re PR tree-optimization/54000 (Performance breakdown for gcc-4.{6,7} vs. gcc-4.5…

re PR tree-optimization/54000 (Performance breakdown for gcc-4.{6,7} vs. gcc-4.5 using std::vector in matrix vector multiplication (IVopts / inliner))

2015-02-09  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/54000
	* tree-ssa-looo-ivopts.c: Include tree-vectorizer.h.
	(struct ivopts_data): Add loop_loc member.
	(tree_ssa_iv_optimize_loop): Dump loop location.
	(create_new_ivs): Likewise, also dump number of IVs generated.

	* g++.dg/tree-ssa/ivopts-3.C: New testcase.

From-SVN: r220536

gcc/ChangeLog

+2015-02-09  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/54000
+	* tree-ssa-looo-ivopts.c: Include tree-vectorizer.h.
+	(struct ivopts_data): Add loop_loc member.
+	(tree_ssa_iv_optimize_loop): Dump loop location.
+	(create_new_ivs): Likewise, also dump number of IVs generated.
+
 2015-02-09  Martin Liska  <mliska@suse.cz>
 
 	* ipa-icf.c (sem_item_optimizer::register_hooks): Register hooks

gcc/testsuite/ChangeLog

+2015-02-09  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/54000
+	* g++.dg/tree-ssa/ivopts-3.C: New testcase.
+
 2015-02-09  Tom de Vries  <tom@codesourcery.com>
 
 	* gcc.dg/graphite/scop-19.c: Fix scan-tree-dump for fpic.

gcc/testsuite/g++.dg/tree-ssa/ivopts-3.C

+// { dg-do compile }
+// { dg-options "-O2 -fdump-tree-ivopts-details" }
+
+class MinimalVec3
+{
+protected:
+  double coords[3];
+
+public:
+
+  MinimalVec3( ) {
+    for ( int i = 0; i < 3; ++i )
+      coords[i] = 0.;
+  }
+
+  inline const double& operator[] ( int I ) const {
+    return coords[I];
+  }
+};
+
+class MinimalVector
+{
+protected:
+  double *_pData;
+  double stuff;
+
+public:
+  explicit MinimalVector ( int length ) {
+    _pData = new double[length];
+    for (int i = 0; i < length; ++i) _pData[i] = 0.;
+  }
+
+  inline double& operator[] ( int I ) {
+    return _pData[I];
+  }
+
+  inline const double& operator[] ( int I ) const {
+    return _pData[I];
+  }
+};
+
+
+int main ( int , char** ) {
+    int w = ( 1 << 7 )+1;
+    int wsqr = w*w;
+    int wcub = w*w*w;
+
+    MinimalVec3 * rows[9];
+    for ( int i = 0; i < 9; ++i ) {
+      rows[i] = new MinimalVec3[wcub];
+    }
+
+    MinimalVector img ( wcub ), res ( wcub );
+
+    for ( int c = 0; c < 1000; ++c ) {
+
+      for ( int i = 1; i < w-1; ++i )
+        for ( int j = 0; j < 3; ++j ) {
+
+          for ( int k = 1; k < w - 1; ++k )
+            for ( int l = 0; l < 3; ++l ) {
+
+              for ( int m = 1; m < w - 1; ++m )
+                for ( int n = 0; n < 3; ++n )
+                  res[i*wsqr + k*w + m] += img[( i + j - 1 ) *wsqr + ( k + l - 1 ) *w + m + n - 1] * rows[j*3 + l][i*wsqr + k*w + m][n];
+
+            }
+        }
+    }
+    return 0;
+}
+
+// Verify that on x86_64 and i?86 we use a single IV for the innermost loop
+
+// { dg-final { scan-tree-dump "Selected IV set for loop \[0-9\]* at \[^ \]*:64, 1 IVs" "ivopts" { target x86_64-*-* i?86-*-* } } }
+// { dg-final { cleanup-tree-dump "ivopts" } }

gcc/tree-ssa-loop-ivopts.c

@@ -138,6 +138,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "tree-ssa-propagate.h"
 #include "tree-ssa-address.h"
 #include "builtins.h"
+#include "tree-vectorizer.h"
 
 /* FIXME: Expressions are expanded to RTL in this pass to determine the
    cost of different addressing modes.  This should be moved to a TBD
@@ -318,6 +319,7 @@ struct ivopts_data
 {
   /* The currently optimized loop.  */
   struct loop *current_loop;
+  source_location loop_loc;
 
   /* Numbers of iterations for all exits of the current loop.  */
   hash_map<edge, tree_niter_desc *> *niters;
@@ -6340,7 +6342,12 @@ create_new_ivs (struct ivopts_data *data, struct iv_ca *set)
 
   if (dump_file && (dump_flags & TDF_DETAILS))
     {
-      fprintf (dump_file, "\nSelected IV set: \n");
+      fprintf (dump_file, "Selected IV set for loop %d",
+	       data->current_loop->num);
+      if (data->loop_loc != UNKNOWN_LOCATION)
+	fprintf (dump_file, " at %s:%d", LOCATION_FILE (data->loop_loc),
+		 LOCATION_LINE (data->loop_loc));
+      fprintf (dump_file, ", %lu IVs:\n", bitmap_count_bits (set->cands));
       EXECUTE_IF_SET_IN_BITMAP (set->cands, 0, i, bi)
         {
           cand = iv_cand (data, i);
@@ -6943,11 +6950,16 @@ tree_ssa_iv_optimize_loop (struct ivopts_data *data, struct loop *loop)
 
   gcc_assert (!data->niters);
   data->current_loop = loop;
+  data->loop_loc = find_loop_location (loop);
   data->speed = optimize_loop_for_speed_p (loop);
 
   if (dump_file && (dump_flags & TDF_DETAILS))
     {
-      fprintf (dump_file, "Processing loop %d\n", loop->num);
+      fprintf (dump_file, "Processing loop %d", loop->num);
+      if (data->loop_loc != UNKNOWN_LOCATION)
+	fprintf (dump_file, " at %s:%d", LOCATION_FILE (data->loop_loc),
+		 LOCATION_LINE (data->loop_loc));
+      fprintf (dump_file, "\n");
 
       if (exit)
 	{