Note that for float32 we do most checks on the float32 and not on
the native type; for float64 we do the opposite. This is faster
than going either way for both, as shown below.
I am keeping both macro-based definitions to ease testing of
either option.
Performance results (single and double precision) for fp-bench
run under aarch64-linux-user on an Intel(R) Core(TM) i7-4790K
CPU @ 4.00GHz host:
- before:
add-single: 86.74 MFlops
add-double: 86.46 MFlops
sub-single: 83.33 MFlops
sub-double: 84.57 MFlops
- after this commit:
add-single: 188.89 MFlops
add-double: 172.27 MFlops
sub-single: 187.69 MFlops
sub-double: 171.89 MFlops
- w/ both using float32/64_is_normal etc.:
add-single: 187.63 MFlops
add-double: 143.51 MFlops
sub-single: 187.91 MFlops
sub-double: 144.23 MFlops
- w/ both using fpclassify etc.:
add-single: 166.61 MFlops
add-double: 172.32 MFlops
sub-single: 169.13 MFlops
sub-double: 173.09 MFlops
Signed-off-by: Emilio G. Cota <c...@braap.org>
---
fpu/softfloat.c | 120 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 112 insertions(+), 8 deletions(-)
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index ffe16b2..e0ab0ca 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -829,8 +829,8 @@ float16 __attribute__((flatten)) float16_add(float16 a,
float16 b,
return float16_round_pack_canonical(pr, status);
}
-float32 __attribute__((flatten)) float32_add(float32 a, float32 b,
- float_status *status)
+static float32 __attribute__((flatten, noinline))
+soft_float32_add(float32 a, float32 b, float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -839,8 +839,8 @@ float32 __attribute__((flatten)) float32_add(float32 a,
float32 b,
return float32_round_pack_canonical(pr, status);
}
-float64 __attribute__((flatten)) float64_add(float64 a, float64 b,
- float_status *status)
+static float64 __attribute__((flatten, noinline))
+soft_float64_add(float64 a, float64 b, float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
@@ -859,8 +859,8 @@ float16 __attribute__((flatten)) float16_sub(float16 a,
float16 b,
return float16_round_pack_canonical(pr, status);
}
-float32 __attribute__((flatten)) float32_sub(float32 a, float32 b,
- float_status *status)
+static float32 __attribute__((flatten, noinline))
+soft_float32_sub(float32 a, float32 b, float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -869,8 +869,8 @@ float32 __attribute__((flatten)) float32_sub(float32 a,
float32 b,
return float32_round_pack_canonical(pr, status);
}
-float64 __attribute__((flatten)) float64_sub(float64 a, float64 b,
- float_status *status)
+static float64 __attribute__((flatten, noinline))
+soft_float64_sub(float64 a, float64 b, float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
@@ -879,6 +879,110 @@ float64 __attribute__((flatten)) float64_sub(float64 a,
float64 b,
return float64_round_pack_canonical(pr, status);
}
+#define GEN_FPU_ADDSUB(add_name, sub_name, soft_t, host_t, \
+ host_abs_func, min_normal) \
+ static inline __attribute__((always_inline)) soft_t \
+ fpu_ ## soft_t ## _addsub(soft_t a, soft_t b, bool subtract, \
+ float_status *s) \
+ { \
+ soft_t ## _input_flush2(&a, &b, s); \
+ if (likely((soft_t ## _is_normal(a) || soft_t ## _is_zero(a)) && \
+ (soft_t ## _is_normal(b) || soft_t ## _is_zero(b)) && \
+ s->float_exception_flags & float_flag_inexact && \
+ s->float_rounding_mode == float_round_nearest_even)) { \
+ host_t ha = soft_t ## _to_ ## host_t(a); \
+ host_t hb = soft_t ## _to_ ## host_t(b); \
+ host_t hr; \
+ soft_t r; \
+ \
+ if (subtract) { \
+ hb = -hb; \
+ } \
+ hr = ha + hb; \
+ r = host_t ## _to_ ## soft_t(hr); \
+ if (unlikely(soft_t ## _is_infinity(r))) { \
+ s->float_exception_flags |= float_flag_overflow; \
+ } else if (unlikely(host_abs_func(hr) <= min_normal) && \
+ !(soft_t ## _is_zero(a) && \
+ soft_t ## _is_zero(b))) { \
+ goto soft; \
+ } \
+ return r; \
+ } \
+ soft: \
+ if (subtract) { \
+ return soft_ ## soft_t ## _sub(a, b, s); \
+ } else { \
+ return soft_ ## soft_t ## _add(a, b, s); \
+ } \
+ } \
+ \
+ soft_t add_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, false, status); \
+ } \
+ \
+ soft_t sub_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, true, status); \
+ }
+
+GEN_FPU_ADDSUB(float32_add, float32_sub, float32, float, fabsf, FLT_MIN)
+#undef GEN_FPU_ADDSUB
+
+#define GEN_FPU_ADDSUB(add_name, sub_name, soft_t, host_t, \
+ host_abs_func, min_normal) \
+ static inline __attribute__((always_inline)) soft_t \
+ fpu_ ## soft_t ## _addsub(soft_t a, soft_t b, bool subtract, \
+ float_status *s) \
+ { \
+ double ha, hb; \
+ \
+ soft_t ## _input_flush2(&a, &b, s); \
+ ha = soft_t ## _to_ ## host_t(a); \
+ hb = soft_t ## _to_ ## host_t(b); \
+ if (likely((fpclassify(ha) == FP_NORMAL || \
+ fpclassify(ha) == FP_ZERO) && \
+ (fpclassify(hb) == FP_NORMAL || \
+ fpclassify(hb) == FP_ZERO) && \
+ s->float_exception_flags & float_flag_inexact && \
+ s->float_rounding_mode == float_round_nearest_even)) { \
+ host_t hr; \
+ \
+ if (subtract) { \
+ hb = -hb; \
+ } \
+ hr = ha + hb; \
+ if (unlikely(isinf(hr))) { \
+ s->float_exception_flags |= float_flag_overflow; \
+ } else if (unlikely(host_abs_func(hr) <= min_normal) && \
+ !(soft_t ## _is_zero(a) && \
+ soft_t ## _is_zero(b))) { \
+ goto soft; \
+ } \
+ return host_t ## _to_ ## soft_t(hr); \
+ } \
+ soft: \
+ if (subtract) { \
+ return soft_ ## soft_t ## _sub(a, b, s); \
+ } else { \
+ return soft_ ## soft_t ## _add(a, b, s); \
+ } \
+ } \
+ \
+ soft_t add_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, false, status); \
+ } \
+ \
+ soft_t sub_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, true, status); \
+ }
+
+GEN_FPU_ADDSUB(float64_add, float64_sub, float64, double, fabs, DBL_MIN)
+#undef GEN_FPU_ADDSUB
+
/*
* Returns the result of multiplying the floating-point values `a' and
* `b'. The operation is performed according to the IEC/IEEE Standard
--
2.7.4
