| Message ID | 20200924012453.659757-5-richard.henderson@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | softfloat: Implement float128_muladd | expand |
On 24.09.20 03:24, Richard Henderson wrote: > Testing more than one class at a time is better done with masks. > This reduces the static branch count. > > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > fpu/softfloat.c | 31 ++++++++++++++++++++++++------- > 1 file changed, 24 insertions(+), 7 deletions(-) > > diff --git a/fpu/softfloat.c b/fpu/softfloat.c > index 9db55d2b11..3e625c47cd 100644 > --- a/fpu/softfloat.c > +++ b/fpu/softfloat.c > @@ -469,6 +469,20 @@ typedef enum __attribute__ ((__packed__)) { > float_class_snan, > } FloatClass; > > +#define float_cmask(bit) (1u << (bit)) > + > +enum { > + float_cmask_zero = float_cmask(float_class_zero), > + float_cmask_normal = float_cmask(float_class_normal), > + float_cmask_inf = float_cmask(float_class_inf), > + float_cmask_qnan = float_cmask(float_class_qnan), > + float_cmask_snan = float_cmask(float_class_snan), > + > + float_cmask_infzero = float_cmask_zero | float_cmask_inf, > + float_cmask_anynan = float_cmask_qnan | float_cmask_snan, > +}; > + > + > /* Simple helpers for checking if, or what kind of, NaN we have */ > static inline __attribute__((unused)) bool is_nan(FloatClass c) > { > @@ -1335,24 +1349,27 @@ bfloat16 QEMU_FLATTEN bfloat16_mul(bfloat16 a, bfloat16 b, float_status *status) > static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, > int flags, float_status *s) > { > - bool inf_zero = ((1 << a.cls) | (1 << b.cls)) == > - ((1 << float_class_inf) | (1 << float_class_zero)); > - bool p_sign; > + bool inf_zero, p_sign; > bool sign_flip = flags & float_muladd_negate_result; > FloatClass p_class; > uint64_t hi, lo; > int p_exp; > + int ab_mask, abc_mask; > + > + ab_mask = float_cmask(a.cls) | float_cmask(b.cls); > + abc_mask = float_cmask(c.cls) | ab_mask; > + inf_zero = ab_mask == float_cmask_infzero; > > /* It is implementation-defined whether the cases of (0,inf,qnan) > * and (inf,0,qnan) raise InvalidOperation or not (and what QNaN > * they return if they do), so we have to hand this information > * off to the target-specific pick-a-NaN routine. > */ > - if (is_nan(a.cls) || is_nan(b.cls) || is_nan(c.cls)) { > + if (unlikely(abc_mask & float_cmask_anynan)) { > return pick_nan_muladd(a, b, c, inf_zero, s); > } > > - if (inf_zero) { > + if (unlikely(inf_zero)) { > s->float_exception_flags |= float_flag_invalid; > return parts_default_nan(s); > } > @@ -1367,9 +1384,9 @@ static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, > p_sign ^= 1; > } > > - if (a.cls == float_class_inf || b.cls == float_class_inf) { > + if (ab_mask & float_cmask_inf) { > p_class = float_class_inf; > - } else if (a.cls == float_class_zero || b.cls == float_class_zero) { > + } else if (ab_mask & float_cmask_zero) { > p_class = float_class_zero; > } else { > p_class = float_class_normal; > Reviewed-by: David Hildenbrand <david@redhat.com> -- Thanks, David / dhildenb
diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 9db55d2b11..3e625c47cd 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -469,6 +469,20 @@ typedef enum __attribute__ ((__packed__)) { float_class_snan, } FloatClass; +#define float_cmask(bit) (1u << (bit)) + +enum { + float_cmask_zero = float_cmask(float_class_zero), + float_cmask_normal = float_cmask(float_class_normal), + float_cmask_inf = float_cmask(float_class_inf), + float_cmask_qnan = float_cmask(float_class_qnan), + float_cmask_snan = float_cmask(float_class_snan), + + float_cmask_infzero = float_cmask_zero | float_cmask_inf, + float_cmask_anynan = float_cmask_qnan | float_cmask_snan, +}; + + /* Simple helpers for checking if, or what kind of, NaN we have */ static inline __attribute__((unused)) bool is_nan(FloatClass c) { @@ -1335,24 +1349,27 @@ bfloat16 QEMU_FLATTEN bfloat16_mul(bfloat16 a, bfloat16 b, float_status *status) static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, int flags, float_status *s) { - bool inf_zero = ((1 << a.cls) | (1 << b.cls)) == - ((1 << float_class_inf) | (1 << float_class_zero)); - bool p_sign; + bool inf_zero, p_sign; bool sign_flip = flags & float_muladd_negate_result; FloatClass p_class; uint64_t hi, lo; int p_exp; + int ab_mask, abc_mask; + + ab_mask = float_cmask(a.cls) | float_cmask(b.cls); + abc_mask = float_cmask(c.cls) | ab_mask; + inf_zero = ab_mask == float_cmask_infzero; /* It is implementation-defined whether the cases of (0,inf,qnan) * and (inf,0,qnan) raise InvalidOperation or not (and what QNaN * they return if they do), so we have to hand this information * off to the target-specific pick-a-NaN routine. */ - if (is_nan(a.cls) || is_nan(b.cls) || is_nan(c.cls)) { + if (unlikely(abc_mask & float_cmask_anynan)) { return pick_nan_muladd(a, b, c, inf_zero, s); } - if (inf_zero) { + if (unlikely(inf_zero)) { s->float_exception_flags |= float_flag_invalid; return parts_default_nan(s); } @@ -1367,9 +1384,9 @@ static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, p_sign ^= 1; } - if (a.cls == float_class_inf || b.cls == float_class_inf) { + if (ab_mask & float_cmask_inf) { p_class = float_class_inf; - } else if (a.cls == float_class_zero || b.cls == float_class_zero) { + } else if (ab_mask & float_cmask_zero) { p_class = float_class_zero; } else { p_class = float_class_normal;
Testing more than one class at a time is better done with masks. This reduces the static branch count. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- fpu/softfloat.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-)