[PATCH v4] malloc: Optimize small memory zeroing for calloc

[Wilco Dijkstra]

Hi H.J.,

+static __always_inline void *
+clear_memory (void *mem, unsigned long clearsize)
+{
+  /* Unroll clear memory size up to 9 * INTERNAL_SIZE_T bytes.  We know
+     that contents have an odd number of INTERNAL_SIZE_T-sized words;
+     minimally 3 words.  */
+  INTERNAL_SIZE_T *d = (INTERNAL_SIZE_T *) mem;
+  unsigned long nclears = clearsize / sizeof (INTERNAL_SIZE_T);
+
+  if (nclears > 9)
+    return memset (d, 0, clearsize);
+
+  /* Use overlapping stores with 1 branch, instead of up to 3.  */
+  *(d + 0) = 0;
+  *(d + 1) = 0;
+  *(d + 2) = 0;
+  *(d + nclears - 2) = 0;
+  *(d + nclears - 2 + 1) = 0;
+  if (nclears > 3)

Should be nclears > 5, right?

+    {
+      *(d + 3) = 0;
+      *(d + 3 + 1) = 0;
+      *(d + nclears - 4) = 0;
+      *(d + nclears - 4 + 1) = 0;
+    }
+  else if (nclears < 3)
+    __builtin_unreachable ();
+
+  return mem;
+}

This interface makes much more sense indeed. Still, it's hard to see how
targets could do much better than memset