MAINT,ENH: Rewrite scalar math logic

This commit tries to redo the scalar math logic to take some more
care about subclasses, but most of all introduce logic to defer
to the `other` if `self` can be cast to it safely (i.e. it is
the correct promotion).

This makes things much faster and more reliable, since we now use
defer much less to `ufuncs` indirectly.
This ensures that integer overflows are reported more reliably.

Another major point about it, is that this reorganizes the coercion
of Python int, float, complex (and bool).
This should help a bit with switching to "weak" Python scalars.

This may just be a first step on a longer path...

1 files changed, 12 insertions, 0 deletions

diff --git a/benchmarks/benchmarks/bench_scalar.py b/benchmarks/benchmarks/bench_scalar.py
index 219e48bed..2ad3ae670 100644
--- a/benchmarks/benchmarks/bench_scalar.py
+++ b/benchmarks/benchmarks/bench_scalar.py
@@ -10,6 +10,7 @@ class ScalarMath(Benchmark):
     param_names = ["type"]
     def setup(self, typename):
         self.num = np.dtype(typename).type(2)
+        self.int32 = np.int32(2)
 
     def time_addition(self, typename):
         n = self.num
@@ -31,3 +32,14 @@ class ScalarMath(Benchmark):
         n = self.num
         res = abs(abs(abs(abs(abs(abs(abs(abs(abs(abs(n))))))))))
 
+    def time_add_int32_other(self, typename):
+        # Some mixed cases are fast, some are slow, this documents these
+        # differences.  (When writing, it was fast if the type of the result
+        # is one of the inputs.)
+        int32 = self.int32
+        other = self.num
+        int32 + other
+        int32 + other
+        int32 + other
+        int32 + other
+        int32 + other