atomic update of profile counters (issue7000044)

[xur@google.com (Rong Xu)]

Hi,

This patch adds support of atomic update of profiles counters. The goal is to improve
the poor counter values for highly thread programs. 

The atomic update is under a new option -fprofile-gen-atomic=<N>
N=0: default, no atomic update
N=1: atomic update edge counters.
N=2: atomic update some of value profile counters (currently indirect-call and one value profile).
N=3: both edge counter and the above value profile counters.
Other value: fall back to the default.

This patch is a simple porting of the version in google-4_7 branch. It uses __atomic_fetch_add
based on Andrew Pinski's suggestion. Note I did not apply to all the value profiles as
the indirect-call profile is the most relevant one here.

Test with bootstrap.

Comments and suggestions are welcomed.

Thanks,

-Rong


2012-12-20  Rong Xu  <xur@google.com>

	* libgcc/libgcov.c (__gcov_one_value_profiler_body_atomic): New
        function. Atomic update profile counters.
	(__gcov_one_value_profiler_atomic): Ditto.
	(__gcov_indirect_call_profiler_atomic): Ditto.
	* gcc/gcov-io.h: Macros for atomic update.
	* gcc/common.opt: New option.
	* gcc/tree-profile.c (gimple_init_edge_profiler): Atomic
        update profile counters.
	(gimple_gen_edge_profiler): Ditto.

Index: libgcc/libgcov.c
===================================================================
--- libgcc/libgcov.c	(revision 194652)
+++ libgcc/libgcov.c	(working copy)
@@ -1113,12 +1113,35 @@ __gcov_one_value_profiler_body (gcov_type *counter
   counters[2]++;
 }
 
+/* Atomic update version of __gcov_one_value_profile_body().  */
+static inline void 
+__gcov_one_value_profiler_body_atomic (gcov_type *counters, gcov_type value)
+{
+  if (value == counters[0])
+    GCOV_TYPE_ATOMIC_FETCH_ADD_FN (&counters[1], 1, MEMMODEL_RELAXED);
+  else if (counters[1] == 0)
+    {    
+      counters[1] = 1; 
+      counters[0] = value;
+    }    
+  else 
+    GCOV_TYPE_ATOMIC_FETCH_ADD_FN (&counters[1], -1, MEMMODEL_RELAXED);
+  GCOV_TYPE_ATOMIC_FETCH_ADD_FN (&counters[2], 1, MEMMODEL_RELAXED);
+}
+
 #ifdef L_gcov_one_value_profiler
 void
 __gcov_one_value_profiler (gcov_type *counters, gcov_type value)
 {
   __gcov_one_value_profiler_body (counters, value);
 }
+
+void
+__gcov_one_value_profiler_atomic (gcov_type *counters, gcov_type value)
+{
+  __gcov_one_value_profiler_body_atomic (counters, value);
+}
+
 #endif
 
 #ifdef L_gcov_indirect_call_profiler
@@ -1153,6 +1176,17 @@ __gcov_indirect_call_profiler (gcov_type* counter,
 	  && *(void **) cur_func == *(void **) callee_func))
     __gcov_one_value_profiler_body (counter, value);
 }
+
+/* Atomic update version of __gcov_indirect_call_profiler().  */
+void
+__gcov_indirect_call_profiler_atomic (gcov_type* counter, gcov_type value,
+                                      void* cur_func, void* callee_func)
+{
+  if (cur_func == callee_func
+      || (VTABLE_USES_DESCRIPTORS && callee_func
+          && *(void **) cur_func == *(void **) callee_func))
+    __gcov_one_value_profiler_body_atomic (counter, value);
+}
 #endif
 
 
Index: gcc/gcov-io.h
===================================================================
--- gcc/gcov-io.h	(revision 194652)
+++ gcc/gcov-io.h	(working copy)
@@ -202,7 +202,15 @@ typedef unsigned gcov_type_unsigned __attribute__
 #endif
 #endif
 
+#if LONG_LONG_TYPE_SIZE > 32
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_8
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_8
+#else
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_4
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_4
+#endif
 
+
 #if defined (TARGET_POSIX_IO)
 #define GCOV_LOCKED 1
 #else
@@ -212,6 +220,18 @@ typedef unsigned gcov_type_unsigned __attribute__
 #else /* !IN_LIBGCOV */
 /* About the host */
 
+#if LONG_LONG_TYPE_SIZE > 32
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_8
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_8
+#else
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_4
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_4
+#endif
+#define PROFILE_GEN_EDGE_ATOMIC (flag_profile_gen_atomic == 1 || \
+                                 flag_profile_gen_atomic == 3)
+#define PROFILE_GEN_VALUE_ATOMIC (flag_profile_gen_atomic == 2 || \
+                                  flag_profile_gen_atomic == 3)
+
 typedef unsigned gcov_unsigned_t;
 typedef unsigned gcov_position_t;
 /* gcov_type is typedef'd elsewhere for the compiler */
Index: gcc/common.opt
===================================================================
--- gcc/common.opt	(revision 194652)
+++ gcc/common.opt	(working copy)
@@ -1635,6 +1635,15 @@ fprofile-correction
 Common Report Var(flag_profile_correction)
 Enable correction of flow inconsistent profile data input
 
+; fprofile-gen-atomic=0: disable atomically update.
+; fprofile-gen-atomic=1: atomically update edge profile counters.
+; fprofile-gen-atomic=2: atomically update value profile counters.
+; fprofile-gen-atomic=3: atomically update edge and value profile counters.
+; other values will be ignored (fall back to the default of 0).
+fprofile-gen-atomic=
+Common Joined UInteger Report Var(flag_profile_gen_atomic) Init(0) Optimization
+fprofile-gen-atomic=[0..3] Atomically increments for profile counters.
+
 fprofile-generate
 Common
 Enable common options for generating profile info for profile feedback directed optimizations
Index: gcc/tree-profile.c
===================================================================
--- gcc/tree-profile.c	(revision 194652)
+++ gcc/tree-profile.c	(working copy)
@@ -147,7 +147,12 @@ gimple_init_edge_profiler (void)
 	      = build_function_type_list (void_type_node,
 					  gcov_type_ptr, gcov_type_node,
 					  NULL_TREE);
-      tree_one_value_profiler_fn
+      if (PROFILE_GEN_VALUE_ATOMIC)
+        tree_one_value_profiler_fn
+	      = build_fn_decl ("__gcov_one_value_profiler_atomic",
+				     one_value_profiler_fn_type);
+      else
+        tree_one_value_profiler_fn
 	      = build_fn_decl ("__gcov_one_value_profiler",
 				     one_value_profiler_fn_type);
       TREE_NOTHROW (tree_one_value_profiler_fn) = 1;
@@ -163,9 +168,14 @@ gimple_init_edge_profiler (void)
 					  gcov_type_ptr, gcov_type_node,
 					  ptr_void,
 					  ptr_void, NULL_TREE);
-      tree_indirect_call_profiler_fn
-	      = build_fn_decl ("__gcov_indirect_call_profiler",
-				     ic_profiler_fn_type);
+      if (PROFILE_GEN_VALUE_ATOMIC)
+        tree_indirect_call_profiler_fn
+          = build_fn_decl ("__gcov_indirect_call_profiler_atomic",
+			   ic_profiler_fn_type);
+      else
+        tree_indirect_call_profiler_fn
+          = build_fn_decl ("__gcov_indirect_call_profiler",
+			   ic_profiler_fn_type);
       TREE_NOTHROW (tree_indirect_call_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_indirect_call_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
@@ -211,8 +221,21 @@ gimple_gen_edge_profiler (int edgeno, edge e)
   tree ref, one, gcov_type_tmp_var;
   gimple stmt1, stmt2, stmt3;
 
+  one = build_int_cst (gcov_type_node, 1);
+  if (PROFILE_GEN_EDGE_ATOMIC)
+    {
+      ref = tree_coverage_counter_addr (GCOV_COUNTER_ARCS, edgeno);
+      /* __atomic_fetch_add (&counter, 1, MEMMODEL_RELAXED); */
+      stmt1 = gimple_build_call (builtin_decl_explicit (
+                                   GCOV_TYPE_ATOMIC_FETCH_ADD),
+                                 3, ref, one,
+                                 build_int_cst (integer_type_node,
+                                   MEMMODEL_RELAXED));
+     gsi_insert_on_edge (e, stmt1);
+     return;
+    }
+
   ref = tree_coverage_counter_ref (GCOV_COUNTER_ARCS, edgeno);
-  one = build_int_cst (gcov_type_node, 1);
   gcov_type_tmp_var = make_temp_ssa_name (gcov_type_node,
 					  NULL, "PROF_edge_counter");
   stmt1 = gimple_build_assign (gcov_type_tmp_var, ref);

--
This patch is available for review at http://codereview.appspot.com/7000044