diff -ru /home/edwin/ocaml-3.12.0+rc1/byterun//major_gc.c ./major_gc.c
--- /home/edwin/ocaml-3.12.0+rc1/byterun//major_gc.c	2009-11-04 14:25:47.000000000 +0200
+++ ./major_gc.c	2010-12-02 17:02:38.000000000 +0200
@@ -286,21 +286,25 @@
 {
   char *hp;
   header_t hd;
+  /* speed opt: keep global in local var */
+  char *gc_sweep_hp = caml_gc_sweep_hp;
 
   caml_gc_message (0x40, "Sweeping %ld words\n", work);
   while (work > 0){
-    if (caml_gc_sweep_hp < limit){
-      hp = caml_gc_sweep_hp;
+    if (gc_sweep_hp < limit){
+      hp = gc_sweep_hp;
       hd = Hd_hp (hp);
       work -= Whsize_hd (hd);
-      caml_gc_sweep_hp += Bhsize_hd (hd);
+      gc_sweep_hp += Bhsize_hd (hd);
+      PREFETCH_READ_NT(gc_sweep_hp);
       switch (Color_hd (hd)){
       case Caml_white:
+	caml_gc_sweep_hp = gc_sweep_hp;
         if (Tag_hd (hd) == Custom_tag){
           void (*final_fun)(value) = Custom_ops_val(Val_hp(hp))->finalize;
           if (final_fun != NULL) final_fun(Val_hp(hp));
         }
-        caml_gc_sweep_hp = caml_fl_merge_block (Bp_hp (hp));
+        gc_sweep_hp = caml_fl_merge_block (Bp_hp (hp));
         break;
       case Caml_blue:
         /* Only the blocks of the free-list are blue.  See [freelist.c]. */
@@ -311,7 +315,7 @@
         Hd_hp (hp) = Whitehd_hd (hd);
         break;
       }
-      Assert (caml_gc_sweep_hp <= limit);
+      Assert (gc_sweep_hp <= limit);
     }else{
       chunk = Chunk_next (chunk);
       if (chunk == NULL){
@@ -320,11 +324,12 @@
         work = 0;
         caml_gc_phase = Phase_idle;
       }else{
-        caml_gc_sweep_hp = chunk;
+        gc_sweep_hp = chunk;
         limit = chunk + Chunk_size (chunk);
       }
     }
   }
+  caml_gc_sweep_hp = gc_sweep_hp;
 }
 
diff -ru /home/edwin/ocaml-3.12.0+rc1/byterun//memory.h ./memory.h
--- /home/edwin/ocaml-3.12.0+rc1/byterun//memory.h	2008-12-03 20:09:09.000000000 +0200
+++ ./memory.h	2010-12-02 17:06:12.000000000 +0200
@@ -215,6 +215,16 @@
   #define CAMLunused
 #endif
 
+/* non-temporal prefetch for read (it need not be left in the cache after the access) */
+#if defined (__GNUC__) && (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 1))
+  #define PREFETCH_READ_NT(addr) __builtin_prefetch((addr), 0, 0)
+  #define PREFETCH_READ(addr) __builtin_prefetch((addr), 0, 3)
+#else
+  #define PREFETCH_READ_NT(addr)
+  #define PREFETCH_READ(addr)
+#endif
+
+
 #define CAMLxparam1(x) \
   struct caml__roots_block caml__roots_##x; \
   CAMLunused int caml__dummy_##x = ( \