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:
add-single: 188.26 MFlops
add-double: 186.60 MFlops
sub-single: 186.19 MFlops
sub-double: 187.77 MFlops
Signed-off-by: Emilio G. Cota <c...@braap.org>
---
include/fpu/hostfloat.h | 6 ++++++
include/fpu/softfloat.h | 8 ++++----
fpu/hostfloat.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++
fpu/softfloat.c | 16 ++++++++--------
4 files changed, 68 insertions(+), 12 deletions(-)
diff --git a/include/fpu/hostfloat.h b/include/fpu/hostfloat.h
index b01291b..db49efa 100644
--- a/include/fpu/hostfloat.h
+++ b/include/fpu/hostfloat.h
@@ -11,4 +11,10 @@
#error fpu/hostfloat.h must only be included from softfloat.h
#endif
+float32 float32_add(float32 a, float32 b, float_status *status);
+float32 float32_sub(float32 a, float32 b, float_status *status);
+
+float64 float64_add(float64 a, float64 b, float_status *status);
+float64 float64_sub(float64 a, float64 b, float_status *status);
+
#endif /* HOSTFLOAT_H */
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index 8963b68..eb7e9bc 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -342,8 +342,8 @@ float128 float32_to_float128(float32, float_status *status);
| Software IEC/IEEE single-precision operations.
*----------------------------------------------------------------------------*/
float32 float32_round_to_int(float32, float_status *status);
-float32 float32_add(float32, float32, float_status *status);
-float32 float32_sub(float32, float32, float_status *status);
+float32 soft_float32_add(float32, float32, float_status *status);
+float32 soft_float32_sub(float32, float32, float_status *status);
float32 float32_mul(float32, float32, float_status *status);
float32 float32_div(float32, float32, float_status *status);
float32 float32_rem(float32, float32, float_status *status);
@@ -482,8 +482,8 @@ float128 float64_to_float128(float64, float_status *status);
*----------------------------------------------------------------------------*/
float64 float64_round_to_int(float64, float_status *status);
float64 float64_trunc_to_int(float64, float_status *status);
-float64 float64_add(float64, float64, float_status *status);
-float64 float64_sub(float64, float64, float_status *status);
+float64 soft_float64_add(float64, float64, float_status *status);
+float64 soft_float64_sub(float64, float64, float_status *status);
float64 float64_mul(float64, float64, float_status *status);
float64 float64_div(float64, float64, float_status *status);
float64 float64_rem(float64, float64, float_status *status);
diff --git a/fpu/hostfloat.c b/fpu/hostfloat.c
index cab0341..502552b 100644
--- a/fpu/hostfloat.c
+++ b/fpu/hostfloat.c
@@ -94,3 +94,53 @@ GEN_TYPE_CONV(double_to_float64, float64, double)
GEN_INPUT_FLUSH(float32)
GEN_INPUT_FLUSH(float64)
#undef GEN_INPUT_FLUSH
+
+#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)) { \
+ 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)
+GEN_FPU_ADDSUB(float64_add, float64_sub, float64, double, fabs, DBL_MIN)
+#undef GEN_FPU_ADDSUB
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index ee615a9..bd82adf 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -738,8 +738,8 @@ 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)
+float32 __attribute__((flatten)) soft_float32_add(float32 a, float32 b,
+ float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -748,8 +748,8 @@ 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)
+float64 __attribute__((flatten)) soft_float64_add(float64 a, float64 b,
+ float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
@@ -768,8 +768,8 @@ 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)
+float32 __attribute__((flatten)) soft_float32_sub(float32 a, float32 b,
+ float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -778,8 +778,8 @@ 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)
+float64 __attribute__((flatten)) soft_float64_sub(float64 a, float64 b,
+ float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
--
2.7.4
