Performance results included in the following commit's log.
Signed-off-by: Emilio G. Cota <c...@braap.org>
---
include/fpu/hostfloat.h | 4 ++++
include/fpu/softfloat.h | 6 ++----
fpu/hostfloat.c | 36 ++++++++++++++++++++++++++++++++++++
fpu/softfloat.c | 34 ++++++++++++++++++++--------------
4 files changed, 62 insertions(+), 18 deletions(-)
diff --git a/include/fpu/hostfloat.h b/include/fpu/hostfloat.h
index b1e0689..aa555f6 100644
--- a/include/fpu/hostfloat.h
+++ b/include/fpu/hostfloat.h
@@ -17,6 +17,8 @@ float32 float32_mul(float32 a, float32 b, float_status
*status);
float32 float32_div(float32 a, float32 b, float_status *status);
float32 float32_muladd(float32 a, float32 b, float32 c, int f, float_status
*s);
float32 float32_sqrt(float32 a, float_status *status);
+int float32_compare(float32 a, float32 b, float_status *s);
+int float32_compare_quiet(float32 a, float32 b, float_status *s);
float64 float64_add(float64 a, float64 b, float_status *status);
float64 float64_sub(float64 a, float64 b, float_status *status);
@@ -24,5 +26,7 @@ float64 float64_mul(float64 a, float64 b, float_status
*status);
float64 float64_div(float64 a, float64 b, float_status *status);
float64 float64_muladd(float64 a, float64 b, float64 c, int f, float_status
*s);
float64 float64_sqrt(float64 a, float_status *status);
+int float64_compare(float64 a, float64 b, float_status *s);
+int float64_compare_quiet(float64 a, float64 b, float_status *s);
#endif /* HOSTFLOAT_H */
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index 8d5a50a..cb57942 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -359,8 +359,7 @@ int float32_eq_quiet(float32, float32, float_status
*status);
int float32_le_quiet(float32, float32, float_status *status);
int float32_lt_quiet(float32, float32, float_status *status);
int float32_unordered_quiet(float32, float32, float_status *status);
-int float32_compare(float32, float32, float_status *status);
-int float32_compare_quiet(float32, float32, float_status *status);
+int soft_float32_compare(float32, float32, bool is_quiet, float_status
*status);
float32 float32_min(float32, float32, float_status *status);
float32 float32_max(float32, float32, float_status *status);
float32 float32_minnum(float32, float32, float_status *status);
@@ -498,8 +497,7 @@ int float64_eq_quiet(float64, float64, float_status
*status);
int float64_le_quiet(float64, float64, float_status *status);
int float64_lt_quiet(float64, float64, float_status *status);
int float64_unordered_quiet(float64, float64, float_status *status);
-int float64_compare(float64, float64, float_status *status);
-int float64_compare_quiet(float64, float64, float_status *status);
+int soft_float64_compare(float64, float64, bool is_quiet, float_status
*status);
float64 float64_min(float64, float64, float_status *status);
float64 float64_max(float64, float64, float_status *status);
float64 float64_minnum(float64, float64, float_status *status);
diff --git a/fpu/hostfloat.c b/fpu/hostfloat.c
index 974bd57..139e419 100644
--- a/fpu/hostfloat.c
+++ b/fpu/hostfloat.c
@@ -290,3 +290,39 @@ GEN_FPU_FMA(float64_muladd, float64, double, fma, fabs,
DBL_MIN)
GEN_FPU_SQRT(float32_sqrt, float32, float, sqrtf)
GEN_FPU_SQRT(float64_sqrt, float64, double, sqrt)
#undef GEN_FPU_SQRT
+
+#define GEN_FPU_COMPARE(name, soft_t, host_t) \
+ static inline __attribute__((always_inline)) int \
+ fpu_ ## name(soft_t a, soft_t b, bool is_quiet, float_status *s) \
+ { \
+ soft_t ## _input_flush2(&a, &b, s); \
+ if (unlikely(soft_t ## _is_any_nan(a) || \
+ soft_t ## _is_any_nan(b))) { \
+ return soft_ ## name(a, b, is_quiet, s); \
+ } else { \
+ host_t ha = soft_t ## _to_ ## host_t(a); \
+ host_t hb = soft_t ## _to_ ## host_t(b); \
+ \
+ if (isgreater(ha, hb)) { \
+ return float_relation_greater; \
+ } \
+ if (isless(ha, hb)) { \
+ return float_relation_less; \
+ } \
+ return float_relation_equal; \
+ } \
+ } \
+ \
+ int name(soft_t a, soft_t b, float_status *s) \
+ { \
+ return fpu_ ## name(a, b, false, s); \
+ } \
+ \
+ int name ## _quiet(soft_t a, soft_t b, float_status *s) \
+ { \
+ return fpu_ ## name(a, b, true, s); \
+ }
+
+GEN_FPU_COMPARE(float32_compare, float32, float)
+GEN_FPU_COMPARE(float64_compare, float64, double)
+#undef GEN_FPU_COMPARE
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 096b658..1a32216 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -1844,28 +1844,34 @@ static int compare_floats(FloatParts a, FloatParts b,
bool is_quiet,
}
}
-#define COMPARE(sz) \
-int float ## sz ## _compare(float ## sz a, float ## sz b, \
- float_status *s) \
+#define COMPARE(storage_class, sz) \
+storage_class int \
+soft_float ## sz ## _compare(float ## sz a, float ## sz b, \
+ bool is_quiet, float_status *s) \
{ \
FloatParts pa = float ## sz ## _unpack_canonical(a, s); \
FloatParts pb = float ## sz ## _unpack_canonical(b, s); \
- return compare_floats(pa, pb, false, s); \
-} \
-int float ## sz ## _compare_quiet(float ## sz a, float ## sz b, \
- float_status *s) \
-{ \
- FloatParts pa = float ## sz ## _unpack_canonical(a, s); \
- FloatParts pb = float ## sz ## _unpack_canonical(b, s); \
- return compare_floats(pa, pb, true, s); \
+ return compare_floats(pa, pb, is_quiet, s); \
}
-COMPARE(16)
-COMPARE(32)
-COMPARE(64)
+COMPARE(static, 16)
+COMPARE(, 32)
+COMPARE(, 64)
#undef COMPARE
+int __attribute__((flatten))
+float16_compare(float16 a, float16 b, float_status *s)
+{
+ return soft_float16_compare(a, b, false, s);
+}
+
+int __attribute__((flatten))
+float16_compare_quiet(float16 a, float16 b, float_status *s)
+{
+ return soft_float16_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)
{
--
2.7.4
