[Bug target/47000] Major performance regression in parallel SSE2 impl of SHA256 hash algorithm

[hjl.tools at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=47000

--- Comment #8 from H.J. Lu <hjl.tools at gmail dot com> 2010-12-18 16:03:44 UTC ---
Can you try

--
diff --git a/gcc/tree-inline.c b/gcc/tree-inline.c
index af1adf4..dd00de6 100644
--- a/gcc/tree-inline.c
+++ b/gcc/tree-inline.c
@@ -3342,7 +3342,11 @@ estimate_num_insns (gimple stmt, eni_weights *weights)
     if (POINTER_TYPE_P (funtype))
       funtype = TREE_TYPE (funtype);

-    if (decl && DECL_BUILT_IN_CLASS (decl) == BUILT_IN_MD)
+    /* Do not special case builtins where we see the body.
+       This just confuse inliner.  */
+    if (!decl || cgraph_node (decl)->analyzed)
+      ;
+    else if (decl && DECL_BUILT_IN_CLASS (decl) == BUILT_IN_MD)
       cost = weights->target_builtin_call_cost;
     else
       cost = weights->call_cost;
---