diff options
Diffstat (limited to 'fpu/softfloat.c')
| -rw-r--r-- | fpu/softfloat.c | 425 |
1 files changed, 425 insertions, 0 deletions
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 33abc8207b..67cfa0fd82 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -554,6 +554,10 @@ static const FloatFmt float16_params_ahp = { .arm_althp = true }; +static const FloatFmt bfloat16_params = { + FLOAT_PARAMS(8, 7) +}; + static const FloatFmt float32_params = { FLOAT_PARAMS(8, 23) }; @@ -580,6 +584,11 @@ static inline FloatParts float16_unpack_raw(float16 f) return unpack_raw(float16_params, f); } +static inline FloatParts bfloat16_unpack_raw(bfloat16 f) +{ + return unpack_raw(bfloat16_params, f); +} + static inline FloatParts float32_unpack_raw(float32 f) { return unpack_raw(float32_params, f); @@ -603,6 +612,11 @@ static inline float16 float16_pack_raw(FloatParts p) return make_float16(pack_raw(float16_params, p)); } +static inline bfloat16 bfloat16_pack_raw(FloatParts p) +{ + return pack_raw(bfloat16_params, p); +} + static inline float32 float32_pack_raw(FloatParts p) { return make_float32(pack_raw(float32_params, p)); @@ -820,6 +834,11 @@ static FloatParts float16_unpack_canonical(float16 f, float_status *s) return float16a_unpack_canonical(f, s, &float16_params); } +static FloatParts bfloat16_unpack_canonical(bfloat16 f, float_status *s) +{ + return sf_canonicalize(bfloat16_unpack_raw(f), &bfloat16_params, s); +} + static float16 float16a_round_pack_canonical(FloatParts p, float_status *s, const FloatFmt *params) { @@ -831,6 +850,11 @@ static float16 float16_round_pack_canonical(FloatParts p, float_status *s) return float16a_round_pack_canonical(p, s, &float16_params); } +static bfloat16 bfloat16_round_pack_canonical(FloatParts p, float_status *s) +{ + return bfloat16_pack_raw(round_canonical(p, s, &bfloat16_params)); +} + static FloatParts float32_unpack_canonical(float32 f, float_status *s) { return sf_canonicalize(float32_unpack_raw(f), &float32_params, s); @@ -1159,6 +1183,28 @@ float64_sub(float64 a, float64 b, float_status *s) } /* + * Returns the result of adding or subtracting the bfloat16 + * values `a' and `b'. + */ +bfloat16 QEMU_FLATTEN bfloat16_add(bfloat16 a, bfloat16 b, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pb = bfloat16_unpack_canonical(b, status); + FloatParts pr = addsub_floats(pa, pb, false, status); + + return bfloat16_round_pack_canonical(pr, status); +} + +bfloat16 QEMU_FLATTEN bfloat16_sub(bfloat16 a, bfloat16 b, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pb = bfloat16_unpack_canonical(b, status); + FloatParts pr = addsub_floats(pa, pb, true, status); + + return bfloat16_round_pack_canonical(pr, status); +} + +/* * Returns the result of multiplying the floating-point values `a' and * `b'. The operation is performed according to the IEC/IEEE Standard * for Binary Floating-Point Arithmetic. @@ -1261,6 +1307,20 @@ float64_mul(float64 a, float64 b, float_status *s) } /* + * Returns the result of multiplying the bfloat16 + * values `a' and `b'. + */ + +bfloat16 QEMU_FLATTEN bfloat16_mul(bfloat16 a, bfloat16 b, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pb = bfloat16_unpack_canonical(b, status); + FloatParts pr = mul_floats(pa, pb, status); + + return bfloat16_round_pack_canonical(pr, status); +} + +/* * Returns the result of multiplying the floating-point values `a' and * `b' then adding 'c', with no intermediate rounding step after the * multiplication. The operation is performed according to the @@ -1643,6 +1703,23 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s) } /* + * Returns the result of multiplying the bfloat16 values `a' + * and `b' then adding 'c', with no intermediate rounding step after the + * multiplication. + */ + +bfloat16 QEMU_FLATTEN bfloat16_muladd(bfloat16 a, bfloat16 b, bfloat16 c, + int flags, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pb = bfloat16_unpack_canonical(b, status); + FloatParts pc = bfloat16_unpack_canonical(c, status); + FloatParts pr = muladd_floats(pa, pb, pc, flags, status); + + return bfloat16_round_pack_canonical(pr, status); +} + +/* * Returns the result of dividing the floating-point value `a' by the * corresponding value `b'. The operation is performed according to * the IEC/IEEE Standard for Binary Floating-Point Arithmetic. @@ -1809,6 +1886,20 @@ float64_div(float64 a, float64 b, float_status *s) } /* + * Returns the result of dividing the bfloat16 + * value `a' by the corresponding value `b'. + */ + +bfloat16 bfloat16_div(bfloat16 a, bfloat16 b, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pb = bfloat16_unpack_canonical(b, status); + FloatParts pr = div_floats(pa, pb, status); + + return bfloat16_round_pack_canonical(pr, status); +} + +/* * Float to Float conversions * * Returns the result of converting one float format to another. The @@ -1923,6 +2014,34 @@ float32 float64_to_float32(float64 a, float_status *s) return float32_round_pack_canonical(pr, s); } +float32 bfloat16_to_float32(bfloat16 a, float_status *s) +{ + FloatParts p = bfloat16_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &float32_params, s); + return float32_round_pack_canonical(pr, s); +} + +float64 bfloat16_to_float64(bfloat16 a, float_status *s) +{ + FloatParts p = bfloat16_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &float64_params, s); + return float64_round_pack_canonical(pr, s); +} + +bfloat16 float32_to_bfloat16(float32 a, float_status *s) +{ + FloatParts p = float32_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &bfloat16_params, s); + return bfloat16_round_pack_canonical(pr, s); +} + +bfloat16 float64_to_bfloat16(float64 a, float_status *s) +{ + FloatParts p = float64_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &bfloat16_params, s); + return bfloat16_round_pack_canonical(pr, s); +} + /* * Rounds the floating-point value `a' to an integer, and returns the * result as a floating-point value. The operation is performed @@ -2053,6 +2172,18 @@ float64 float64_round_to_int(float64 a, float_status *s) } /* + * Rounds the bfloat16 value `a' to an integer, and returns the + * result as a bfloat16 value. + */ + +bfloat16 bfloat16_round_to_int(bfloat16 a, float_status *s) +{ + FloatParts pa = bfloat16_unpack_canonical(a, s); + FloatParts pr = round_to_int(pa, s->float_rounding_mode, 0, s); + return bfloat16_round_pack_canonical(pr, s); +} + +/* * Returns the result of converting the floating-point value `a' to * the two's complement integer format. The conversion is performed * according to the IEC/IEEE Standard for Binary Floating-Point @@ -2109,6 +2240,13 @@ static int64_t round_to_int_and_pack(FloatParts in, FloatRoundMode rmode, } } +int8_t float16_to_int8_scalbn(float16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + return round_to_int_and_pack(float16_unpack_canonical(a, s), + rmode, scale, INT8_MIN, INT8_MAX, s); +} + int16_t float16_to_int16_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { @@ -2172,6 +2310,11 @@ int64_t float64_to_int64_scalbn(float64 a, FloatRoundMode rmode, int scale, rmode, scale, INT64_MIN, INT64_MAX, s); } +int8_t float16_to_int8(float16 a, float_status *s) +{ + return float16_to_int8_scalbn(a, s->float_rounding_mode, 0, s); +} + int16_t float16_to_int16(float16 a, float_status *s) { return float16_to_int16_scalbn(a, s->float_rounding_mode, 0, s); @@ -2263,6 +2406,62 @@ int64_t float64_to_int64_round_to_zero(float64 a, float_status *s) } /* + * Returns the result of converting the floating-point value `a' to + * the two's complement integer format. + */ + +int16_t bfloat16_to_int16_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, INT16_MIN, INT16_MAX, s); +} + +int32_t bfloat16_to_int32_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, INT32_MIN, INT32_MAX, s); +} + +int64_t bfloat16_to_int64_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, INT64_MIN, INT64_MAX, s); +} + +int16_t bfloat16_to_int16(bfloat16 a, float_status *s) +{ + return bfloat16_to_int16_scalbn(a, s->float_rounding_mode, 0, s); +} + +int32_t bfloat16_to_int32(bfloat16 a, float_status *s) +{ + return bfloat16_to_int32_scalbn(a, s->float_rounding_mode, 0, s); +} + +int64_t bfloat16_to_int64(bfloat16 a, float_status *s) +{ + return bfloat16_to_int64_scalbn(a, s->float_rounding_mode, 0, s); +} + +int16_t bfloat16_to_int16_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_int16_scalbn(a, float_round_to_zero, 0, s); +} + +int32_t bfloat16_to_int32_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_int32_scalbn(a, float_round_to_zero, 0, s); +} + +int64_t bfloat16_to_int64_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_int64_scalbn(a, float_round_to_zero, 0, s); +} + +/* * Returns the result of converting the floating-point value `a' to * the unsigned integer format. The conversion is performed according * to the IEC/IEEE Standard for Binary Floating-Point @@ -2322,6 +2521,13 @@ static uint64_t round_to_uint_and_pack(FloatParts in, FloatRoundMode rmode, } } +uint8_t float16_to_uint8_scalbn(float16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + return round_to_uint_and_pack(float16_unpack_canonical(a, s), + rmode, scale, UINT8_MAX, s); +} + uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { @@ -2385,6 +2591,11 @@ uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale, rmode, scale, UINT64_MAX, s); } +uint8_t float16_to_uint8(float16 a, float_status *s) +{ + return float16_to_uint8_scalbn(a, s->float_rounding_mode, 0, s); +} + uint16_t float16_to_uint16(float16 a, float_status *s) { return float16_to_uint16_scalbn(a, s->float_rounding_mode, 0, s); @@ -2476,6 +2687,62 @@ uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *s) } /* + * Returns the result of converting the bfloat16 value `a' to + * the unsigned integer format. + */ + +uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, UINT16_MAX, s); +} + +uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, UINT32_MAX, s); +} + +uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), + rmode, scale, UINT64_MAX, s); +} + +uint16_t bfloat16_to_uint16(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint16_scalbn(a, s->float_rounding_mode, 0, s); +} + +uint32_t bfloat16_to_uint32(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint32_scalbn(a, s->float_rounding_mode, 0, s); +} + +uint64_t bfloat16_to_uint64(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint64_scalbn(a, s->float_rounding_mode, 0, s); +} + +uint16_t bfloat16_to_uint16_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint16_scalbn(a, float_round_to_zero, 0, s); +} + +uint32_t bfloat16_to_uint32_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint32_scalbn(a, float_round_to_zero, 0, s); +} + +uint64_t bfloat16_to_uint64_round_to_zero(bfloat16 a, float_status *s) +{ + return bfloat16_to_uint64_scalbn(a, float_round_to_zero, 0, s); +} + +/* * Integer to float conversions * * Returns the result of converting the two's complement integer `a' @@ -2539,6 +2806,11 @@ float16 int16_to_float16(int16_t a, float_status *status) return int64_to_float16_scalbn(a, 0, status); } +float16 int8_to_float16(int8_t a, float_status *status) +{ + return int64_to_float16_scalbn(a, 0, status); +} + float32 int64_to_float32_scalbn(int64_t a, int scale, float_status *status) { FloatParts pa = int_to_float(a, scale, status); @@ -2601,6 +2873,41 @@ float64 int16_to_float64(int16_t a, float_status *status) return int64_to_float64_scalbn(a, 0, status); } +/* + * Returns the result of converting the two's complement integer `a' + * to the bfloat16 format. + */ + +bfloat16 int64_to_bfloat16_scalbn(int64_t a, int scale, float_status *status) +{ + FloatParts pa = int_to_float(a, scale, status); + return bfloat16_round_pack_canonical(pa, status); +} + +bfloat16 int32_to_bfloat16_scalbn(int32_t a, int scale, float_status *status) +{ + return int64_to_bfloat16_scalbn(a, scale, status); +} + +bfloat16 int16_to_bfloat16_scalbn(int16_t a, int scale, float_status *status) +{ + return int64_to_bfloat16_scalbn(a, scale, status); +} + +bfloat16 int64_to_bfloat16(int64_t a, float_status *status) +{ + return int64_to_bfloat16_scalbn(a, 0, status); +} + +bfloat16 int32_to_bfloat16(int32_t a, float_status *status) +{ + return int64_to_bfloat16_scalbn(a, 0, status); +} + +bfloat16 int16_to_bfloat16(int16_t a, float_status *status) +{ + return int64_to_bfloat16_scalbn(a, 0, status); +} /* * Unsigned Integer to float conversions @@ -2664,6 +2971,11 @@ float16 uint16_to_float16(uint16_t a, float_status *status) return uint64_to_float16_scalbn(a, 0, status); } +float16 uint8_to_float16(uint8_t a, float_status *status) +{ + return uint64_to_float16_scalbn(a, 0, status); +} + float32 uint64_to_float32_scalbn(uint64_t a, int scale, float_status *status) { FloatParts pa = uint_to_float(a, scale, status); @@ -2726,6 +3038,42 @@ float64 uint16_to_float64(uint16_t a, float_status *status) return uint64_to_float64_scalbn(a, 0, status); } +/* + * Returns the result of converting the unsigned integer `a' to the + * bfloat16 format. + */ + +bfloat16 uint64_to_bfloat16_scalbn(uint64_t a, int scale, float_status *status) +{ + FloatParts pa = uint_to_float(a, scale, status); + return bfloat16_round_pack_canonical(pa, status); +} + +bfloat16 uint32_to_bfloat16_scalbn(uint32_t a, int scale, float_status *status) +{ + return uint64_to_bfloat16_scalbn(a, scale, status); +} + +bfloat16 uint16_to_bfloat16_scalbn(uint16_t a, int scale, float_status *status) +{ + return uint64_to_bfloat16_scalbn(a, scale, status); +} + +bfloat16 uint64_to_bfloat16(uint64_t a, float_status *status) +{ + return uint64_to_bfloat16_scalbn(a, 0, status); +} + +bfloat16 uint32_to_bfloat16(uint32_t a, float_status *status) +{ + return uint64_to_bfloat16_scalbn(a, 0, status); +} + +bfloat16 uint16_to_bfloat16(uint16_t a, float_status *status) +{ + return uint64_to_bfloat16_scalbn(a, 0, status); +} + /* Float Min/Max */ /* min() and max() functions. These can't be implemented as * 'compare and pick one input' because that would mishandle @@ -2847,6 +3195,25 @@ MINMAX(64, maxnummag, false, true, true) #undef MINMAX +#define BF16_MINMAX(name, ismin, isiee, ismag) \ +bfloat16 bfloat16_ ## name(bfloat16 a, bfloat16 b, float_status *s) \ +{ \ + FloatParts pa = bfloat16_unpack_canonical(a, s); \ + FloatParts pb = bfloat16_unpack_canonical(b, s); \ + FloatParts pr = minmax_floats(pa, pb, ismin, isiee, ismag, s); \ + \ + return bfloat16_round_pack_canonical(pr, s); \ +} + +BF16_MINMAX(min, true, false, false) +BF16_MINMAX(minnum, true, true, false) +BF16_MINMAX(minnummag, true, true, true) +BF16_MINMAX(max, false, false, false) +BF16_MINMAX(maxnum, false, true, false) +BF16_MINMAX(maxnummag, false, true, true) + +#undef BF16_MINMAX + /* Floating point compare */ static FloatRelation compare_floats(FloatParts a, FloatParts b, bool is_quiet, float_status *s) @@ -3008,6 +3375,24 @@ FloatRelation float64_compare_quiet(float64 a, float64 b, float_status *s) return f64_compare(a, b, true, s); } +static FloatRelation QEMU_FLATTEN +soft_bf16_compare(bfloat16 a, bfloat16 b, bool is_quiet, float_status *s) +{ + FloatParts pa = bfloat16_unpack_canonical(a, s); + FloatParts pb = bfloat16_unpack_canonical(b, s); + return compare_floats(pa, pb, is_quiet, s); +} + +FloatRelation bfloat16_compare(bfloat16 a, bfloat16 b, float_status *s) +{ + return soft_bf16_compare(a, b, false, s); +} + +FloatRelation bfloat16_compare_quiet(bfloat16 a, bfloat16 b, float_status *s) +{ + return soft_bf16_compare(a, b, true, s); +} + /* Multiply A by 2 raised to the power N. */ static FloatParts scalbn_decomposed(FloatParts a, int n, float_status *s) { @@ -3047,6 +3432,13 @@ float64 float64_scalbn(float64 a, int n, float_status *status) return float64_round_pack_canonical(pr, status); } +bfloat16 bfloat16_scalbn(bfloat16 a, int n, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pr = scalbn_decomposed(pa, n, status); + return bfloat16_round_pack_canonical(pr, status); +} + /* * Square Root * @@ -3197,6 +3589,13 @@ float64 QEMU_FLATTEN float64_sqrt(float64 xa, float_status *s) return soft_f64_sqrt(ua.s, s); } +bfloat16 QEMU_FLATTEN bfloat16_sqrt(bfloat16 a, float_status *status) +{ + FloatParts pa = bfloat16_unpack_canonical(a, status); + FloatParts pr = sqrt_float(pa, status, &bfloat16_params); + return bfloat16_round_pack_canonical(pr, status); +} + /*---------------------------------------------------------------------------- | The pattern for a default generated NaN. *----------------------------------------------------------------------------*/ @@ -3239,6 +3638,13 @@ float128 float128_default_nan(float_status *status) return r; } +bfloat16 bfloat16_default_nan(float_status *status) +{ + FloatParts p = parts_default_nan(status); + p.frac >>= bfloat16_params.frac_shift; + return bfloat16_pack_raw(p); +} + /*---------------------------------------------------------------------------- | Returns a quiet NaN from a signalling NaN for the floating point value `a'. *----------------------------------------------------------------------------*/ @@ -3270,6 +3676,14 @@ float64 float64_silence_nan(float64 a, float_status *status) return float64_pack_raw(p); } +bfloat16 bfloat16_silence_nan(bfloat16 a, float_status *status) +{ + FloatParts p = bfloat16_unpack_raw(a); + p.frac <<= bfloat16_params.frac_shift; + p = parts_silence_nan(p, status); + p.frac >>= bfloat16_params.frac_shift; + return bfloat16_pack_raw(p); +} /*---------------------------------------------------------------------------- | If `a' is denormal and we are in flush-to-zero mode then set the @@ -3319,6 +3733,17 @@ float64 float64_squash_input_denormal(float64 a, float_status *status) return a; } +bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status) +{ + if (status->flush_inputs_to_zero) { + FloatParts p = bfloat16_unpack_raw(a); + if (parts_squash_denormal(p, status)) { + return bfloat16_set_sign(bfloat16_zero, p.sign); + } + } + return a; +} + /*---------------------------------------------------------------------------- | Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 | and 7, and returns the properly rounded 32-bit integer corresponding to the |