ENH: improve bool argmin performance

in glibc memchr using SSE2 is about 18 times faster than our current
code.

numpy/core/src/multiarray/arraytypes.c.src

@@ -21,6 +21,7 @@
 #include "alloc.h"
 
 #include "numpyos.h"
+#include <string.h>
 
 
 /*
@@ -2851,26 +2852,37 @@ static int
 
 /**end repeat**/
 
+static int
+BOOL_argmin(npy_bool *ip, npy_intp n, npy_intp *min_ind,
+            PyArrayObject *NPY_UNUSED(aip))
+
+{
+    npy_bool * p = memchr(ip, 0, n * sizeof(*ip));
+    if (p == NULL) {
+        *min_ind = 0;
+        return 0;
+    }
+    *min_ind = p - ip;
+    return 0;
+}
+
 /**begin repeat
  *
- * #fname = BOOL,
- *          BYTE, UBYTE, SHORT, USHORT, INT, UINT,
+ * #fname = BYTE, UBYTE, SHORT, USHORT, INT, UINT,
  *          LONG, ULONG, LONGLONG, ULONGLONG,
  *          HALF, FLOAT, DOUBLE, LONGDOUBLE,
  *          CFLOAT, CDOUBLE, CLONGDOUBLE,
  *          DATETIME, TIMEDELTA#
- * #type = npy_bool,
- *         npy_byte, npy_ubyte, npy_short, npy_ushort, npy_int, npy_uint,
+ * #type = npy_byte, npy_ubyte, npy_short, npy_ushort, npy_int, npy_uint,
  *         npy_long, npy_ulong, npy_longlong, npy_ulonglong,
  *         npy_half, npy_float, npy_double, npy_longdouble,
  *         npy_float, npy_double, npy_longdouble,
  *         npy_datetime, npy_timedelta#
- * #isbool = 1, 0*19#
- * #isfloat = 0*11, 1*7, 0*2#
- * #isnan = nop*11, npy_half_isnan, npy_isnan*6, nop*2#
- * #le = _LESS_THAN_OR_EQUAL*11, npy_half_le, _LESS_THAN_OR_EQUAL*8#
- * #iscomplex = 0*15, 1*3, 0*2#
- * #incr = ip++*15, ip+=2*3, ip++*2#
+ * #isfloat = 0*10, 1*7, 0*2#
+ * #isnan = nop*10, npy_half_isnan, npy_isnan*6, nop*2#
+ * #le = _LESS_THAN_OR_EQUAL*10, npy_half_le, _LESS_THAN_OR_EQUAL*8#
+ * #iscomplex = 0*14, 1*3, 0*2#
+ * #incr = ip++*14, ip+=2*3, ip++*2#
  */
 static int
 @fname@_argmin(@type@ *ip, npy_intp n, npy_intp *min_ind,
@@ -2896,12 +2908,6 @@ static int
         return 0;
     }
 #endif
-#if @isbool@
-    if (!mp) {
-        /* False encountered; it's minimal */
-        return 0;
-    }
-#endif
 
     for (i = 1; i < n; i++) {
         @incr@;
@@ -2929,12 +2935,6 @@ static int
                 /* nan encountered, it's minimal */
                 break;
             }
-#endif
-#if @isbool@
-            if (!mp) {
-                /* False encountered; it's minimal */
-                break;
-            }
 #endif
         }
 #endif