Merge pull request #5111 from larsmans/fast-bool

ENH: faster (branchless) logical_xor

2 files changed, 40 insertions, 18 deletions

diff --git a/numpy/core/src/umath/loops.c.src b/numpy/core/src/umath/loops.c.src
index d747864f8..14076f3fa 100644
--- a/numpy/core/src/umath/loops.c.src
+++ b/numpy/core/src/umath/loops.c.src
@@ -838,9 +838,9 @@ NPY_NO_EXPORT void
 @TYPE@_logical_xor(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func))
 {
     BINARY_LOOP {
-        const @type@ in1 = *(@type@ *)ip1;
-        const @type@ in2 = *(@type@ *)ip2;
-        *((npy_bool *)op1)= (in1 && !in2) || (!in1 && in2);
+        const int t1 = !!*(@type@ *)ip1;
+        const int t2 = !!*(@type@ *)ip2;
+        *((npy_bool *)op1) = (t1 != t2);
     }
 }
 
@@ -1515,9 +1515,9 @@ NPY_NO_EXPORT void
 @TYPE@_logical_xor(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUSED(func))
 {
     BINARY_LOOP {
-        const @type@ in1 = *(@type@ *)ip1;
-        const @type@ in2 = *(@type@ *)ip2;
-        *((npy_bool *)op1)= (in1 && !in2) || (!in1 && in2);
+        const int t1 = !!*(@type@ *)ip1;
+        const int t2 = !!*(@type@ *)ip2;
+        *((npy_bool *)op1) = (t1 != t2);
     }
 }
 
@@ -1864,7 +1864,7 @@ HALF_logical_xor(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_U
     BINARY_LOOP {
         const int in1 = !npy_half_iszero(*(npy_half *)ip1);
         const int in2 = !npy_half_iszero(*(npy_half *)ip2);
-        *((npy_bool *)op1)= (in1 && !in2) || (!in1 && in2);
+        *((npy_bool *)op1) = (in1 != in2);
     }
 }
 
@@ -2346,7 +2346,7 @@ NPY_NO_EXPORT void
         const @ftype@ in2i = ((@ftype@ *)ip2)[1];
         const npy_bool tmp1 = (in1r || in1i);
         const npy_bool tmp2 = (in2r || in2i);
-        *((npy_bool *)op1) = (tmp1 && !tmp2) || (!tmp1 && tmp2);
+        *((npy_bool *)op1) = tmp1 != tmp2;
     }
 }
 
diff --git a/numpy/core/tests/test_umath.py b/numpy/core/tests/test_umath.py
index 1cba24d06..4bbf5601a 100644
--- a/numpy/core/tests/test_umath.py
+++ b/numpy/core/tests/test_umath.py
@@ -720,21 +720,43 @@ class TestFmin(_FilterInvalids):
 
 
 class TestBool(TestCase):
-    def test_truth_table(self):
+    def test_truth_table_logical(self):
+        # 2, 3 and 4 serves as true values
+        input1 = [0, 0, 3, 2]
+        input2 = [0, 4, 0, 2]
+
+        typecodes = (np.typecodes['AllFloat']
+                     + np.typecodes['AllInteger']
+                     + '?')     # boolean
+        for dtype in map(np.dtype, typecodes):
+            arg1 = np.asarray(input1, dtype=dtype)
+            arg2 = np.asarray(input2, dtype=dtype)
+
+            # OR
+            out = [False, True, True, True]
+            for func in (np.logical_or, np.maximum):
+                assert_equal(func(arg1, arg2).astype(bool), out)
+            # AND
+            out = [False, False, False, True]
+            for func in (np.logical_and, np.minimum):
+                assert_equal(func(arg1, arg2).astype(bool), out)
+            # XOR
+            out = [False, True, True, False]
+            for func in (np.logical_xor, np.not_equal):
+                assert_equal(func(arg1, arg2).astype(bool), out)
+
+    def test_truth_table_bitwise(self):
         arg1 = [False, False, True, True]
         arg2 = [False, True, False, True]
-        # OR
+
         out = [False, True, True, True]
-        for func in (np.logical_or, np.bitwise_or, np.maximum):
-            assert_equal(func(arg1, arg2), out)
-        # AND
+        assert_equal(np.bitwise_or(arg1, arg2), out)
+
         out = [False, False, False, True]
-        for func in (np.logical_and, np.bitwise_and, np.minimum):
-            assert_equal(func(arg1, arg2), out)
-        # XOR
+        assert_equal(np.bitwise_and(arg1, arg2), out)
+
         out = [False, True, True, False]
-        for func in (np.logical_xor, np.bitwise_xor, np.not_equal):
-            assert_equal(func(arg1, arg2), out)
+        assert_equal(np.bitwise_xor(arg1, arg2), out)
 
 
 class TestFloatingPoint(TestCase):