GvR's idea to use memset() for the most common special case of repeating
a single character. Shaves another 10% off the running time by avoiding
the lg2(N) loops and cache effects for the other cases.
diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index acfce8b..1a4a754 100644
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -966,6 +966,11 @@
PyObject_INIT_VAR(op, &PyString_Type, size);
op->ob_shash = -1;
op->ob_sstate = SSTATE_NOT_INTERNED;
+ op->ob_sval[size] = '\0';
+ if (a->ob_size == 1 && n > 0) {
+ memset(op->ob_sval, a->ob_sval[0] , n);
+ return (PyObject *) op;
+ }
i = 0;
if (i < size) {
memcpy(op->ob_sval, a->ob_sval, (int) a->ob_size);
@@ -976,7 +981,6 @@
memcpy(op->ob_sval+i, op->ob_sval, j);
i += j;
}
- op->ob_sval[size] = '\0';
return (PyObject *) op;
}