softfloat: Use hard-float for {u}int64_to_float{32,64}

For the normal case of no additional scaling, this reduces the
profile contribution of int64_to_float64 to the testcase in the
linked issue from 0.81% to 0.04%.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/134
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 28 insertions, 0 deletions

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 5026f518b0..1cb162882b 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -3559,6 +3559,13 @@ float32 int64_to_float32_scalbn(int64_t a, int scale, float_status *status)
 {
     FloatParts64 p;
 
+    /* Without scaling, there are no overflow concerns. */
+    if (likely(scale == 0) && can_use_fpu(status)) {
+        union_float32 ur;
+        ur.h = a;
+        return ur.s;
+    }
+
     parts64_sint_to_float(&p, a, scale, status);
     return float32_round_pack_canonical(&p, status);
 }
@@ -3592,6 +3599,13 @@ float64 int64_to_float64_scalbn(int64_t a, int scale, float_status *status)
 {
     FloatParts64 p;
 
+    /* Without scaling, there are no overflow concerns. */
+    if (likely(scale == 0) && can_use_fpu(status)) {
+        union_float64 ur;
+        ur.h = a;
+        return ur.s;
+    }
+
     parts_sint_to_float(&p, a, scale, status);
     return float64_round_pack_canonical(&p, status);
 }
@@ -3726,6 +3740,13 @@ float32 uint64_to_float32_scalbn(uint64_t a, int scale, float_status *status)
 {
     FloatParts64 p;
 
+    /* Without scaling, there are no overflow concerns. */
+    if (likely(scale == 0) && can_use_fpu(status)) {
+        union_float32 ur;
+        ur.h = a;
+        return ur.s;
+    }
+
     parts_uint_to_float(&p, a, scale, status);
     return float32_round_pack_canonical(&p, status);
 }
@@ -3759,6 +3780,13 @@ float64 uint64_to_float64_scalbn(uint64_t a, int scale, float_status *status)
 {
     FloatParts64 p;
 
+    /* Without scaling, there are no overflow concerns. */
+    if (likely(scale == 0) && can_use_fpu(status)) {
+        union_float64 ur;
+        ur.h = a;
+        return ur.s;
+    }
+
     parts_uint_to_float(&p, a, scale, status);
     return float64_round_pack_canonical(&p, status);
 }