tested sp sort and works the first version. Slightly slower on random than std and sometimes slightly faster - but this version do copies that I should optimize out!

ypsu.cpp

@@ -393,9 +393,9 @@
   }
 
   int main(void) {
-    //int n = 100000000;
+    int n = 100000000;
     //int n = 10000000;
-    int n = 64;
+    //int n = 64;
     for (auto inputtype : inputtypes) {
       printf("%10s", inputtype.c_str());
       fflush(stdout);