero, status);
+ }
return (aSign) ? float32_zero : a;
}
if (aExp == 0) {
if (aSig == 0) return float32_one;
}
- float_raise( float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_inexact, status);
/* ******************************* */
/* using float64 for approximation */
/* ******************************* */
- x = float32_to_float64(a STATUS_VAR);
- x = float64_mul(x, float64_ln2 STATUS_VAR);
+ x = float32_to_float64(a, status);
+ x = float64_mul(x, float64_ln2, status);
xn = x;
r = float64_one;
for (i = 0 ; i < 15 ; i++) {
float64 f;
- f = float64_mul(xn, float32_exp2_coefficients[i] STATUS_VAR);
- r = float64_add(r, f STATUS_VAR);
+ f = float64_mul(xn, float32_exp2_coefficients[i], status);
+ r = float64_add(r, f, status);
- xn = float64_mul(xn, x STATUS_VAR);
+ xn = float64_mul(xn, x, status);
}
return float64_to_float32(r, status);
| The operation is performed according to the IEC/IEEE Standard for Binary
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float32_log2( float32 a STATUS_PARAM )
+float32 float32_log2(float32 a, float_status *status)
{
flag aSign, zSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig, zSig, i;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
normalizeFloat32Subnormal( aSig, &aExp, &aSig );
}
if ( aSign ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float32_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
}
if ( aExp == 0xFF ) {
- if ( aSig ) return propagateFloat32NaN( a, float32_zero STATUS_VAR );
+ if (aSig) {
+ return propagateFloat32NaN(a, float32_zero, status);
+ }
return a;
}
if ( zSign )
zSig = -zSig;
- return normalizeRoundAndPackFloat32( zSign, 0x85, zSig STATUS_VAR );
+ return normalizeRoundAndPackFloat32(zSign, 0x85, zSig, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_eq( float32 a, float32 b STATUS_PARAM )
+int float32_eq(float32 a, float32 b, float_status *status)
{
uint32_t av, bv;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
av = float32_val(a);
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_le( float32 a, float32 b STATUS_PARAM )
+int float32_le(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
uint32_t av, bv;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat32Sign( a );
| to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_lt( float32 a, float32 b STATUS_PARAM )
+int float32_lt(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
uint32_t av, bv;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat32Sign( a );
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_unordered( float32 a, float32 b STATUS_PARAM )
+int float32_unordered(float32 a, float32 b, float_status *status)
{
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 1;
}
return 0;
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_eq_quiet( float32 a, float32 b STATUS_PARAM )
+int float32_eq_quiet(float32 a, float32 b, float_status *status)
{
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- if ( float32_is_signaling_nan( a ) || float32_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float32_is_signaling_nan(a, status)
+ || float32_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_le_quiet( float32 a, float32 b STATUS_PARAM )
+int float32_le_quiet(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
uint32_t av, bv;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- if ( float32_is_signaling_nan( a ) || float32_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float32_is_signaling_nan(a, status)
+ || float32_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_lt_quiet( float32 a, float32 b STATUS_PARAM )
+int float32_lt_quiet(float32 a, float32 b, float_status *status)
{
flag aSign, bSign;
uint32_t av, bv;
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- if ( float32_is_signaling_nan( a ) || float32_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float32_is_signaling_nan(a, status)
+ || float32_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float32_unordered_quiet( float32 a, float32 b STATUS_PARAM )
+int float32_unordered_quiet(float32 a, float32 b, float_status *status)
{
- a = float32_squash_input_denormal(a STATUS_VAR);
- b = float32_squash_input_denormal(b STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
+ b = float32_squash_input_denormal(b, status);
if ( ( ( extractFloat32Exp( a ) == 0xFF ) && extractFloat32Frac( a ) )
|| ( ( extractFloat32Exp( b ) == 0xFF ) && extractFloat32Frac( b ) )
) {
- if ( float32_is_signaling_nan( a ) || float32_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float32_is_signaling_nan(a, status)
+ || float32_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 1;
}
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int32 float64_to_int32( float64 a STATUS_PARAM )
+int32_t float64_to_int32(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
if ( aExp ) aSig |= LIT64( 0x0010000000000000 );
shiftCount = 0x42C - aExp;
if ( 0 < shiftCount ) shift64RightJamming( aSig, shiftCount, &aSig );
- return roundAndPackInt32( aSign, aSig STATUS_VAR );
+ return roundAndPackInt32(aSign, aSig, status);
}
| returned.
*----------------------------------------------------------------------------*/
-int32 float64_to_int32_round_to_zero( float64 a STATUS_PARAM )
+int32_t float64_to_int32_round_to_zero(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig, savedASig;
int32_t z;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
goto invalid;
}
else if ( aExp < 0x3FF ) {
- if ( aExp || aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp || aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
aSig |= LIT64( 0x0010000000000000 );
if ( aSign ) z = - z;
if ( ( z < 0 ) ^ aSign ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF;
}
if ( ( aSig<<shiftCount ) != savedASig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return z;
| returned.
*----------------------------------------------------------------------------*/
-int_fast16_t float64_to_int16_round_to_zero(float64 a STATUS_PARAM)
+int16_t float64_to_int16_round_to_zero(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig, savedASig;
- int32 z;
+ int32_t z;
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
}
else if ( aExp < 0x3FF ) {
if ( aExp || aSig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return 0;
}
}
if ( ( (int16_t)z < 0 ) ^ aSign ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return aSign ? (int32_t) 0xffff8000 : 0x7FFF;
}
if ( ( aSig<<shiftCount ) != savedASig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return z;
}
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int64 float64_to_int64( float64 a STATUS_PARAM )
+int64_t float64_to_int64(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig, aSigExtra;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
shiftCount = 0x433 - aExp;
if ( shiftCount <= 0 ) {
if ( 0x43E < aExp ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign
|| ( ( aExp == 0x7FF )
&& ( aSig != LIT64( 0x0010000000000000 ) ) )
else {
shift64ExtraRightJamming( aSig, 0, shiftCount, &aSig, &aSigExtra );
}
- return roundAndPackInt64( aSign, aSig, aSigExtra STATUS_VAR );
+ return roundAndPackInt64(aSign, aSig, aSigExtra, status);
}
| returned.
*----------------------------------------------------------------------------*/
-int64 float64_to_int64_round_to_zero( float64 a STATUS_PARAM )
+int64_t float64_to_int64_round_to_zero(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig;
- int64 z;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ int64_t z;
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
if ( 0 <= shiftCount ) {
if ( 0x43E <= aExp ) {
if ( float64_val(a) != LIT64( 0xC3E0000000000000 ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign
|| ( ( aExp == 0x7FF )
&& ( aSig != LIT64( 0x0010000000000000 ) ) )
}
else {
if ( aExp < 0x3FE ) {
- if ( aExp | aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp | aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
z = aSig>>( - shiftCount );
if ( (uint64_t) ( aSig<<( shiftCount & 63 ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
}
if ( aSign ) z = - z;
| Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float64_to_float32( float64 a STATUS_PARAM )
+float32 float64_to_float32(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig;
uint32_t zSig;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
if ( aExp == 0x7FF ) {
- if ( aSig ) return commonNaNToFloat32( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloat32(float64ToCommonNaN(a, status), status);
+ }
return packFloat32( aSign, 0xFF, 0 );
}
shift64RightJamming( aSig, 22, &aSig );
zSig |= 0x40000000;
aExp -= 0x381;
}
- return roundAndPackFloat32( aSign, aExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(aSign, aExp, zSig, status);
}
| than the desired result exponent whenever `zSig' is a complete, normalized
| significand.
*----------------------------------------------------------------------------*/
-static float16 packFloat16(flag zSign, int_fast16_t zExp, uint16_t zSig)
+static float16 packFloat16(flag zSign, int zExp, uint16_t zSig)
{
return make_float16(
(((uint32_t)zSign) << 15) + (((uint32_t)zExp) << 10) + zSig);
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float32 roundAndPackFloat16(flag zSign, int_fast16_t zExp,
- uint32_t zSig, flag ieee STATUS_PARAM)
+static float16 roundAndPackFloat16(flag zSign, int zExp,
+ uint32_t zSig, flag ieee,
+ float_status *status)
{
int maxexp = ieee ? 29 : 30;
uint32_t mask;
mask = 0x00001fff;
}
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
increment = (mask + 1) >> 1;
if ((zSig & mask) == increment) {
if (zExp > maxexp || (zExp == maxexp && rounding_bumps_exp)) {
if (ieee) {
- float_raise(float_flag_overflow | float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_overflow | float_flag_inexact, status);
return packFloat16(zSign, 0x1f, 0);
} else {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return packFloat16(zSign, 0x1f, 0x3ff);
}
}
if (zExp < 0) {
/* Note that flush-to-zero does not affect half-precision results */
is_tiny =
- (STATUS(float_detect_tininess) == float_tininess_before_rounding)
+ (status->float_detect_tininess == float_tininess_before_rounding)
|| (zExp < -1)
|| (!rounding_bumps_exp);
}
if (zSig & mask) {
- float_raise(float_flag_inexact STATUS_VAR);
+ float_raise(float_flag_inexact, status);
if (is_tiny) {
- float_raise(float_flag_underflow STATUS_VAR);
+ float_raise(float_flag_underflow, status);
}
}
return packFloat16(zSign, zExp, zSig >> 13);
}
-static void normalizeFloat16Subnormal(uint32_t aSig, int_fast16_t *zExpPtr,
+static void normalizeFloat16Subnormal(uint32_t aSig, int *zExpPtr,
uint32_t *zSigPtr)
{
int8_t shiftCount = countLeadingZeros32(aSig) - 21;
/* Half precision floats come in two formats: standard IEEE and "ARM" format.
The latter gains extra exponent range by omitting the NaN/Inf encodings. */
-float32 float16_to_float32(float16 a, flag ieee STATUS_PARAM)
+float32 float16_to_float32(float16 a, flag ieee, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
aSign = extractFloat16Sign(a);
if (aExp == 0x1f && ieee) {
if (aSig) {
- return commonNaNToFloat32(float16ToCommonNaN(a STATUS_VAR) STATUS_VAR);
+ return commonNaNToFloat32(float16ToCommonNaN(a, status), status);
}
return packFloat32(aSign, 0xff, 0);
}
return packFloat32( aSign, aExp + 0x70, aSig << 13);
}
-float16 float32_to_float16(float32 a, flag ieee STATUS_PARAM)
+float16 float32_to_float16(float32 a, flag ieee, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
if (aSig) {
/* Input is a NaN */
if (!ieee) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return packFloat16(aSign, 0, 0);
}
return commonNaNToFloat16(
- float32ToCommonNaN(a STATUS_VAR) STATUS_VAR);
+ float32ToCommonNaN(a, status), status);
}
/* Infinity */
if (!ieee) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return packFloat16(aSign, 0x1f, 0x3ff);
}
return packFloat16(aSign, 0x1f, 0);
aSig |= 0x00800000;
aExp -= 0x71;
- return roundAndPackFloat16(aSign, aExp, aSig, ieee STATUS_VAR);
+ return roundAndPackFloat16(aSign, aExp, aSig, ieee, status);
}
-float64 float16_to_float64(float16 a, flag ieee STATUS_PARAM)
+float64 float16_to_float64(float16 a, flag ieee, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint32_t aSig;
aSign = extractFloat16Sign(a);
if (aExp == 0x1f && ieee) {
if (aSig) {
return commonNaNToFloat64(
- float16ToCommonNaN(a STATUS_VAR) STATUS_VAR);
+ float16ToCommonNaN(a, status), status);
}
return packFloat64(aSign, 0x7ff, 0);
}
return packFloat64(aSign, aExp + 0x3f0, ((uint64_t)aSig) << 42);
}
-float16 float64_to_float16(float64 a, flag ieee STATUS_PARAM)
+float16 float64_to_float16(float64 a, flag ieee, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig;
uint32_t zSig;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac(a);
aExp = extractFloat64Exp(a);
if (aSig) {
/* Input is a NaN */
if (!ieee) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return packFloat16(aSign, 0, 0);
}
return commonNaNToFloat16(
- float64ToCommonNaN(a STATUS_VAR) STATUS_VAR);
+ float64ToCommonNaN(a, status), status);
}
/* Infinity */
if (!ieee) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return packFloat16(aSign, 0x1f, 0x3ff);
}
return packFloat16(aSign, 0x1f, 0);
zSig |= 0x00800000;
aExp -= 0x3F1;
- return roundAndPackFloat16(aSign, aExp, zSig, ieee STATUS_VAR);
+ return roundAndPackFloat16(aSign, aExp, zSig, ieee, status);
}
/*----------------------------------------------------------------------------
| Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 float64_to_floatx80( float64 a STATUS_PARAM )
+floatx80 float64_to_floatx80(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
if ( aExp == 0x7FF ) {
- if ( aSig ) return commonNaNToFloatx80( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloatx80(float64ToCommonNaN(a, status), status);
+ }
return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( aExp == 0 ) {
| Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float64_to_float128( float64 a STATUS_PARAM )
+float128 float64_to_float128(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig, zSig0, zSig1;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
if ( aExp == 0x7FF ) {
- if ( aSig ) return commonNaNToFloat128( float64ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ if (aSig) {
+ return commonNaNToFloat128(float64ToCommonNaN(a, status), status);
+ }
return packFloat128( aSign, 0x7FFF, 0, 0 );
}
if ( aExp == 0 ) {
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_round_to_int( float64 a STATUS_PARAM )
+float64 float64_round_to_int(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t lastBitMask, roundBitsMask;
uint64_t z;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aExp = extractFloat64Exp( a );
if ( 0x433 <= aExp ) {
if ( ( aExp == 0x7FF ) && extractFloat64Frac( a ) ) {
- return propagateFloat64NaN( a, a STATUS_VAR );
+ return propagateFloat64NaN(a, a, status);
}
return a;
}
if ( aExp < 0x3FF ) {
if ( (uint64_t) ( float64_val(a)<<1 ) == 0 ) return a;
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
aSign = extractFloat64Sign( a );
- switch ( STATUS(float_rounding_mode) ) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
if ( ( aExp == 0x3FE ) && extractFloat64Frac( a ) ) {
return packFloat64( aSign, 0x3FF, 0 );
lastBitMask <<= 0x433 - aExp;
roundBitsMask = lastBitMask - 1;
z = float64_val(a);
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
z += lastBitMask >> 1;
if ((z & roundBitsMask) == 0) {
abort();
}
z &= ~ roundBitsMask;
- if ( z != float64_val(a) )
- STATUS(float_exception_flags) |= float_flag_inexact;
+ if (z != float64_val(a)) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return make_float64(z);
}
-float64 float64_trunc_to_int( float64 a STATUS_PARAM)
+float64 float64_trunc_to_int(float64 a, float_status *status)
{
int oldmode;
float64 res;
- oldmode = STATUS(float_rounding_mode);
- STATUS(float_rounding_mode) = float_round_to_zero;
- res = float64_round_to_int(a STATUS_VAR);
- STATUS(float_rounding_mode) = oldmode;
+ oldmode = status->float_rounding_mode;
+ status->float_rounding_mode = float_round_to_zero;
+ res = float64_round_to_int(a, status);
+ status->float_rounding_mode = oldmode;
return res;
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float64 addFloat64Sigs( float64 a, float64 b, flag zSign STATUS_PARAM )
+static float64 addFloat64Sigs(float64 a, float64 b, flag zSign,
+ float_status *status)
{
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint64_t aSig, bSig, zSig;
- int_fast16_t expDiff;
+ int expDiff;
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
bSig <<= 9;
if ( 0 < expDiff ) {
if ( aExp == 0x7FF ) {
- if ( aSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
}
else if ( expDiff < 0 ) {
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return packFloat64( zSign, 0x7FF, 0 );
}
if ( aExp == 0 ) {
}
else {
if ( aExp == 0x7FF ) {
- if ( aSig | bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (aSig | bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return a;
}
if ( aExp == 0 ) {
- if (STATUS(flush_to_zero)) {
+ if (status->flush_to_zero) {
if (aSig | bSig) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ float_raise(float_flag_output_denormal, status);
}
return packFloat64(zSign, 0, 0);
}
++zExp;
}
roundAndPack:
- return roundAndPackFloat64( zSign, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat64(zSign, zExp, zSig, status);
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float64 subFloat64Sigs( float64 a, float64 b, flag zSign STATUS_PARAM )
+static float64 subFloat64Sigs(float64 a, float64 b, flag zSign,
+ float_status *status)
{
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint64_t aSig, bSig, zSig;
- int_fast16_t expDiff;
+ int expDiff;
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
if ( 0 < expDiff ) goto aExpBigger;
if ( expDiff < 0 ) goto bExpBigger;
if ( aExp == 0x7FF ) {
- if ( aSig | bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ if (aSig | bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if ( aExp == 0 ) {
aExp = 1;
}
if ( bSig < aSig ) goto aBigger;
if ( aSig < bSig ) goto bBigger;
- return packFloat64( STATUS(float_rounding_mode) == float_round_down, 0, 0 );
+ return packFloat64(status->float_rounding_mode == float_round_down, 0, 0);
bExpBigger:
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return packFloat64( zSign ^ 1, 0x7FF, 0 );
}
if ( aExp == 0 ) {
goto normalizeRoundAndPack;
aExpBigger:
if ( aExp == 0x7FF ) {
- if ( aSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
zExp = aExp;
normalizeRoundAndPack:
--zExp;
- return normalizeRoundAndPackFloat64( zSign, zExp, zSig STATUS_VAR );
+ return normalizeRoundAndPackFloat64(zSign, zExp, zSig, status);
}
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_add( float64 a, float64 b STATUS_PARAM )
+float64 float64_add(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
aSign = extractFloat64Sign( a );
bSign = extractFloat64Sign( b );
if ( aSign == bSign ) {
- return addFloat64Sigs( a, b, aSign STATUS_VAR );
+ return addFloat64Sigs(a, b, aSign, status);
}
else {
- return subFloat64Sigs( a, b, aSign STATUS_VAR );
+ return subFloat64Sigs(a, b, aSign, status);
}
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_sub( float64 a, float64 b STATUS_PARAM )
+float64 float64_sub(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
aSign = extractFloat64Sign( a );
bSign = extractFloat64Sign( b );
if ( aSign == bSign ) {
- return subFloat64Sigs( a, b, aSign STATUS_VAR );
+ return subFloat64Sigs(a, b, aSign, status);
}
else {
- return addFloat64Sigs( a, b, aSign STATUS_VAR );
+ return addFloat64Sigs(a, b, aSign, status);
}
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_mul( float64 a, float64 b STATUS_PARAM )
+float64 float64_mul(float64 a, float64 b, float_status *status)
{
flag aSign, bSign, zSign;
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint64_t aSig, bSig, zSig0, zSig1;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
zSign = aSign ^ bSign;
if ( aExp == 0x7FF ) {
if ( aSig || ( ( bExp == 0x7FF ) && bSig ) ) {
- return propagateFloat64NaN( a, b STATUS_VAR );
+ return propagateFloat64NaN(a, b, status);
}
if ( ( bExp | bSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
return packFloat64( zSign, 0x7FF, 0 );
}
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
if ( ( aExp | aSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
return packFloat64( zSign, 0x7FF, 0 );
}
zSig0 <<= 1;
--zExp;
}
- return roundAndPackFloat64( zSign, zExp, zSig0 STATUS_VAR );
+ return roundAndPackFloat64(zSign, zExp, zSig0, status);
}
| the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_div( float64 a, float64 b STATUS_PARAM )
+float64 float64_div(float64 a, float64 b, float_status *status)
{
flag aSign, bSign, zSign;
- int_fast16_t aExp, bExp, zExp;
+ int aExp, bExp, zExp;
uint64_t aSig, bSig, zSig;
uint64_t rem0, rem1;
uint64_t term0, term1;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
bSign = extractFloat64Sign( b );
zSign = aSign ^ bSign;
if ( aExp == 0x7FF ) {
- if ( aSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (aSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
return packFloat64( zSign, 0x7FF, 0 );
}
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return packFloat64( zSign, 0, 0 );
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
if ( ( aExp | aSig ) == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
- float_raise( float_flag_divbyzero STATUS_VAR);
+ float_raise(float_flag_divbyzero, status);
return packFloat64( zSign, 0x7FF, 0 );
}
normalizeFloat64Subnormal( bSig, &bExp, &bSig );
}
zSig |= ( rem1 != 0 );
}
- return roundAndPackFloat64( zSign, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat64(zSign, zExp, zSig, status);
}
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_rem( float64 a, float64 b STATUS_PARAM )
+float64 float64_rem(float64 a, float64 b, float_status *status)
{
flag aSign, zSign;
- int_fast16_t aExp, bExp, expDiff;
+ int aExp, bExp, expDiff;
uint64_t aSig, bSig;
uint64_t q, alternateASig;
int64_t sigMean;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
bExp = extractFloat64Exp( b );
if ( aExp == 0x7FF ) {
if ( aSig || ( ( bExp == 0x7FF ) && bSig ) ) {
- return propagateFloat64NaN( a, b STATUS_VAR );
+ return propagateFloat64NaN(a, b, status);
}
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if ( bExp == 0x7FF ) {
- if ( bSig ) return propagateFloat64NaN( a, b STATUS_VAR );
+ if (bSig) {
+ return propagateFloat64NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
normalizeFloat64Subnormal( bSig, &bExp, &bSig );
}
}
zSign = ( (int64_t) aSig < 0 );
if ( zSign ) aSig = - aSig;
- return normalizeRoundAndPackFloat64( aSign ^ zSign, bExp, aSig STATUS_VAR );
+ return normalizeRoundAndPackFloat64(aSign ^ zSign, bExp, aSig, status);
}
| externally will flip the sign bit on NaNs.)
*----------------------------------------------------------------------------*/
-float64 float64_muladd(float64 a, float64 b, float64 c, int flags STATUS_PARAM)
+float64 float64_muladd(float64 a, float64 b, float64 c, int flags,
+ float_status *status)
{
flag aSign, bSign, cSign, zSign;
- int_fast16_t aExp, bExp, cExp, pExp, zExp, expDiff;
+ int aExp, bExp, cExp, pExp, zExp, expDiff;
uint64_t aSig, bSig, cSig;
flag pInf, pZero, pSign;
uint64_t pSig0, pSig1, cSig0, cSig1, zSig0, zSig1;
int shiftcount;
flag signflip, infzero;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
- c = float64_squash_input_denormal(c STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
+ c = float64_squash_input_denormal(c, status);
aSig = extractFloat64Frac(a);
aExp = extractFloat64Exp(a);
aSign = extractFloat64Sign(a);
if (((aExp == 0x7ff) && aSig) ||
((bExp == 0x7ff) && bSig) ||
((cExp == 0x7ff) && cSig)) {
- return propagateFloat64MulAddNaN(a, b, c, infzero STATUS_VAR);
+ return propagateFloat64MulAddNaN(a, b, c, infzero, status);
}
if (infzero) {
- float_raise(float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if (flags & float_muladd_negate_c) {
if (cExp == 0x7ff) {
if (pInf && (pSign ^ cSign)) {
/* addition of opposite-signed infinities => InvalidOperation */
- float_raise(float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
/* Otherwise generate an infinity of the same sign */
return packFloat64(cSign ^ signflip, 0x7ff, 0);
/* Adding two exact zeroes */
if (pSign == cSign) {
zSign = pSign;
- } else if (STATUS(float_rounding_mode) == float_round_down) {
+ } else if (status->float_rounding_mode == float_round_down) {
zSign = 1;
} else {
zSign = 0;
return packFloat64(zSign ^ signflip, 0, 0);
}
/* Exact zero plus a denorm */
- if (STATUS(flush_to_zero)) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ if (status->flush_to_zero) {
+ float_raise(float_flag_output_denormal, status);
return packFloat64(cSign ^ signflip, 0, 0);
}
}
/* Zero plus something non-zero : just return the something */
+ if (flags & float_muladd_halve_result) {
+ if (cExp == 0) {
+ normalizeFloat64Subnormal(cSig, &cExp, &cSig);
+ }
+ /* Subtract one to halve, and one again because roundAndPackFloat64
+ * wants one less than the true exponent.
+ */
+ cExp -= 2;
+ cSig = (cSig | 0x0010000000000000ULL) << 10;
+ return roundAndPackFloat64(cSign ^ signflip, cExp, cSig, status);
+ }
return packFloat64(cSign ^ signflip, cExp, cSig);
}
if (!cSig) {
/* Throw out the special case of c being an exact zero now */
shift128RightJamming(pSig0, pSig1, 64, &pSig0, &pSig1);
+ if (flags & float_muladd_halve_result) {
+ pExp--;
+ }
return roundAndPackFloat64(zSign, pExp - 1,
- pSig1 STATUS_VAR);
+ pSig1, status);
}
normalizeFloat64Subnormal(cSig, &cExp, &cSig);
}
zExp--;
}
shift128RightJamming(zSig0, zSig1, 64, &zSig0, &zSig1);
- return roundAndPackFloat64(zSign, zExp, zSig1 STATUS_VAR);
+ if (flags & float_muladd_halve_result) {
+ zExp--;
+ }
+ return roundAndPackFloat64(zSign, zExp, zSig1, status);
} else {
/* Subtraction */
if (expDiff > 0) {
} else {
/* Exact zero */
zSign = signflip;
- if (STATUS(float_rounding_mode) == float_round_down) {
+ if (status->float_rounding_mode == float_round_down) {
zSign ^= 1;
}
return packFloat64(zSign, 0, 0);
zExp -= (shiftcount + 64);
}
}
- return roundAndPackFloat64(zSign, zExp, zSig0 STATUS_VAR);
+ if (flags & float_muladd_halve_result) {
+ zExp--;
+ }
+ return roundAndPackFloat64(zSign, zExp, zSig0, status);
}
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_sqrt( float64 a STATUS_PARAM )
+float64 float64_sqrt(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, zExp;
+ int aExp, zExp;
uint64_t aSig, zSig, doubleZSig;
uint64_t rem0, rem1, term0, term1;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
if ( aExp == 0x7FF ) {
- if ( aSig ) return propagateFloat64NaN( a, a STATUS_VAR );
+ if (aSig) {
+ return propagateFloat64NaN(a, a, status);
+ }
if ( ! aSign ) return a;
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if ( aSign ) {
if ( ( aExp | aSig ) == 0 ) return a;
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if ( aExp == 0 ) {
if ( aSig == 0 ) return float64_zero;
}
zSig |= ( ( rem0 | rem1 ) != 0 );
}
- return roundAndPackFloat64( 0, zExp, zSig STATUS_VAR );
+ return roundAndPackFloat64(0, zExp, zSig, status);
}
| The operation is performed according to the IEC/IEEE Standard for Binary
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float64_log2( float64 a STATUS_PARAM )
+float64 float64_log2(float64 a, float_status *status)
{
flag aSign, zSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig, aSig0, aSig1, zSig, i;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
normalizeFloat64Subnormal( aSig, &aExp, &aSig );
}
if ( aSign ) {
- float_raise( float_flag_invalid STATUS_VAR);
- return float64_default_nan;
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
}
if ( aExp == 0x7FF ) {
- if ( aSig ) return propagateFloat64NaN( a, float64_zero STATUS_VAR );
+ if (aSig) {
+ return propagateFloat64NaN(a, float64_zero, status);
+ }
return a;
}
if ( zSign )
zSig = -zSig;
- return normalizeRoundAndPackFloat64( zSign, 0x408, zSig STATUS_VAR );
+ return normalizeRoundAndPackFloat64(zSign, 0x408, zSig, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_eq( float64 a, float64 b STATUS_PARAM )
+int float64_eq(float64 a, float64 b, float_status *status)
{
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
av = float64_val(a);
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_le( float64 a, float64 b STATUS_PARAM )
+int float64_le(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat64Sign( a );
| to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_lt( float64 a, float64 b STATUS_PARAM )
+int float64_lt(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat64Sign( a );
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_unordered( float64 a, float64 b STATUS_PARAM )
+int float64_unordered(float64 a, float64 b, float_status *status)
{
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 1;
}
return 0;
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_eq_quiet( float64 a, float64 b STATUS_PARAM )
+int float64_eq_quiet(float64 a, float64 b, float_status *status)
{
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- if ( float64_is_signaling_nan( a ) || float64_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float64_is_signaling_nan(a, status)
+ || float64_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_le_quiet( float64 a, float64 b STATUS_PARAM )
+int float64_le_quiet(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- if ( float64_is_signaling_nan( a ) || float64_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float64_is_signaling_nan(a, status)
+ || float64_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_lt_quiet( float64 a, float64 b STATUS_PARAM )
+int float64_lt_quiet(float64 a, float64 b, float_status *status)
{
flag aSign, bSign;
uint64_t av, bv;
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- if ( float64_is_signaling_nan( a ) || float64_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float64_is_signaling_nan(a, status)
+ || float64_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float64_unordered_quiet( float64 a, float64 b STATUS_PARAM )
+int float64_unordered_quiet(float64 a, float64 b, float_status *status)
{
- a = float64_squash_input_denormal(a STATUS_VAR);
- b = float64_squash_input_denormal(b STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
+ b = float64_squash_input_denormal(b, status);
if ( ( ( extractFloat64Exp( a ) == 0x7FF ) && extractFloat64Frac( a ) )
|| ( ( extractFloat64Exp( b ) == 0x7FF ) && extractFloat64Frac( b ) )
) {
- if ( float64_is_signaling_nan( a ) || float64_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float64_is_signaling_nan(a, status)
+ || float64_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 1;
}
| overflows, the largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int32 floatx80_to_int32( floatx80 a STATUS_PARAM )
+int32_t floatx80_to_int32(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return 1 << 31;
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
shiftCount = 0x4037 - aExp;
if ( shiftCount <= 0 ) shiftCount = 1;
shift64RightJamming( aSig, shiftCount, &aSig );
- return roundAndPackInt32( aSign, aSig STATUS_VAR );
+ return roundAndPackInt32(aSign, aSig, status);
}
| sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int32 floatx80_to_int32_round_to_zero( floatx80 a STATUS_PARAM )
+int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig, savedASig;
int32_t z;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return 1 << 31;
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
goto invalid;
}
else if ( aExp < 0x3FFF ) {
- if ( aExp || aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp || aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
shiftCount = 0x403E - aExp;
if ( aSign ) z = - z;
if ( ( z < 0 ) ^ aSign ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF;
}
if ( ( aSig<<shiftCount ) != savedASig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return z;
| overflows, the largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int64 floatx80_to_int64( floatx80 a STATUS_PARAM )
+int64_t floatx80_to_int64(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig, aSigExtra;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return 1ULL << 63;
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
shiftCount = 0x403E - aExp;
if ( shiftCount <= 0 ) {
if ( shiftCount ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign
|| ( ( aExp == 0x7FFF )
&& ( aSig != LIT64( 0x8000000000000000 ) ) )
else {
shift64ExtraRightJamming( aSig, 0, shiftCount, &aSig, &aSigExtra );
}
- return roundAndPackInt64( aSign, aSig, aSigExtra STATUS_VAR );
+ return roundAndPackInt64(aSign, aSig, aSigExtra, status);
}
| sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int64 floatx80_to_int64_round_to_zero( floatx80 a STATUS_PARAM )
+int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig;
- int64 z;
+ int64_t z;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return 1ULL << 63;
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( 0 <= shiftCount ) {
aSig &= LIT64( 0x7FFFFFFFFFFFFFFF );
if ( ( a.high != 0xC03E ) || aSig ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0x7FFF ) && aSig ) ) {
return LIT64( 0x7FFFFFFFFFFFFFFF );
}
return (int64_t) LIT64( 0x8000000000000000 );
}
else if ( aExp < 0x3FFF ) {
- if ( aExp | aSig ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp | aSig) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
z = aSig>>( - shiftCount );
if ( (uint64_t) ( aSig<<( shiftCount & 63 ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
if ( aSign ) z = - z;
return z;
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float32 floatx80_to_float32( floatx80 a STATUS_PARAM )
+float32 floatx80_to_float32(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t aSig;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return float32_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( aExp == 0x7FFF ) {
if ( (uint64_t) ( aSig<<1 ) ) {
- return commonNaNToFloat32( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloat32(floatx80ToCommonNaN(a, status), status);
}
return packFloat32( aSign, 0xFF, 0 );
}
shift64RightJamming( aSig, 33, &aSig );
if ( aExp || aSig ) aExp -= 0x3F81;
- return roundAndPackFloat32( aSign, aExp, aSig STATUS_VAR );
+ return roundAndPackFloat32(aSign, aExp, aSig, status);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float64 floatx80_to_float64( floatx80 a STATUS_PARAM )
+float64 floatx80_to_float64(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t aSig, zSig;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return float64_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( aExp == 0x7FFF ) {
if ( (uint64_t) ( aSig<<1 ) ) {
- return commonNaNToFloat64( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloat64(floatx80ToCommonNaN(a, status), status);
}
return packFloat64( aSign, 0x7FF, 0 );
}
shift64RightJamming( aSig, 1, &zSig );
if ( aExp || aSig ) aExp -= 0x3C01;
- return roundAndPackFloat64( aSign, aExp, zSig STATUS_VAR );
+ return roundAndPackFloat64(aSign, aExp, zSig, status);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 floatx80_to_float128( floatx80 a STATUS_PARAM )
+float128 floatx80_to_float128(floatx80 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp;
+ int aExp;
uint64_t aSig, zSig0, zSig1;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) {
- return commonNaNToFloat128( floatx80ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloat128(floatx80ToCommonNaN(a, status), status);
}
shift128Right( aSig<<1, 0, 16, &zSig0, &zSig1 );
return packFloat128( aSign, aExp, zSig0, zSig1 );
}
+/*----------------------------------------------------------------------------
+| Rounds the extended double-precision floating-point value `a'
+| to the precision provided by floatx80_rounding_precision and returns the
+| result as an extended double-precision floating-point value.
+| The operation is performed according to the IEC/IEEE Standard for Binary
+| Floating-Point Arithmetic.
+*----------------------------------------------------------------------------*/
+
+floatx80 floatx80_round(floatx80 a, float_status *status)
+{
+ return roundAndPackFloatx80(status->floatx80_rounding_precision,
+ extractFloatx80Sign(a),
+ extractFloatx80Exp(a),
+ extractFloatx80Frac(a), 0, status);
+}
+
/*----------------------------------------------------------------------------
| Rounds the extended double-precision floating-point value `a' to an integer,
| and returns the result as an extended quadruple-precision floating-point
| Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_round_to_int( floatx80 a STATUS_PARAM )
+floatx80 floatx80_round_to_int(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t lastBitMask, roundBitsMask;
floatx80 z;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
+ }
aExp = extractFloatx80Exp( a );
if ( 0x403E <= aExp ) {
if ( ( aExp == 0x7FFF ) && (uint64_t) ( extractFloatx80Frac( a )<<1 ) ) {
- return propagateFloatx80NaN( a, a STATUS_VAR );
+ return propagateFloatx80NaN(a, a, status);
}
return a;
}
&& ( (uint64_t) ( extractFloatx80Frac( a )<<1 ) == 0 ) ) {
return a;
}
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
aSign = extractFloatx80Sign( a );
- switch ( STATUS(float_rounding_mode) ) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
if ( ( aExp == 0x3FFE ) && (uint64_t) ( extractFloatx80Frac( a )<<1 )
) {
lastBitMask <<= 0x403E - aExp;
roundBitsMask = lastBitMask - 1;
z = a;
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
z.low += lastBitMask>>1;
if ((z.low & roundBitsMask) == 0) {
++z.high;
z.low = LIT64( 0x8000000000000000 );
}
- if ( z.low != a.low ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (z.low != a.low) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return z;
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static floatx80 addFloatx80Sigs( floatx80 a, floatx80 b, flag zSign STATUS_PARAM)
+static floatx80 addFloatx80Sigs(floatx80 a, floatx80 b, flag zSign,
+ float_status *status)
{
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig, bSig, zSig0, zSig1;
- int32 expDiff;
+ int32_t expDiff;
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
expDiff = aExp - bExp;
if ( 0 < expDiff ) {
if ( aExp == 0x7FFF ) {
- if ( (uint64_t) ( aSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(aSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) --expDiff;
}
else if ( expDiff < 0 ) {
if ( bExp == 0x7FFF ) {
- if ( (uint64_t) ( bSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( aExp == 0 ) ++expDiff;
else {
if ( aExp == 0x7FFF ) {
if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) {
- return propagateFloatx80NaN( a, b STATUS_VAR );
+ return propagateFloatx80NaN(a, b, status);
}
return a;
}
zSig0 |= LIT64( 0x8000000000000000 );
++zExp;
roundAndPack:
- return
- roundAndPackFloatx80(
- STATUS(floatx80_rounding_precision), zSign, zExp, zSig0, zSig1 STATUS_VAR );
-
+ return roundAndPackFloatx80(status->floatx80_rounding_precision,
+ zSign, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static floatx80 subFloatx80Sigs( floatx80 a, floatx80 b, flag zSign STATUS_PARAM )
+static floatx80 subFloatx80Sigs(floatx80 a, floatx80 b, flag zSign,
+ float_status *status)
{
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig, bSig, zSig0, zSig1;
- int32 expDiff;
- floatx80 z;
+ int32_t expDiff;
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
if ( expDiff < 0 ) goto bExpBigger;
if ( aExp == 0x7FFF ) {
if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) {
- return propagateFloatx80NaN( a, b STATUS_VAR );
+ return propagateFloatx80NaN(a, b, status);
}
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = floatx80_default_nan_low;
- z.high = floatx80_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
}
if ( aExp == 0 ) {
aExp = 1;
zSig1 = 0;
if ( bSig < aSig ) goto aBigger;
if ( aSig < bSig ) goto bBigger;
- return packFloatx80( STATUS(float_rounding_mode) == float_round_down, 0, 0 );
+ 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_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return packFloatx80( zSign ^ 1, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( aExp == 0 ) ++expDiff;
goto normalizeRoundAndPack;
aExpBigger:
if ( aExp == 0x7FFF ) {
- if ( (uint64_t) ( aSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(aSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) --expDiff;
sub128( aSig, 0, bSig, zSig1, &zSig0, &zSig1 );
zExp = aExp;
normalizeRoundAndPack:
- return
- normalizeRoundAndPackFloatx80(
- STATUS(floatx80_rounding_precision), zSign, zExp, zSig0, zSig1 STATUS_VAR );
-
+ return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision,
+ zSign, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_add( floatx80 a, floatx80 b STATUS_PARAM )
+floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status)
{
flag 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_VAR );
+ return addFloatx80Sigs(a, b, aSign, status);
}
else {
- return subFloatx80Sigs( a, b, aSign STATUS_VAR );
+ return subFloatx80Sigs(a, b, aSign, status);
}
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_sub( floatx80 a, floatx80 b STATUS_PARAM )
+floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status)
{
flag 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_VAR );
+ return subFloatx80Sigs(a, b, aSign, status);
}
else {
- return addFloatx80Sigs( a, b, aSign STATUS_VAR );
+ return addFloatx80Sigs(a, b, aSign, status);
}
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_mul( floatx80 a, floatx80 b STATUS_PARAM )
+floatx80 floatx80_mul(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign, zSign;
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig, bSig, zSig0, zSig1;
- floatx80 z;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( aExp == 0x7FFF ) {
if ( (uint64_t) ( aSig<<1 )
|| ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) {
- return propagateFloatx80NaN( a, b STATUS_VAR );
+ return propagateFloatx80NaN(a, b, status);
}
if ( ( bExp | bSig ) == 0 ) goto invalid;
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( bExp == 0x7FFF ) {
- if ( (uint64_t) ( bSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
if ( ( aExp | aSig ) == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = floatx80_default_nan_low;
- z.high = floatx80_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
}
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
shortShift128Left( zSig0, zSig1, 1, &zSig0, &zSig1 );
--zExp;
}
- return
- roundAndPackFloatx80(
- STATUS(floatx80_rounding_precision), zSign, zExp, zSig0, zSig1 STATUS_VAR );
-
+ return roundAndPackFloatx80(status->floatx80_rounding_precision,
+ zSign, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_div( floatx80 a, floatx80 b STATUS_PARAM )
+floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign, zSign;
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig, bSig, zSig0, zSig1;
uint64_t rem0, rem1, rem2, term0, term1, term2;
- floatx80 z;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
bSign = extractFloatx80Sign( b );
zSign = aSign ^ bSign;
if ( aExp == 0x7FFF ) {
- if ( (uint64_t) ( aSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(aSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
if ( bExp == 0x7FFF ) {
- if ( (uint64_t) ( bSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
goto invalid;
}
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
if ( bExp == 0x7FFF ) {
- if ( (uint64_t) ( bSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return packFloatx80( zSign, 0, 0 );
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
if ( ( aExp | aSig ) == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = floatx80_default_nan_low;
- z.high = floatx80_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
}
- float_raise( float_flag_divbyzero STATUS_VAR);
+ float_raise(float_flag_divbyzero, status);
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
normalizeFloatx80Subnormal( bSig, &bExp, &bSig );
}
zSig1 |= ( ( rem1 | rem2 ) != 0 );
}
- return
- roundAndPackFloatx80(
- STATUS(floatx80_rounding_precision), zSign, zExp, zSig0, zSig1 STATUS_VAR );
-
+ return roundAndPackFloatx80(status->floatx80_rounding_precision,
+ zSign, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_rem( floatx80 a, floatx80 b STATUS_PARAM )
+floatx80 floatx80_rem(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, zSign;
- int32 aExp, bExp, expDiff;
+ int32_t aExp, bExp, expDiff;
uint64_t aSig0, aSig1, bSig;
uint64_t q, term0, term1, alternateASig0, alternateASig1;
- floatx80 z;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ 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 )
|| ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) {
- return propagateFloatx80NaN( a, b STATUS_VAR );
+ return propagateFloatx80NaN(a, b, status);
}
goto invalid;
}
if ( bExp == 0x7FFF ) {
- if ( (uint64_t) ( bSig<<1 ) ) return propagateFloatx80NaN( a, b STATUS_VAR );
+ if ((uint64_t)(bSig << 1)) {
+ return propagateFloatx80NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
if ( bSig == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = floatx80_default_nan_low;
- z.high = floatx80_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
}
normalizeFloatx80Subnormal( bSig, &bExp, &bSig );
}
}
return
normalizeRoundAndPackFloatx80(
- 80, zSign, bExp + expDiff, aSig0, aSig1 STATUS_VAR );
+ 80, zSign, bExp + expDiff, aSig0, aSig1, status);
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 floatx80_sqrt( floatx80 a STATUS_PARAM )
+floatx80 floatx80_sqrt(floatx80 a, float_status *status)
{
flag aSign;
- int32 aExp, zExp;
+ int32_t aExp, zExp;
uint64_t aSig0, aSig1, zSig0, zSig1, doubleZSig0;
uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3;
- floatx80 z;
+ 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_VAR );
+ 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_VAR);
- z.low = floatx80_default_nan_low;
- z.high = floatx80_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
}
if ( aExp == 0 ) {
if ( aSig0 == 0 ) return packFloatx80( 0, 0, 0 );
}
shortShift128Left( 0, zSig1, 1, &zSig0, &zSig1 );
zSig0 |= doubleZSig0;
- return
- roundAndPackFloatx80(
- STATUS(floatx80_rounding_precision), 0, zExp, zSig0, zSig1 STATUS_VAR );
-
+ return roundAndPackFloatx80(status->floatx80_rounding_precision,
+ 0, zExp, zSig0, zSig1, status);
}
/*----------------------------------------------------------------------------
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_eq( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_eq(floatx80 a, floatx80 b, float_status *status)
{
- if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
- || ( ( extractFloatx80Exp( b ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)
+ || (extractFloatx80Exp(a) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(a) << 1))
+ || (extractFloatx80Exp(b) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(b) << 1))
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
return
| Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_le( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_le(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign;
- if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
- || ( ( extractFloatx80Exp( b ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)
+ || (extractFloatx80Exp(a) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(a) << 1))
+ || (extractFloatx80Exp(b) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(b) << 1))
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloatx80Sign( a );
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_lt( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_lt(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign;
- if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
- || ( ( extractFloatx80Exp( b ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)
+ || (extractFloatx80Exp(a) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(a) << 1))
+ || (extractFloatx80Exp(b) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(b) << 1))
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloatx80Sign( a );
| either operand is a NaN. The comparison is performed according to the
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_unordered( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_unordered(floatx80 a, floatx80 b, float_status *status)
{
- if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
- || ( ( extractFloatx80Exp( b ) == 0x7FFF )
- && (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)
+ || (extractFloatx80Exp(a) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(a) << 1))
+ || (extractFloatx80Exp(b) == 0x7FFF
+ && (uint64_t) (extractFloatx80Frac(b) << 1))
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 1;
}
return 0;
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_eq_quiet( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_eq_quiet(floatx80 a, floatx80 b, float_status *status)
{
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return 0;
+ }
if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
|| ( ( extractFloatx80Exp( b ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
) {
- if ( floatx80_is_signaling_nan( a )
- || floatx80_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (floatx80_is_signaling_nan(a, status)
+ || floatx80_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_le_quiet( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_le_quiet(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return 0;
+ }
if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
|| ( ( extractFloatx80Exp( b ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
) {
- if ( floatx80_is_signaling_nan( a )
- || floatx80_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (floatx80_is_signaling_nan(a, status)
+ || floatx80_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_lt_quiet( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_lt_quiet(floatx80 a, floatx80 b, float_status *status)
{
flag aSign, bSign;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return 0;
+ }
if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
|| ( ( extractFloatx80Exp( b ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
) {
- if ( floatx80_is_signaling_nan( a )
- || floatx80_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (floatx80_is_signaling_nan(a, status)
+ || floatx80_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| The comparison is performed according to the IEC/IEEE Standard for Binary
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int floatx80_unordered_quiet( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_unordered_quiet(floatx80 a, floatx80 b, float_status *status)
{
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return 1;
+ }
if ( ( ( extractFloatx80Exp( a ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( a )<<1 ) )
|| ( ( extractFloatx80Exp( b ) == 0x7FFF )
&& (uint64_t) ( extractFloatx80Frac( b )<<1 ) )
) {
- if ( floatx80_is_signaling_nan( a )
- || floatx80_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (floatx80_is_signaling_nan(a, status)
+ || floatx80_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 1;
}
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int32 float128_to_int32( float128 a STATUS_PARAM )
+int32_t float128_to_int32(float128 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig0, aSig1;
aSig1 = extractFloat128Frac1( a );
aSig0 |= ( aSig1 != 0 );
shiftCount = 0x4028 - aExp;
if ( 0 < shiftCount ) shift64RightJamming( aSig0, shiftCount, &aSig0 );
- return roundAndPackInt32( aSign, aSig0 STATUS_VAR );
+ return roundAndPackInt32(aSign, aSig0, status);
}
| returned.
*----------------------------------------------------------------------------*/
-int32 float128_to_int32_round_to_zero( float128 a STATUS_PARAM )
+int32_t float128_to_int32_round_to_zero(float128 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig0, aSig1, savedASig;
int32_t z;
goto invalid;
}
else if ( aExp < 0x3FFF ) {
- if ( aExp || aSig0 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aExp || aSig0) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
return 0;
}
aSig0 |= LIT64( 0x0001000000000000 );
if ( aSign ) z = - z;
if ( ( z < 0 ) ^ aSign ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF;
}
if ( ( aSig0<<shiftCount ) != savedASig ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return z;
| largest integer with the same sign as `a' is returned.
*----------------------------------------------------------------------------*/
-int64 float128_to_int64( float128 a STATUS_PARAM )
+int64_t float128_to_int64(float128 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig0, aSig1;
aSig1 = extractFloat128Frac1( a );
shiftCount = 0x402F - aExp;
if ( shiftCount <= 0 ) {
if ( 0x403E < aExp ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign
|| ( ( aExp == 0x7FFF )
&& ( aSig1 || ( aSig0 != LIT64( 0x0001000000000000 ) ) )
else {
shift64ExtraRightJamming( aSig0, aSig1, shiftCount, &aSig0, &aSig1 );
}
- return roundAndPackInt64( aSign, aSig0, aSig1 STATUS_VAR );
+ return roundAndPackInt64(aSign, aSig0, aSig1, status);
}
| returned.
*----------------------------------------------------------------------------*/
-int64 float128_to_int64_round_to_zero( float128 a STATUS_PARAM )
+int64_t float128_to_int64_round_to_zero(float128 a, float_status *status)
{
flag aSign;
- int32 aExp, shiftCount;
+ int32_t aExp, shiftCount;
uint64_t aSig0, aSig1;
- int64 z;
+ int64_t z;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
aSig0 &= LIT64( 0x0000FFFFFFFFFFFF );
if ( ( a.high == LIT64( 0xC03E000000000000 ) )
&& ( aSig1 < LIT64( 0x0002000000000000 ) ) ) {
- if ( aSig1 ) STATUS(float_exception_flags) |= float_flag_inexact;
+ if (aSig1) {
+ status->float_exception_flags |= float_flag_inexact;
+ }
}
else {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if ( ! aSign || ( ( aExp == 0x7FFF ) && ( aSig0 | aSig1 ) ) ) {
return LIT64( 0x7FFFFFFFFFFFFFFF );
}
}
z = ( aSig0<<shiftCount ) | ( aSig1>>( ( - shiftCount ) & 63 ) );
if ( (uint64_t) ( aSig1<<shiftCount ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
}
else {
if ( aExp < 0x3FFF ) {
if ( aExp | aSig0 | aSig1 ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return 0;
}
z = aSig0>>( - shiftCount );
if ( aSig1
|| ( shiftCount && (uint64_t) ( aSig0<<( shiftCount & 63 ) ) ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
}
if ( aSign ) z = - z;
}
+/*----------------------------------------------------------------------------
+| 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)
+{
+ flag 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 LIT64(0xFFFFFFFFFFFFFFFF);
+ } else {
+ return 0;
+ }
+ }
+ if (aExp) {
+ aSig0 |= LIT64(0x0001000000000000);
+ }
+ shiftCount = 0x402F - aExp;
+ if (shiftCount <= 0) {
+ if (0x403E < aExp) {
+ float_raise(float_flag_invalid, status);
+ return LIT64(0xFFFFFFFFFFFFFFFF);
+ }
+ 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 single-precision floating-point format. The conversion
| Arithmetic.
*----------------------------------------------------------------------------*/
-float32 float128_to_float32( float128 a STATUS_PARAM )
+float32 float128_to_float32(float128 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t aSig0, aSig1;
uint32_t zSig;
aSign = extractFloat128Sign( a );
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 ) {
- return commonNaNToFloat32( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloat32(float128ToCommonNaN(a, status), status);
}
return packFloat32( aSign, 0xFF, 0 );
}
zSig |= 0x40000000;
aExp -= 0x3F81;
}
- return roundAndPackFloat32( aSign, aExp, zSig STATUS_VAR );
+ return roundAndPackFloat32(aSign, aExp, zSig, status);
}
| Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float128_to_float64( float128 a STATUS_PARAM )
+float64 float128_to_float64(float128 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t aSig0, aSig1;
aSig1 = extractFloat128Frac1( a );
aSign = extractFloat128Sign( a );
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 ) {
- return commonNaNToFloat64( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloat64(float128ToCommonNaN(a, status), status);
}
return packFloat64( aSign, 0x7FF, 0 );
}
aSig0 |= LIT64( 0x4000000000000000 );
aExp -= 0x3C01;
}
- return roundAndPackFloat64( aSign, aExp, aSig0 STATUS_VAR );
+ return roundAndPackFloat64(aSign, aExp, aSig0, status);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-floatx80 float128_to_floatx80( float128 a STATUS_PARAM )
+floatx80 float128_to_floatx80(float128 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t aSig0, aSig1;
aSig1 = extractFloat128Frac1( a );
aSign = extractFloat128Sign( a );
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 ) {
- return commonNaNToFloatx80( float128ToCommonNaN( a STATUS_VAR ) STATUS_VAR );
+ return commonNaNToFloatx80(float128ToCommonNaN(a, status), status);
}
return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
}
aSig0 |= LIT64( 0x0001000000000000 );
}
shortShift128Left( aSig0, aSig1, 15, &aSig0, &aSig1 );
- return roundAndPackFloatx80( 80, aSign, aExp, aSig0, aSig1 STATUS_VAR );
+ return roundAndPackFloatx80(80, aSign, aExp, aSig0, aSig1, status);
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_round_to_int( float128 a STATUS_PARAM )
+float128 float128_round_to_int(float128 a, float_status *status)
{
flag aSign;
- int32 aExp;
+ int32_t aExp;
uint64_t lastBitMask, roundBitsMask;
float128 z;
if ( ( aExp == 0x7FFF )
&& ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) )
) {
- return propagateFloat128NaN( a, a STATUS_VAR );
+ return propagateFloat128NaN(a, a, status);
}
return a;
}
lastBitMask = ( lastBitMask<<( 0x406E - aExp ) )<<1;
roundBitsMask = lastBitMask - 1;
z = a;
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
if ( lastBitMask ) {
add128( z.high, z.low, 0, lastBitMask>>1, &z.high, &z.low );
else {
if ( aExp < 0x3FFF ) {
if ( ( ( (uint64_t) ( a.high<<1 ) ) | a.low ) == 0 ) return a;
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
aSign = extractFloat128Sign( a );
- switch ( STATUS(float_rounding_mode) ) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
if ( ( aExp == 0x3FFE )
&& ( extractFloat128Frac0( a )
roundBitsMask = lastBitMask - 1;
z.low = 0;
z.high = a.high;
- switch (STATUS(float_rounding_mode)) {
+ switch (status->float_rounding_mode) {
case float_round_nearest_even:
z.high += lastBitMask>>1;
if ( ( ( z.high & roundBitsMask ) | a.low ) == 0 ) {
z.high &= ~ roundBitsMask;
}
if ( ( z.low != a.low ) || ( z.high != a.high ) ) {
- STATUS(float_exception_flags) |= float_flag_inexact;
+ status->float_exception_flags |= float_flag_inexact;
}
return z;
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float128 addFloat128Sigs( float128 a, float128 b, flag zSign STATUS_PARAM)
+static float128 addFloat128Sigs(float128 a, float128 b, flag zSign,
+ float_status *status)
{
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2;
- int32 expDiff;
+ int32_t expDiff;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
expDiff = aExp - bExp;
if ( 0 < expDiff ) {
if ( aExp == 0x7FFF ) {
- if ( aSig0 | aSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (aSig0 | aSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
}
else if ( expDiff < 0 ) {
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
if ( aExp == 0 ) {
else {
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 | bSig0 | bSig1 ) {
- return propagateFloat128NaN( a, b STATUS_VAR );
+ return propagateFloat128NaN(a, b, status);
}
return a;
}
add128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 );
if ( aExp == 0 ) {
- if (STATUS(flush_to_zero)) {
+ if (status->flush_to_zero) {
if (zSig0 | zSig1) {
- float_raise(float_flag_output_denormal STATUS_VAR);
+ float_raise(float_flag_output_denormal, status);
}
return packFloat128(zSign, 0, 0, 0);
}
shift128ExtraRightJamming(
zSig0, zSig1, zSig2, 1, &zSig0, &zSig1, &zSig2 );
roundAndPack:
- return roundAndPackFloat128( zSign, zExp, zSig0, zSig1, zSig2 STATUS_VAR );
+ return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status);
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-static float128 subFloat128Sigs( float128 a, float128 b, flag zSign STATUS_PARAM)
+static float128 subFloat128Sigs(float128 a, float128 b, flag zSign,
+ float_status *status)
{
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1;
- int32 expDiff;
- float128 z;
+ int32_t expDiff;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
if ( expDiff < 0 ) goto bExpBigger;
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 | bSig0 | bSig1 ) {
- return propagateFloat128NaN( a, b STATUS_VAR );
+ return propagateFloat128NaN(a, b, status);
}
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = float128_default_nan_low;
- z.high = float128_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
}
if ( aExp == 0 ) {
aExp = 1;
if ( aSig0 < bSig0 ) goto bBigger;
if ( bSig1 < aSig1 ) goto aBigger;
if ( aSig1 < bSig1 ) goto bBigger;
- return packFloat128( STATUS(float_rounding_mode) == float_round_down, 0, 0, 0 );
+ return packFloat128(status->float_rounding_mode == float_round_down,
+ 0, 0, 0);
bExpBigger:
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return packFloat128( zSign ^ 1, 0x7FFF, 0, 0 );
}
if ( aExp == 0 ) {
goto normalizeRoundAndPack;
aExpBigger:
if ( aExp == 0x7FFF ) {
- if ( aSig0 | aSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (aSig0 | aSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
zExp = aExp;
normalizeRoundAndPack:
--zExp;
- return normalizeRoundAndPackFloat128( zSign, zExp - 14, zSig0, zSig1 STATUS_VAR );
+ return normalizeRoundAndPackFloat128(zSign, zExp - 14, zSig0, zSig1,
+ status);
}
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_add( float128 a, float128 b STATUS_PARAM )
+float128 float128_add(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
aSign = extractFloat128Sign( a );
bSign = extractFloat128Sign( b );
if ( aSign == bSign ) {
- return addFloat128Sigs( a, b, aSign STATUS_VAR );
+ return addFloat128Sigs(a, b, aSign, status);
}
else {
- return subFloat128Sigs( a, b, aSign STATUS_VAR );
+ return subFloat128Sigs(a, b, aSign, status);
}
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_sub( float128 a, float128 b STATUS_PARAM )
+float128 float128_sub(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
aSign = extractFloat128Sign( a );
bSign = extractFloat128Sign( b );
if ( aSign == bSign ) {
- return subFloat128Sigs( a, b, aSign STATUS_VAR );
+ return subFloat128Sigs(a, b, aSign, status);
}
else {
- return addFloat128Sigs( a, b, aSign STATUS_VAR );
+ return addFloat128Sigs(a, b, aSign, status);
}
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_mul( float128 a, float128 b STATUS_PARAM )
+float128 float128_mul(float128 a, float128 b, float_status *status)
{
flag aSign, bSign, zSign;
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2, zSig3;
- float128 z;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
if ( aExp == 0x7FFF ) {
if ( ( aSig0 | aSig1 )
|| ( ( bExp == 0x7FFF ) && ( bSig0 | bSig1 ) ) ) {
- return propagateFloat128NaN( a, b STATUS_VAR );
+ return propagateFloat128NaN(a, b, status);
}
if ( ( bExp | bSig0 | bSig1 ) == 0 ) goto invalid;
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
if ( ( aExp | aSig0 | aSig1 ) == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = float128_default_nan_low;
- z.high = float128_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
}
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
zSig0, zSig1, zSig2, 1, &zSig0, &zSig1, &zSig2 );
++zExp;
}
- return roundAndPackFloat128( zSign, zExp, zSig0, zSig1, zSig2 STATUS_VAR );
+ return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status);
}
| the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_div( float128 a, float128 b STATUS_PARAM )
+float128 float128_div(float128 a, float128 b, float_status *status)
{
flag aSign, bSign, zSign;
- int32 aExp, bExp, zExp;
+ int32_t aExp, bExp, zExp;
uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2;
uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3;
- float128 z;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
bSign = extractFloat128Sign( b );
zSign = aSign ^ bSign;
if ( aExp == 0x7FFF ) {
- if ( aSig0 | aSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (aSig0 | aSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
goto invalid;
}
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return packFloat128( zSign, 0, 0, 0 );
}
if ( bExp == 0 ) {
if ( ( bSig0 | bSig1 ) == 0 ) {
if ( ( aExp | aSig0 | aSig1 ) == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = float128_default_nan_low;
- z.high = float128_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
}
- float_raise( float_flag_divbyzero STATUS_VAR);
+ float_raise(float_flag_divbyzero, status);
return packFloat128( zSign, 0x7FFF, 0, 0 );
}
normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 );
zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 );
}
shift128ExtraRightJamming( zSig0, zSig1, 0, 15, &zSig0, &zSig1, &zSig2 );
- return roundAndPackFloat128( zSign, zExp, zSig0, zSig1, zSig2 STATUS_VAR );
+ return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status);
}
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_rem( float128 a, float128 b STATUS_PARAM )
+float128 float128_rem(float128 a, float128 b, float_status *status)
{
flag aSign, zSign;
- int32 aExp, bExp, expDiff;
+ int32_t aExp, bExp, expDiff;
uint64_t aSig0, aSig1, bSig0, bSig1, q, term0, term1, term2;
uint64_t allZero, alternateASig0, alternateASig1, sigMean1;
int64_t sigMean0;
- float128 z;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
if ( aExp == 0x7FFF ) {
if ( ( aSig0 | aSig1 )
|| ( ( bExp == 0x7FFF ) && ( bSig0 | bSig1 ) ) ) {
- return propagateFloat128NaN( a, b STATUS_VAR );
+ return propagateFloat128NaN(a, b, status);
}
goto invalid;
}
if ( bExp == 0x7FFF ) {
- if ( bSig0 | bSig1 ) return propagateFloat128NaN( a, b STATUS_VAR );
+ if (bSig0 | bSig1) {
+ return propagateFloat128NaN(a, b, status);
+ }
return a;
}
if ( bExp == 0 ) {
if ( ( bSig0 | bSig1 ) == 0 ) {
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = float128_default_nan_low;
- z.high = float128_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
}
normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 );
}
}
zSign = ( (int64_t) aSig0 < 0 );
if ( zSign ) sub128( 0, 0, aSig0, aSig1, &aSig0, &aSig1 );
- return
- normalizeRoundAndPackFloat128( aSign ^ zSign, bExp - 4, aSig0, aSig1 STATUS_VAR );
-
+ return normalizeRoundAndPackFloat128(aSign ^ zSign, bExp - 4, aSig0, aSig1,
+ status);
}
/*----------------------------------------------------------------------------
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-float128 float128_sqrt( float128 a STATUS_PARAM )
+float128 float128_sqrt(float128 a, float_status *status)
{
flag aSign;
- int32 aExp, zExp;
+ int32_t aExp, zExp;
uint64_t aSig0, aSig1, zSig0, zSig1, zSig2, doubleZSig0;
uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3;
- float128 z;
aSig1 = extractFloat128Frac1( a );
aSig0 = extractFloat128Frac0( a );
aExp = extractFloat128Exp( a );
aSign = extractFloat128Sign( a );
if ( aExp == 0x7FFF ) {
- if ( aSig0 | aSig1 ) return propagateFloat128NaN( a, a STATUS_VAR );
+ if (aSig0 | aSig1) {
+ return propagateFloat128NaN(a, a, status);
+ }
if ( ! aSign ) return a;
goto invalid;
}
if ( aSign ) {
if ( ( aExp | aSig0 | aSig1 ) == 0 ) return a;
invalid:
- float_raise( float_flag_invalid STATUS_VAR);
- z.low = float128_default_nan_low;
- z.high = float128_default_nan_high;
- return z;
+ float_raise(float_flag_invalid, status);
+ return float128_default_nan(status);
}
if ( aExp == 0 ) {
if ( ( aSig0 | aSig1 ) == 0 ) return packFloat128( 0, 0, 0, 0 );
zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 );
}
shift128ExtraRightJamming( zSig0, zSig1, 0, 14, &zSig0, &zSig1, &zSig2 );
- return roundAndPackFloat128( 0, zExp, zSig0, zSig1, zSig2 STATUS_VAR );
+ return roundAndPackFloat128(0, zExp, zSig0, zSig1, zSig2, status);
}
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_eq( float128 a, float128 b STATUS_PARAM )
+int float128_eq(float128 a, float128 b, float_status *status)
{
if ( ( ( extractFloat128Exp( a ) == 0x7FFF )
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
return
| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_le( float128 a, float128 b STATUS_PARAM )
+int float128_le(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat128Sign( a );
| to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_lt( float128 a, float128 b STATUS_PARAM )
+int float128_lt(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 0;
}
aSign = extractFloat128Sign( a );
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_unordered( float128 a, float128 b STATUS_PARAM )
+int float128_unordered(float128 a, float128 b, float_status *status)
{
if ( ( ( extractFloat128Exp( a ) == 0x7FFF )
&& ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) ) )
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return 1;
}
return 0;
| for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_eq_quiet( float128 a, float128 b STATUS_PARAM )
+int float128_eq_quiet(float128 a, float128 b, float_status *status)
{
if ( ( ( extractFloat128Exp( a ) == 0x7FFF )
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- if ( float128_is_signaling_nan( a )
- || float128_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float128_is_signaling_nan(a, status)
+ || float128_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_le_quiet( float128 a, float128 b STATUS_PARAM )
+int float128_le_quiet(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- if ( float128_is_signaling_nan( a )
- || float128_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float128_is_signaling_nan(a, status)
+ || float128_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Standard for Binary Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_lt_quiet( float128 a, float128 b STATUS_PARAM )
+int float128_lt_quiet(float128 a, float128 b, float_status *status)
{
flag aSign, bSign;
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- if ( float128_is_signaling_nan( a )
- || float128_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float128_is_signaling_nan(a, status)
+ || float128_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 0;
}
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/
-int float128_unordered_quiet( float128 a, float128 b STATUS_PARAM )
+int float128_unordered_quiet(float128 a, float128 b, float_status *status)
{
if ( ( ( extractFloat128Exp( a ) == 0x7FFF )
&& ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) ) )
|| ( ( extractFloat128Exp( b ) == 0x7FFF )
&& ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )
) {
- if ( float128_is_signaling_nan( a )
- || float128_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ if (float128_is_signaling_nan(a, status)
+ || float128_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return 1;
}
}
/* misc functions */
-float32 uint32_to_float32(uint32_t a STATUS_PARAM)
+float32 uint32_to_float32(uint32_t a, float_status *status)
{
- return int64_to_float32(a STATUS_VAR);
+ return int64_to_float32(a, status);
}
-float64 uint32_to_float64(uint32_t a STATUS_PARAM)
+float64 uint32_to_float64(uint32_t a, float_status *status)
{
- return int64_to_float64(a STATUS_VAR);
+ return int64_to_float64(a, status);
}
-uint32 float32_to_uint32( float32 a STATUS_PARAM )
+uint32_t float32_to_uint32(float32 a, float_status *status)
{
int64_t v;
- uint32 res;
+ uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float32_to_int64(a STATUS_VAR);
+ v = float32_to_int64(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffffffff) {
return v;
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint32 float32_to_uint32_round_to_zero( float32 a STATUS_PARAM )
+uint32_t float32_to_uint32_round_to_zero(float32 a, float_status *status)
{
int64_t v;
- uint32 res;
+ uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float32_to_int64_round_to_zero(a STATUS_VAR);
+ v = float32_to_int64_round_to_zero(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffffffff) {
return v;
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-int_fast16_t float32_to_int16(float32 a STATUS_PARAM)
+int16_t float32_to_int16(float32 a, float_status *status)
{
int32_t v;
- int_fast16_t res;
+ int16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float32_to_int32(a STATUS_VAR);
+ v = float32_to_int32(a, status);
if (v < -0x8000) {
res = -0x8000;
} else if (v > 0x7fff) {
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint_fast16_t float32_to_uint16(float32 a STATUS_PARAM)
+uint16_t float32_to_uint16(float32 a, float_status *status)
{
int32_t v;
- uint_fast16_t res;
+ uint16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float32_to_int32(a STATUS_VAR);
+ v = float32_to_int32(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffff) {
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint_fast16_t float32_to_uint16_round_to_zero(float32 a STATUS_PARAM)
+uint16_t float32_to_uint16_round_to_zero(float32 a, float_status *status)
{
int64_t v;
- uint_fast16_t res;
+ uint16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float32_to_int64_round_to_zero(a STATUS_VAR);
+ v = float32_to_int64_round_to_zero(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffff) {
return v;
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint32 float64_to_uint32( float64 a STATUS_PARAM )
+uint32_t float64_to_uint32(float64 a, float_status *status)
{
uint64_t v;
- uint32 res;
+ uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float64_to_uint64(a STATUS_VAR);
+ v = float64_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_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint32 float64_to_uint32_round_to_zero( float64 a STATUS_PARAM )
+uint32_t float64_to_uint32_round_to_zero(float64 a, float_status *status)
{
uint64_t v;
- uint32 res;
+ uint32_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float64_to_uint64_round_to_zero(a STATUS_VAR);
+ v = float64_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_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-int_fast16_t float64_to_int16(float64 a STATUS_PARAM)
+int16_t float64_to_int16(float64 a, float_status *status)
{
int64_t v;
- int_fast16_t res;
+ int16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float64_to_int32(a STATUS_VAR);
+ v = float64_to_int32(a, status);
if (v < -0x8000) {
res = -0x8000;
} else if (v > 0x7fff) {
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint_fast16_t float64_to_uint16(float64 a STATUS_PARAM)
+uint16_t float64_to_uint16(float64 a, float_status *status)
{
int64_t v;
- uint_fast16_t res;
+ uint16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float64_to_int32(a STATUS_VAR);
+ v = float64_to_int32(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffff) {
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
-uint_fast16_t float64_to_uint16_round_to_zero(float64 a STATUS_PARAM)
+uint16_t float64_to_uint16_round_to_zero(float64 a, float_status *status)
{
int64_t v;
- uint_fast16_t res;
+ uint16_t res;
int old_exc_flags = get_float_exception_flags(status);
- v = float64_to_int64_round_to_zero(a STATUS_VAR);
+ v = float64_to_int64_round_to_zero(a, status);
if (v < 0) {
res = 0;
} else if (v > 0xffff) {
return v;
}
set_float_exception_flags(old_exc_flags, status);
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return res;
}
| will raise the inexact exception.
*----------------------------------------------------------------------------*/
-uint64_t float64_to_uint64(float64 a STATUS_PARAM)
+uint64_t float64_to_uint64(float64 a, float_status *status)
{
flag aSign;
- int_fast16_t aExp, shiftCount;
+ int aExp;
+ int shiftCount;
uint64_t aSig, aSigExtra;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac(a);
aExp = extractFloat64Exp(a);
aSign = extractFloat64Sign(a);
if (aSign && (aExp > 1022)) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
if (float64_is_any_nan(a)) {
return LIT64(0xFFFFFFFFFFFFFFFF);
} else {
shiftCount = 0x433 - aExp;
if (shiftCount <= 0) {
if (0x43E < aExp) {
- float_raise(float_flag_invalid STATUS_VAR);
+ float_raise(float_flag_invalid, status);
return LIT64(0xFFFFFFFFFFFFFFFF);
}
aSigExtra = 0;
} else {
shift64ExtraRightJamming(aSig, 0, shiftCount, &aSig, &aSigExtra);
}
- return roundAndPackUint64(aSign, aSig, aSigExtra STATUS_VAR);
+ return roundAndPackUint64(aSign, aSig, aSigExtra, status);
}
-uint64_t float64_to_uint64_round_to_zero (float64 a STATUS_PARAM)
+uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *status)
{
- signed char current_rounding_mode = STATUS(float_rounding_mode);
- set_float_rounding_mode(float_round_to_zero STATUS_VAR);
- int64_t v = float64_to_uint64(a STATUS_VAR);
- set_float_rounding_mode(current_rounding_mode STATUS_VAR);
+ signed char current_rounding_mode = status->float_rounding_mode;
+ set_float_rounding_mode(float_round_to_zero, status);
+ uint64_t v = float64_to_uint64(a, status);
+ set_float_rounding_mode(current_rounding_mode, status);
return v;
}
#define COMPARE(s, nan_exp) \
-INLINE int float ## s ## _compare_internal( float ## s a, float ## s b, \
- int is_quiet STATUS_PARAM ) \
+static inline int float ## s ## _compare_internal(float ## s a, float ## s b,\
+ int is_quiet, float_status *status) \
{ \
flag aSign, bSign; \
uint ## s ## _t av, bv; \
- a = float ## s ## _squash_input_denormal(a STATUS_VAR); \
- b = float ## s ## _squash_input_denormal(b STATUS_VAR); \
+ a = float ## s ## _squash_input_denormal(a, status); \
+ b = float ## s ## _squash_input_denormal(b, status); \
\
if (( ( extractFloat ## s ## Exp( a ) == nan_exp ) && \
extractFloat ## s ## Frac( a ) ) || \
( ( extractFloat ## s ## Exp( b ) == nan_exp ) && \
extractFloat ## s ## Frac( b ) )) { \
if (!is_quiet || \
- float ## s ## _is_signaling_nan( a ) || \
- float ## s ## _is_signaling_nan( b ) ) { \
- float_raise( float_flag_invalid STATUS_VAR); \
+ float ## s ## _is_signaling_nan(a, status) || \
+ float ## s ## _is_signaling_nan(b, status)) { \
+ float_raise(float_flag_invalid, status); \
} \
return float_relation_unordered; \
} \
} \
} \
\
-int float ## s ## _compare( float ## s a, float ## s b STATUS_PARAM ) \
+int float ## s ## _compare(float ## s a, float ## s b, float_status *status) \
{ \
- return float ## s ## _compare_internal(a, b, 0 STATUS_VAR); \
+ return float ## s ## _compare_internal(a, b, 0, status); \
} \
\
-int float ## s ## _compare_quiet( float ## s a, float ## s b STATUS_PARAM ) \
+int float ## s ## _compare_quiet(float ## s a, float ## s b, \
+ float_status *status) \
{ \
- return float ## s ## _compare_internal(a, b, 1 STATUS_VAR); \
+ return float ## s ## _compare_internal(a, b, 1, status); \
}
COMPARE(32, 0xff)
COMPARE(64, 0x7ff)
-INLINE int floatx80_compare_internal( floatx80 a, floatx80 b,
- int is_quiet STATUS_PARAM )
+static inline int floatx80_compare_internal(floatx80 a, floatx80 b,
+ int is_quiet, float_status *status)
{
flag aSign, bSign;
+ if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) {
+ float_raise(float_flag_invalid, status);
+ return float_relation_unordered;
+ }
if (( ( extractFloatx80Exp( a ) == 0x7fff ) &&
( extractFloatx80Frac( a )<<1 ) ) ||
( ( extractFloatx80Exp( b ) == 0x7fff ) &&
( extractFloatx80Frac( b )<<1 ) )) {
if (!is_quiet ||
- floatx80_is_signaling_nan( a ) ||
- floatx80_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ floatx80_is_signaling_nan(a, status) ||
+ floatx80_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return float_relation_unordered;
}
}
}
-int floatx80_compare( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_compare(floatx80 a, floatx80 b, float_status *status)
{
- return floatx80_compare_internal(a, b, 0 STATUS_VAR);
+ return floatx80_compare_internal(a, b, 0, status);
}
-int floatx80_compare_quiet( floatx80 a, floatx80 b STATUS_PARAM )
+int floatx80_compare_quiet(floatx80 a, floatx80 b, float_status *status)
{
- return floatx80_compare_internal(a, b, 1 STATUS_VAR);
+ return floatx80_compare_internal(a, b, 1, status);
}
-INLINE int float128_compare_internal( float128 a, float128 b,
- int is_quiet STATUS_PARAM )
+static inline int float128_compare_internal(float128 a, float128 b,
+ int is_quiet, float_status *status)
{
flag aSign, bSign;
( ( extractFloat128Exp( b ) == 0x7fff ) &&
( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )) {
if (!is_quiet ||
- float128_is_signaling_nan( a ) ||
- float128_is_signaling_nan( b ) ) {
- float_raise( float_flag_invalid STATUS_VAR);
+ float128_is_signaling_nan(a, status) ||
+ float128_is_signaling_nan(b, status)) {
+ float_raise(float_flag_invalid, status);
}
return float_relation_unordered;
}
}
}
-int float128_compare( float128 a, float128 b STATUS_PARAM )
+int float128_compare(float128 a, float128 b, float_status *status)
{
- return float128_compare_internal(a, b, 0 STATUS_VAR);
+ return float128_compare_internal(a, b, 0, status);
}
-int float128_compare_quiet( float128 a, float128 b STATUS_PARAM )
+int float128_compare_quiet(float128 a, float128 b, float_status *status)
{
- return float128_compare_internal(a, b, 1 STATUS_VAR);
+ return float128_compare_internal(a, b, 1, status);
}
/* min() and max() functions. These can't be implemented as
* minnum() and maxnum correspond to the IEEE 754-2008 minNum()
* and maxNum() operations. min() and max() are the typical min/max
* semantics provided by many CPUs which predate that specification.
+ *
+ * minnummag() and maxnummag() functions correspond to minNumMag()
+ * and minNumMag() from the IEEE-754 2008.
*/
#define MINMAX(s) \
-INLINE float ## s float ## s ## _minmax(float ## s a, float ## s b, \
- int ismin, int isieee STATUS_PARAM) \
+static inline float ## s float ## s ## _minmax(float ## s a, float ## s b, \
+ int ismin, int isieee, \
+ int ismag, \
+ float_status *status) \
{ \
flag aSign, bSign; \
- uint ## s ## _t av, bv; \
- a = float ## s ## _squash_input_denormal(a STATUS_VAR); \
- b = float ## s ## _squash_input_denormal(b STATUS_VAR); \
+ uint ## s ## _t av, bv, aav, abv; \
+ a = float ## s ## _squash_input_denormal(a, status); \
+ b = float ## s ## _squash_input_denormal(b, status); \
if (float ## s ## _is_any_nan(a) || \
float ## s ## _is_any_nan(b)) { \
if (isieee) { \
- if (float ## s ## _is_quiet_nan(a) && \
+ if (float ## s ## _is_quiet_nan(a, status) && \
!float ## s ##_is_any_nan(b)) { \
return b; \
- } else if (float ## s ## _is_quiet_nan(b) && \
- !float ## s ## _is_any_nan(a)) { \
+ } else if (float ## s ## _is_quiet_nan(b, status) && \
+ !float ## s ## _is_any_nan(a)) { \
return a; \
} \
} \
- return propagateFloat ## s ## NaN(a, b STATUS_VAR); \
+ return propagateFloat ## s ## NaN(a, b, status); \
} \
aSign = extractFloat ## s ## Sign(a); \
bSign = extractFloat ## s ## Sign(b); \
av = float ## s ## _val(a); \
bv = float ## s ## _val(b); \
+ if (ismag) { \
+ aav = float ## s ## _abs(av); \
+ abv = float ## s ## _abs(bv); \
+ if (aav != abv) { \
+ if (ismin) { \
+ return (aav < abv) ? a : b; \
+ } else { \
+ return (aav < abv) ? b : a; \
+ } \
+ } \
+ } \
if (aSign != bSign) { \
if (ismin) { \
return aSign ? a : b; \
} \
} \
\
-float ## s float ## s ## _min(float ## s a, float ## s b STATUS_PARAM) \
+float ## s float ## s ## _min(float ## s a, float ## s b, \
+ float_status *status) \
+{ \
+ return float ## s ## _minmax(a, b, 1, 0, 0, status); \
+} \
+ \
+float ## s float ## s ## _max(float ## s a, float ## s b, \
+ float_status *status) \
{ \
- return float ## s ## _minmax(a, b, 1, 0 STATUS_VAR); \
+ return float ## s ## _minmax(a, b, 0, 0, 0, status); \
} \
\
-float ## s float ## s ## _max(float ## s a, float ## s b STATUS_PARAM) \
+float ## s float ## s ## _minnum(float ## s a, float ## s b, \
+ float_status *status) \
{ \
- return float ## s ## _minmax(a, b, 0, 0 STATUS_VAR); \
+ return float ## s ## _minmax(a, b, 1, 1, 0, status); \
} \
\
-float ## s float ## s ## _minnum(float ## s a, float ## s b STATUS_PARAM) \
+float ## s float ## s ## _maxnum(float ## s a, float ## s b, \
+ float_status *status) \
{ \
- return float ## s ## _minmax(a, b, 1, 1 STATUS_VAR); \
+ return float ## s ## _minmax(a, b, 0, 1, 0, status); \
} \
\
-float ## s float ## s ## _maxnum(float ## s a, float ## s b STATUS_PARAM) \
+float ## s float ## s ## _minnummag(float ## s a, float ## s b, \
+ float_status *status) \
{ \
- return float ## s ## _minmax(a, b, 0, 1 STATUS_VAR); \
+ return float ## s ## _minmax(a, b, 1, 1, 1, status); \
+} \
+ \
+float ## s float ## s ## _maxnummag(float ## s a, float ## s b, \
+ float_status *status) \
+{ \
+ return float ## s ## _minmax(a, b, 0, 1, 1, status); \
}
MINMAX(32)
/* Multiply A by 2 raised to the power N. */
-float32 float32_scalbn( float32 a, int n STATUS_PARAM )
+float32 float32_scalbn(float32 a, int n, float_status *status)
{
flag aSign;
int16_t aExp;
uint32_t aSig;
- a = float32_squash_input_denormal(a STATUS_VAR);
+ a = float32_squash_input_denormal(a, status);
aSig = extractFloat32Frac( a );
aExp = extractFloat32Exp( a );
aSign = extractFloat32Sign( a );
if ( aExp == 0xFF ) {
if ( aSig ) {
- return propagateFloat32NaN( a, a STATUS_VAR );
+ return propagateFloat32NaN(a, a, status);
}
return a;
}
aExp += n - 1;
aSig <<= 7;
- return normalizeRoundAndPackFloat32( aSign, aExp, aSig STATUS_VAR );
+ return normalizeRoundAndPackFloat32(aSign, aExp, aSig, status);
}
-float64 float64_scalbn( float64 a, int n STATUS_PARAM )
+float64 float64_scalbn(float64 a, int n, float_status *status)
{
flag aSign;
int16_t aExp;
uint64_t aSig;
- a = float64_squash_input_denormal(a STATUS_VAR);
+ a = float64_squash_input_denormal(a, status);
aSig = extractFloat64Frac( a );
aExp = extractFloat64Exp( a );
aSign = extractFloat64Sign( a );
if ( aExp == 0x7FF ) {
if ( aSig ) {
- return propagateFloat64NaN( a, a STATUS_VAR );
+ return propagateFloat64NaN(a, a, status);
}
return a;
}
aExp += n - 1;
aSig <<= 10;
- return normalizeRoundAndPackFloat64( aSign, aExp, aSig STATUS_VAR );
+ return normalizeRoundAndPackFloat64(aSign, aExp, aSig, status);
}
-floatx80 floatx80_scalbn( floatx80 a, int n STATUS_PARAM )
+floatx80 floatx80_scalbn(floatx80 a, int n, float_status *status)
{
flag aSign;
int32_t aExp;
uint64_t aSig;
+ if (floatx80_invalid_encoding(a)) {
+ float_raise(float_flag_invalid, status);
+ return floatx80_default_nan(status);
+ }
aSig = extractFloatx80Frac( a );
aExp = extractFloatx80Exp( a );
aSign = extractFloatx80Sign( a );
if ( aExp == 0x7FFF ) {
if ( aSig<<1 ) {
- return propagateFloatx80NaN( a, a STATUS_VAR );
+ return propagateFloatx80NaN(a, a, status);
}
return a;
}
}
aExp += n;
- return normalizeRoundAndPackFloatx80( STATUS(floatx80_rounding_precision),
- aSign, aExp, aSig, 0 STATUS_VAR );
+ return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision,
+ aSign, aExp, aSig, 0, status);
}
-float128 float128_scalbn( float128 a, int n STATUS_PARAM )
+float128 float128_scalbn(float128 a, int n, float_status *status)
{
flag aSign;
int32_t aExp;
aSign = extractFloat128Sign( a );
if ( aExp == 0x7FFF ) {
if ( aSig0 | aSig1 ) {
- return propagateFloat128NaN( a, a STATUS_VAR );
+ return propagateFloat128NaN(a, a, status);
}
return a;
}
aExp += n - 1;
return normalizeRoundAndPackFloat128( aSign, aExp, aSig0, aSig1
- STATUS_VAR );
+ , status);
}
projects / qemu.git / blobdiff