* to the IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*/
-static FloatParts int_to_float(int64_t a, float_status *status)
+static FloatParts int_to_float(int64_t a, int scale, float_status *status)
{
- FloatParts r = {};
+ FloatParts r = { .sign = false };
+
if (a == 0) {
r.cls = float_class_zero;
- r.sign = false;
- } else if (a == (1ULL << 63)) {
- r.cls = float_class_normal;
- r.sign = true;
- r.frac = DECOMPOSED_IMPLICIT_BIT;
- r.exp = 63;
} else {
- uint64_t f;
+ uint64_t f = a;
+ int shift;
+
+ r.cls = float_class_normal;
if (a < 0) {
- f = -a;
+ f = -f;
r.sign = true;
- } else {
- f = a;
- r.sign = false;
}
- int shift = clz64(f) - 1;
- r.cls = float_class_normal;
- r.exp = (DECOMPOSED_BINARY_POINT - shift);
- r.frac = f << shift;
+ shift = clz64(f) - 1;
+ scale = MIN(MAX(scale, -0x10000), 0x10000);
+
+ r.exp = DECOMPOSED_BINARY_POINT - shift + scale;
+ r.frac = (shift < 0 ? DECOMPOSED_IMPLICIT_BIT : f << shift);
}
return r;
}
-float16 int64_to_float16(int64_t a, float_status *status)
+float16 int64_to_float16_scalbn(int64_t a, int scale, float_status *status)
{
- FloatParts pa = int_to_float(a, status);
+ FloatParts pa = int_to_float(a, scale, status);
return float16_round_pack_canonical(pa, status);
}
+float16 int32_to_float16_scalbn(int32_t a, int scale, float_status *status)
+{
+ return int64_to_float16_scalbn(a, scale, status);
+}
+
+float16 int16_to_float16_scalbn(int16_t a, int scale, float_status *status)
+{
+ return int64_to_float16_scalbn(a, scale, status);
+}
+
+float16 int64_to_float16(int64_t a, float_status *status)
+{
+ return int64_to_float16_scalbn(a, 0, status);
+}
+
float16 int32_to_float16(int32_t a, float_status *status)
{
- return int64_to_float16(a, status);
+ return int64_to_float16_scalbn(a, 0, status);
}
float16 int16_to_float16(int16_t a, float_status *status)
{
- return int64_to_float16(a, status);
+ return int64_to_float16_scalbn(a, 0, status);
}
-float32 int64_to_float32(int64_t a, float_status *status)
+float32 int64_to_float32_scalbn(int64_t a, int scale, float_status *status)
{
- FloatParts pa = int_to_float(a, status);
+ FloatParts pa = int_to_float(a, scale, status);
return float32_round_pack_canonical(pa, status);
}
+float32 int32_to_float32_scalbn(int32_t a, int scale, float_status *status)
+{
+ return int64_to_float32_scalbn(a, scale, status);
+}
+
+float32 int16_to_float32_scalbn(int16_t a, int scale, float_status *status)
+{
+ return int64_to_float32_scalbn(a, scale, status);
+}
+
+float32 int64_to_float32(int64_t a, float_status *status)
+{
+ return int64_to_float32_scalbn(a, 0, status);
+}
+
float32 int32_to_float32(int32_t a, float_status *status)
{
- return int64_to_float32(a, status);
+ return int64_to_float32_scalbn(a, 0, status);
}
float32 int16_to_float32(int16_t a, float_status *status)
{
- return int64_to_float32(a, status);
+ return int64_to_float32_scalbn(a, 0, status);
}
-float64 int64_to_float64(int64_t a, float_status *status)
+float64 int64_to_float64_scalbn(int64_t a, int scale, float_status *status)
{
- FloatParts pa = int_to_float(a, status);
+ FloatParts pa = int_to_float(a, scale, status);
return float64_round_pack_canonical(pa, status);
}
+float64 int32_to_float64_scalbn(int32_t a, int scale, float_status *status)
+{
+ return int64_to_float64_scalbn(a, scale, status);
+}
+
+float64 int16_to_float64_scalbn(int16_t a, int scale, float_status *status)
+{
+ return int64_to_float64_scalbn(a, scale, status);
+}
+
+float64 int64_to_float64(int64_t a, float_status *status)
+{
+ return int64_to_float64_scalbn(a, 0, status);
+}
+
float64 int32_to_float64(int32_t a, float_status *status)
{
- return int64_to_float64(a, status);
+ return int64_to_float64_scalbn(a, 0, status);
}
float64 int16_to_float64(int16_t a, float_status *status)
{
- return int64_to_float64(a, status);
+ return int64_to_float64_scalbn(a, 0, status);
}
* IEC/IEEE Standard for Binary Floating-Point Arithmetic.
*/
-static FloatParts uint_to_float(uint64_t a, float_status *status)
+static FloatParts uint_to_float(uint64_t a, int scale, float_status *status)
{
- FloatParts r = { .sign = false};
+ FloatParts r = { .sign = false };
if (a == 0) {
r.cls = float_class_zero;
} else {
- int spare_bits = clz64(a) - 1;
+ scale = MIN(MAX(scale, -0x10000), 0x10000);
r.cls = float_class_normal;
- r.exp = DECOMPOSED_BINARY_POINT - spare_bits;
- if (spare_bits < 0) {
- shift64RightJamming(a, -spare_bits, &a);
+ if ((int64_t)a < 0) {
+ r.exp = DECOMPOSED_BINARY_POINT + 1 + scale;
+ shift64RightJamming(a, 1, &a);
r.frac = a;
} else {
- r.frac = a << spare_bits;
+ int shift = clz64(a) - 1;
+ r.exp = DECOMPOSED_BINARY_POINT - shift + scale;
+ r.frac = a << shift;
}
}
return r;
}
-float16 uint64_to_float16(uint64_t a, float_status *status)
+float16 uint64_to_float16_scalbn(uint64_t a, int scale, float_status *status)
{
- FloatParts pa = uint_to_float(a, status);
+ FloatParts pa = uint_to_float(a, scale, status);
return float16_round_pack_canonical(pa, status);
}
+float16 uint32_to_float16_scalbn(uint32_t a, int scale, float_status *status)
+{
+ return uint64_to_float16_scalbn(a, scale, status);
+}
+
+float16 uint16_to_float16_scalbn(uint16_t a, int scale, float_status *status)
+{
+ return uint64_to_float16_scalbn(a, scale, status);
+}
+
+float16 uint64_to_float16(uint64_t a, float_status *status)
+{
+ return uint64_to_float16_scalbn(a, 0, status);
+}
+
float16 uint32_to_float16(uint32_t a, float_status *status)
{
- return uint64_to_float16(a, status);
+ return uint64_to_float16_scalbn(a, 0, status);
}
float16 uint16_to_float16(uint16_t a, float_status *status)
{
- return uint64_to_float16(a, status);
+ return uint64_to_float16_scalbn(a, 0, status);
}
-float32 uint64_to_float32(uint64_t a, float_status *status)
+float32 uint64_to_float32_scalbn(uint64_t a, int scale, float_status *status)
{
- FloatParts pa = uint_to_float(a, status);
+ FloatParts pa = uint_to_float(a, scale, status);
return float32_round_pack_canonical(pa, status);
}
+float32 uint32_to_float32_scalbn(uint32_t a, int scale, float_status *status)
+{
+ return uint64_to_float32_scalbn(a, scale, status);
+}
+
+float32 uint16_to_float32_scalbn(uint16_t a, int scale, float_status *status)
+{
+ return uint64_to_float32_scalbn(a, scale, status);
+}
+
+float32 uint64_to_float32(uint64_t a, float_status *status)
+{
+ return uint64_to_float32_scalbn(a, 0, status);
+}
+
float32 uint32_to_float32(uint32_t a, float_status *status)
{
- return uint64_to_float32(a, status);
+ return uint64_to_float32_scalbn(a, 0, status);
}
float32 uint16_to_float32(uint16_t a, float_status *status)
{
- return uint64_to_float32(a, status);
+ return uint64_to_float32_scalbn(a, 0, status);
}
-float64 uint64_to_float64(uint64_t a, float_status *status)
+float64 uint64_to_float64_scalbn(uint64_t a, int scale, float_status *status)
{
- FloatParts pa = uint_to_float(a, status);
+ FloatParts pa = uint_to_float(a, scale, status);
return float64_round_pack_canonical(pa, status);
}
+float64 uint32_to_float64_scalbn(uint32_t a, int scale, float_status *status)
+{
+ return uint64_to_float64_scalbn(a, scale, status);
+}
+
+float64 uint16_to_float64_scalbn(uint16_t a, int scale, float_status *status)
+{
+ return uint64_to_float64_scalbn(a, scale, status);
+}
+
+float64 uint64_to_float64(uint64_t a, float_status *status)
+{
+ return uint64_to_float64_scalbn(a, 0, status);
+}
+
float64 uint32_to_float64(uint32_t a, float_status *status)
{
- return uint64_to_float64(a, status);
+ return uint64_to_float64_scalbn(a, 0, status);
}
float64 uint16_to_float64(uint16_t a, float_status *status)
{
- return uint64_to_float64(a, status);
+ return uint64_to_float64_scalbn(a, 0, status);
}
/* Float Min/Max */
/*----------------------------------------------------------------------------
| Software IEC/IEEE integer-to-floating-point conversion routines.
*----------------------------------------------------------------------------*/
+
+float16 int16_to_float16_scalbn(int16_t a, int, float_status *status);
+float16 int32_to_float16_scalbn(int32_t a, int, float_status *status);
+float16 int64_to_float16_scalbn(int64_t a, int, float_status *status);
+float16 uint16_to_float16_scalbn(uint16_t a, int, float_status *status);
+float16 uint32_to_float16_scalbn(uint32_t a, int, float_status *status);
+float16 uint64_to_float16_scalbn(uint64_t a, int, float_status *status);
+
+float16 int16_to_float16(int16_t a, float_status *status);
+float16 int32_to_float16(int32_t a, float_status *status);
+float16 int64_to_float16(int64_t a, float_status *status);
+float16 uint16_to_float16(uint16_t a, float_status *status);
+float16 uint32_to_float16(uint32_t a, float_status *status);
+float16 uint64_to_float16(uint64_t a, float_status *status);
+
+float32 int16_to_float32_scalbn(int16_t, int, float_status *status);
+float32 int32_to_float32_scalbn(int32_t, int, float_status *status);
+float32 int64_to_float32_scalbn(int64_t, int, float_status *status);
+float32 uint16_to_float32_scalbn(uint16_t, int, float_status *status);
+float32 uint32_to_float32_scalbn(uint32_t, int, float_status *status);
+float32 uint64_to_float32_scalbn(uint64_t, int, float_status *status);
+
float32 int16_to_float32(int16_t, float_status *status);
float32 int32_to_float32(int32_t, float_status *status);
-float64 int16_to_float64(int16_t, float_status *status);
-float64 int32_to_float64(int32_t, float_status *status);
+float32 int64_to_float32(int64_t, float_status *status);
float32 uint16_to_float32(uint16_t, float_status *status);
float32 uint32_to_float32(uint32_t, float_status *status);
+float32 uint64_to_float32(uint64_t, float_status *status);
+
+float64 int16_to_float64_scalbn(int16_t, int, float_status *status);
+float64 int32_to_float64_scalbn(int32_t, int, float_status *status);
+float64 int64_to_float64_scalbn(int64_t, int, float_status *status);
+float64 uint16_to_float64_scalbn(uint16_t, int, float_status *status);
+float64 uint32_to_float64_scalbn(uint32_t, int, float_status *status);
+float64 uint64_to_float64_scalbn(uint64_t, int, float_status *status);
+
+float64 int16_to_float64(int16_t, float_status *status);
+float64 int32_to_float64(int32_t, float_status *status);
+float64 int64_to_float64(int64_t, float_status *status);
float64 uint16_to_float64(uint16_t, float_status *status);
float64 uint32_to_float64(uint32_t, float_status *status);
+float64 uint64_to_float64(uint64_t, float_status *status);
+
floatx80 int32_to_floatx80(int32_t, float_status *status);
-float128 int32_to_float128(int32_t, float_status *status);
-float32 int64_to_float32(int64_t, float_status *status);
-float64 int64_to_float64(int64_t, float_status *status);
floatx80 int64_to_floatx80(int64_t, float_status *status);
+
+float128 int32_to_float128(int32_t, float_status *status);
float128 int64_to_float128(int64_t, float_status *status);
-float32 uint64_to_float32(uint64_t, float_status *status);
-float64 uint64_to_float64(uint64_t, float_status *status);
float128 uint64_to_float128(uint64_t, float_status *status);
/*----------------------------------------------------------------------------
uint64_t float16_to_uint64(float16 a, float_status *status);
int64_t float16_to_int64_round_to_zero(float16, float_status *status);
uint64_t float16_to_uint64_round_to_zero(float16 a, float_status *status);
-float16 int16_to_float16(int16_t a, float_status *status);
-float16 int32_to_float16(int32_t a, float_status *status);
-float16 int64_to_float16(int64_t a, float_status *status);
-float16 uint16_to_float16(uint16_t a, float_status *status);
-float16 uint32_to_float16(uint32_t a, float_status *status);
-float16 uint64_to_float16(uint64_t a, float_status *status);
/*----------------------------------------------------------------------------
| Software half-precision operations.