Enable prefetching at -O3 for AMD cpus.

2010-06-25  Changpeng Fang  <changpeng.fang@amd.com>

	* common.opt (fprefetch-loop-arrays): Re-define
	-fprefetch-loop-arrays as a tri-state option with the initial
	value of -1.
	* tree-ssa-loop.c (gate_tree_ssa_loop_prefetch): Invoke prefetch
	pass only when flag_prefetch_loop_arrays > 0.
	* toplev.c (process_options): Note that, with tri-states,
	flag_prefetch_loop_arrays>0 means prefetching is enabled.
	* config/i386/i386.c (override_options): Enable prefetching at -O3
	for a set of CPUs that sw prefetching is helpful.
	(software_prefetching_beneficial_p): New.  Return TRUE if software
	prefetching is beneficial for the given CPU.

From-SVN: r161391

gcc/ChangeLog

@@ -1,3 +1,17 @@
+2010-06-25  Changpeng Fang  <changpeng.fang@amd.com>
+
+	* common.opt (fprefetch-loop-arrays): Re-define
+	-fprefetch-loop-arrays as a tri-state option with the initial
+	value of -1.
+	* tree-ssa-loop.c (gate_tree_ssa_loop_prefetch): Invoke prefetch
+	pass only when flag_prefetch_loop_arrays > 0.
+	* toplev.c (process_options): Note that, with tri-states,
+	flag_prefetch_loop_arrays>0 means prefetching is enabled.
+	* config/i386/i386.c (override_options): Enable prefetching at -O3
+	for a set of CPUs that sw prefetching is helpful.
+	(software_prefetching_beneficial_p): New.  Return TRUE if software
+	prefetching is beneficial for the given CPU.
+
 2010-06-25  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR rtl-optimization/44326

gcc/common.opt

@@ -949,7 +949,7 @@ Common Report Var(flag_predictive_commoning) Optimization
 Run predictive commoning optimization.
 
 fprefetch-loop-arrays
-Common Report Var(flag_prefetch_loop_arrays) Optimization
+Common Report Var(flag_prefetch_loop_arrays) Init(-1) Optimization
 Generate prefetch instructions, if available, for arrays in loops
 
 fprofile

gcc/config/i386/i386.c

@@ -2691,6 +2691,26 @@ ix86_target_string (int isa, int flags, const char *arch, const char *tune,
   return ret;
 }
 
+/* Return TRUE if software prefetching is beneficial for the
+   given CPU. */
+
+static bool
+software_prefetching_beneficial_p (void)
+{
+  switch (ix86_tune)
+    {
+    case PROCESSOR_GEODE:
+    case PROCESSOR_K6:
+    case PROCESSOR_ATHLON:
+    case PROCESSOR_K8:
+    case PROCESSOR_AMDFAM10:
+      return true;
+
+    default:
+      return false;
+    }
+}
+
 /* Function that is callable from the debugger to print the current
    options.  */
 void
@@ -3535,6 +3555,13 @@ override_options (bool main_args_p)
   if (!PARAM_SET_P (PARAM_L2_CACHE_SIZE))
     set_param_value ("l2-cache-size", ix86_cost->l2_cache_size);
 
+  /* Enable sw prefetching at -O3 for CPUS that prefetching is helpful.  */
+  if (flag_prefetch_loop_arrays < 0
+      && HAVE_prefetch
+      && optimize >= 3
+      && software_prefetching_beneficial_p ())
+    flag_prefetch_loop_arrays = 1;
+
   /* If using typedef char *va_list, signal that __builtin_va_start (&ap, 0)
      can be optimized to ap = __builtin_next_arg (0).  */
   if (!TARGET_64BIT)

gcc/toplev.c

@@ -2013,13 +2013,13 @@ process_options (void)
     }
 
 #ifndef HAVE_prefetch
-  if (flag_prefetch_loop_arrays)
+  if (flag_prefetch_loop_arrays > 0)
     {
       warning (0, "-fprefetch-loop-arrays not supported for this target");
       flag_prefetch_loop_arrays = 0;
     }
 #else
-  if (flag_prefetch_loop_arrays && !HAVE_prefetch)
+  if (flag_prefetch_loop_arrays > 0 && !HAVE_prefetch)
     {
       warning (0, "-fprefetch-loop-arrays not supported for this target (try -march switches)");
       flag_prefetch_loop_arrays = 0;
@@ -2028,7 +2028,7 @@ process_options (void)
 
   /* This combination of options isn't handled for i386 targets and doesn't
      make much sense anyway, so don't allow it.  */
-  if (flag_prefetch_loop_arrays && optimize_size)
+  if (flag_prefetch_loop_arrays > 0 && optimize_size)
     {
       warning (0, "-fprefetch-loop-arrays is not supported with -Os");
       flag_prefetch_loop_arrays = 0;

gcc/tree-ssa-loop.c

@@ -600,7 +600,7 @@ tree_ssa_loop_prefetch (void)
 static bool
 gate_tree_ssa_loop_prefetch (void)
 {
-  return flag_prefetch_loop_arrays != 0;
+  return flag_prefetch_loop_arrays > 0;
 }
 
 struct gimple_opt_pass pass_loop_prefetch =