diff mbox

[10/12] softfloat: Add float/double to 16 bit integer conversion functions

Message ID 1290538431-13170-11-git-send-email-peter.maydell@linaro.org
State New
Headers show

Commit Message

Peter Maydell Nov. 23, 2010, 6:53 p.m. UTC
The ARM architecture needs float/double to 16 bit integer conversions.
(The 32 bit versions aren't sufficient because of the requirement
to saturate at 16 bit MAXINT/MININT and to get the exception bits right.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 fpu/softfloat.c |  136 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fpu/softfloat.h |    4 ++
 2 files changed, 140 insertions(+), 0 deletions(-)

Comments

Nathan Froyd Nov. 29, 2010, 6:46 p.m. UTC | #1
On Tue, Nov 23, 2010 at 06:53:49PM +0000, Peter Maydell wrote:
> The ARM architecture needs float/double to 16 bit integer conversions.
> (The 32 bit versions aren't sufficient because of the requirement
> to saturate at 16 bit MAXINT/MININT and to get the exception bits right.)
> 
> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

Reviewed-by: Nathan Froyd <froydnj@codesourcery.com>

-Nathan
diff mbox

Patch

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 0b82797..6f5b05d 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -1355,6 +1355,55 @@  int32 float32_to_int32_round_to_zero( float32 a STATUS_PARAM )
 
 /*----------------------------------------------------------------------------
 | Returns the result of converting the single-precision floating-point value
+| `a' to the 16-bit two's complement integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic, except that the conversion is always rounded toward zero.
+| If `a' is a NaN, the largest positive integer is returned.  Otherwise, if
+| the conversion overflows, the largest integer with the same sign as `a' is
+| returned.
+*----------------------------------------------------------------------------*/
+
+int16 float32_to_int16_round_to_zero( float32 a STATUS_PARAM )
+{
+    flag aSign;
+    int16 aExp, shiftCount;
+    bits32 aSig;
+    int32 z;
+
+    aSig = extractFloat32Frac( a );
+    aExp = extractFloat32Exp( a );
+    aSign = extractFloat32Sign( a );
+    shiftCount = aExp - 0x8E;
+    if ( 0 <= shiftCount ) {
+        if ( float32_val(a) != 0xC7000000 ) {
+            float_raise( float_flag_invalid STATUS_VAR);
+            if ( ! aSign || ( ( aExp == 0xFF ) && aSig ) ) {
+                return 0x7FFF;
+            }
+        }
+        return (sbits32) 0xffff8000;
+    }
+    else if ( aExp <= 0x7E ) {
+        if ( aExp | aSig ) {
+            STATUS(float_exception_flags) |= float_flag_inexact;
+        }
+        return 0;
+    }
+    shiftCount -= 0x10;
+    aSig = ( aSig | 0x00800000 )<<8;
+    z = aSig>>( - shiftCount );
+    if ( (bits32) ( aSig<<( shiftCount & 31 ) ) ) {
+        STATUS(float_exception_flags) |= float_flag_inexact;
+    }
+    if ( aSign ) {
+        z = - z;
+    }
+    return z;
+
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the single-precision floating-point value
 | `a' to the 64-bit two's complement integer format.  The conversion is
 | performed according to the IEC/IEEE Standard for Binary Floating-Point
 | Arithmetic---which means in particular that the conversion is rounded
@@ -2412,6 +2461,57 @@  int32 float64_to_int32_round_to_zero( float64 a STATUS_PARAM )
 
 /*----------------------------------------------------------------------------
 | Returns the result of converting the double-precision floating-point value
+| `a' to the 16-bit two's complement integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic, except that the conversion is always rounded toward zero.
+| If `a' is a NaN, the largest positive integer is returned.  Otherwise, if
+| the conversion overflows, the largest integer with the same sign as `a' is
+| returned.
+*----------------------------------------------------------------------------*/
+
+int16 float64_to_int16_round_to_zero( float64 a STATUS_PARAM )
+{
+    flag aSign;
+    int16 aExp, shiftCount;
+    bits64 aSig, savedASig;
+    int32 z;
+
+    aSig = extractFloat64Frac( a );
+    aExp = extractFloat64Exp( a );
+    aSign = extractFloat64Sign( a );
+    if ( 0x40E < aExp ) {
+        if ( ( aExp == 0x7FF ) && aSig ) {
+            aSign = 0;
+        }
+        goto invalid;
+    }
+    else if ( aExp < 0x3FF ) {
+        if ( aExp || aSig ) {
+            STATUS(float_exception_flags) |= float_flag_inexact;
+        }
+        return 0;
+    }
+    aSig |= LIT64( 0x0010000000000000 );
+    shiftCount = 0x433 - aExp;
+    savedASig = aSig;
+    aSig >>= shiftCount;
+    z = aSig;
+    if ( aSign ) {
+        z = - z;
+    }
+    if ( ( (int16_t)z < 0 ) ^ aSign ) {
+ invalid:
+        float_raise( float_flag_invalid STATUS_VAR);
+        return aSign ? (sbits32) 0xffff8000 : 0x7FFF;
+    }
+    if ( ( aSig<<shiftCount ) != savedASig ) {
+        STATUS(float_exception_flags) |= float_flag_inexact;
+    }
+    return z;
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the double-precision floating-point value
 | `a' to the 64-bit two's complement integer format.  The conversion is
 | performed according to the IEC/IEEE Standard for Binary Floating-Point
 | Arithmetic---which means in particular that the conversion is rounded
@@ -5632,6 +5732,24 @@  unsigned int float32_to_uint32_round_to_zero( float32 a STATUS_PARAM )
     return res;
 }
 
+unsigned int float32_to_uint16_round_to_zero( float32 a STATUS_PARAM )
+{
+    int64_t v;
+    unsigned int res;
+
+    v = float32_to_int64_round_to_zero(a STATUS_VAR);
+    if (v < 0) {
+        res = 0;
+        float_raise( float_flag_invalid STATUS_VAR);
+    } else if (v > 0xffff) {
+        res = 0xffff;
+        float_raise( float_flag_invalid STATUS_VAR);
+    } else {
+        res = v;
+    }
+    return res;
+}
+
 unsigned int float64_to_uint32( float64 a STATUS_PARAM )
 {
     int64_t v;
@@ -5668,6 +5786,24 @@  unsigned int float64_to_uint32_round_to_zero( float64 a STATUS_PARAM )
     return res;
 }
 
+unsigned int float64_to_uint16_round_to_zero( float64 a STATUS_PARAM )
+{
+    int64_t v;
+    unsigned int res;
+
+    v = float64_to_int64_round_to_zero(a STATUS_VAR);
+    if (v < 0) {
+        res = 0;
+        float_raise( float_flag_invalid STATUS_VAR);
+    } else if (v > 0xffff) {
+        res = 0xffff;
+        float_raise( float_flag_invalid STATUS_VAR);
+    } else {
+        res = v;
+    }
+    return res;
+}
+
 /* FIXME: This looks broken.  */
 uint64_t float64_to_uint64 (float64 a STATUS_PARAM)
 {
diff --git a/fpu/softfloat.h b/fpu/softfloat.h
index 9528825..5d68a07 100644
--- a/fpu/softfloat.h
+++ b/fpu/softfloat.h
@@ -251,6 +251,8 @@  float32 float16_to_float32( bits16, flag STATUS_PARAM );
 /*----------------------------------------------------------------------------
 | Software IEC/IEEE single-precision conversion routines.
 *----------------------------------------------------------------------------*/
+int float32_to_int16_round_to_zero( float32 STATUS_PARAM );
+unsigned int float32_to_uint16_round_to_zero( float32 STATUS_PARAM );
 int float32_to_int32( float32 STATUS_PARAM );
 int float32_to_int32_round_to_zero( float32 STATUS_PARAM );
 unsigned int float32_to_uint32( float32 STATUS_PARAM );
@@ -321,6 +323,8 @@  INLINE int float32_is_zero(float32 a)
 /*----------------------------------------------------------------------------
 | Software IEC/IEEE double-precision conversion routines.
 *----------------------------------------------------------------------------*/
+int float64_to_int16_round_to_zero( float64 STATUS_PARAM );
+unsigned int float64_to_uint16_round_to_zero( float64 STATUS_PARAM );
 int float64_to_int32( float64 STATUS_PARAM );
 int float64_to_int32_round_to_zero( float64 STATUS_PARAM );
 unsigned int float64_to_uint32( float64 STATUS_PARAM );