loop splitting

(approved at https://gcc.gnu.org/ml/gcc-patches/2015-12/msg00648.html )

	* common.opt (-fsplit-loops): New flag.
	* passes.def (pass_loop_split): Add.
	* opts.c (default_options_table): Add OPT_fsplit_loops entry at -O3.
	(enable_fdo_optimizations): Add loop splitting.
	* timevar.def (TV_LOOP_SPLIT): Add.
	* tree-pass.h (make_pass_loop_split): Declare.
	* tree-ssa-loop-manip.h (rewrite_into_loop_closed_ssa_1): Declare.
	* tree-ssa-loop-unswitch.c: Include tree-ssa-loop-manip.h,
	* tree-ssa-loop-split.c: New file.
	* Makefile.in (OBJS): Add tree-ssa-loop-split.o.
	* doc/invoke.texi (fsplit-loops): Document.
	* doc/passes.texi (Loop optimization): Add paragraph about loop
	splitting.

testsuite/
	* gcc.dg/loop-split.c: New test.
	* gcc.dg/tree-ssa/ifc-9.c: Update.
	* gcc.dg/tree-ssa/ifc-10.c: Update.

From-SVN: r241374

gcc/ChangeLog

+2016-10-20  Michael Matz  <matz@suse.de>
+
+	Loop splitting.
+	* common.opt (-fsplit-loops): New flag.
+	* passes.def (pass_loop_split): Add.
+	* opts.c (default_options_table): Add OPT_fsplit_loops entry at -O3.
+	(enable_fdo_optimizations): Add loop splitting.
+	* timevar.def (TV_LOOP_SPLIT): Add.
+	* tree-pass.h (make_pass_loop_split): Declare.
+	* tree-ssa-loop-manip.h (rewrite_into_loop_closed_ssa_1): Declare.
+	* tree-ssa-loop-unswitch.c: Include tree-ssa-loop-manip.h,
+	* tree-ssa-loop-split.c: New file.
+	* Makefile.in (OBJS): Add tree-ssa-loop-split.o.
+	* doc/invoke.texi (fsplit-loops): Document.
+	* doc/passes.texi (Loop optimization): Add paragraph about loop
+	splitting.
+
 2016-10-20  Richard Biener  <rguenther@suse.de>
 
 	* cgraphunit.c (analyze_functions): Set node->definition to

gcc/Makefile.in

@@ -1508,6 +1508,7 @@ OBJS = \
 	tree-ssa-loop-manip.o \
 	tree-ssa-loop-niter.o \
 	tree-ssa-loop-prefetch.o \
+	tree-ssa-loop-split.o \
 	tree-ssa-loop-unswitch.o \
 	tree-ssa-loop.o \
 	tree-ssa-math-opts.o \

gcc/common.opt

@@ -2576,6 +2576,10 @@ funswitch-loops
 Common Report Var(flag_unswitch_loops) Optimization
 Perform loop unswitching.
 
+fsplit-loops
+Common Report Var(flag_split_loops) Optimization
+Perform loop splitting.
+
 funwind-tables
 Common Report Var(flag_unwind_tables) Optimization
 Just generate unwind tables for exception handling.

gcc/doc/invoke.texi

@@ -402,7 +402,7 @@ Objective-C and Objective-C++ Dialects}.
 -fsel-sched-pipelining -fsel-sched-pipelining-outer-loops @gol
 -fsemantic-interposition -fshrink-wrap -fshrink-wrap-separate @gol
 -fsignaling-nans @gol
--fsingle-precision-constant -fsplit-ivs-in-unroller @gol
+-fsingle-precision-constant -fsplit-ivs-in-unroller -fsplit-loops@gol
 -fsplit-paths @gol
 -fsplit-wide-types -fssa-backprop -fssa-phiopt @gol
 -fstdarg-opt -fstrict-aliasing @gol
@@ -9224,6 +9224,11 @@ Enabled with @option{-O3} and/or @option{-fprofile-use}.
 Enables the loop invariant motion pass in the RTL loop optimizer.  Enabled
 at level @option{-O1}
 
+@item -fsplit-loops
+@opindex fsplit-loops
+Split a loop into two if it contains a condition that's always true
+for one side of the iteration space and false for the other.
+
 @item -funswitch-loops
 @opindex funswitch-loops
 Move branches with loop invariant conditions out of the loop, with duplicates

gcc/doc/passes.texi

@@ -484,6 +484,12 @@ out of the loops.  To achieve this, a duplicate of the loop is created for
 each possible outcome of conditional jump(s).  The pass is implemented in
 @file{tree-ssa-loop-unswitch.c}.
 
+Loop splitting.  If a loop contains a conditional statement that is
+always true for one part of the iteration space and false for the other
+this pass splits the loop into two, one dealing with one side the other
+only with the other, thereby removing one inner-loop conditional.  The
+pass is implemented in @file{tree-ssa-loop-split.c}.
+
 The optimizations also use various utility functions contained in
 @file{tree-ssa-loop-manip.c}, @file{cfgloop.c}, @file{cfgloopanal.c} and
 @file{cfgloopmanip.c}.

gcc/opts.c

@@ -530,6 +530,7 @@ static const struct default_options default_options_table[] =
        regardless of them being declared inline.  */
     { OPT_LEVELS_3_PLUS_AND_SIZE, OPT_finline_functions, NULL, 1 },
     { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_finline_functions_called_once, NULL, 1 },
+    { OPT_LEVELS_3_PLUS, OPT_fsplit_loops, NULL, 1 },
     { OPT_LEVELS_3_PLUS, OPT_funswitch_loops, NULL, 1 },
     { OPT_LEVELS_3_PLUS, OPT_fgcse_after_reload, NULL, 1 },
     { OPT_LEVELS_3_PLUS, OPT_ftree_loop_vectorize, NULL, 1 },
@@ -1427,6 +1428,8 @@ enable_fdo_optimizations (struct gcc_options *opts,
     opts->x_flag_ipa_bit_cp = value;
   if (!opts_set->x_flag_predictive_commoning)
     opts->x_flag_predictive_commoning = value;
+  if (!opts_set->x_flag_split_loops)
+    opts->x_flag_split_loops = value;
   if (!opts_set->x_flag_unswitch_loops)
     opts->x_flag_unswitch_loops = value;
   if (!opts_set->x_flag_gcse_after_reload)

gcc/passes.def

@@ -269,6 +269,7 @@ along with GCC; see the file COPYING3.  If not see
 	  NEXT_PASS (pass_tree_loop_init);
 	  NEXT_PASS (pass_tree_unswitch);
 	  NEXT_PASS (pass_scev_cprop);
+	  NEXT_PASS (pass_loop_split);
 	  NEXT_PASS (pass_record_bounds);
 	  NEXT_PASS (pass_loop_distribution);
 	  NEXT_PASS (pass_copy_prop);

gcc/testsuite/ChangeLog

+2016-10-20  Michael Matz  <matz@suse.de>
+
+	* gcc.dg/loop-split.c: New test.
+	* gcc.dg/tree-ssa/ifc-9.c: Update.
+	* gcc.dg/tree-ssa/ifc-10.c: Update.
+
 2016-10-20  Richard Biener  <rguenther@suse.de>
 
 	* gcc.dg/graphite/pr35356-1.c: Update.

gcc/testsuite/gcc.dg/loop-split.c

+/* { dg-do run } */
+/* { dg-options "-O2 -fsplit-loops -fdump-tree-lsplit-details" } */
+
+#ifdef __cplusplus
+extern "C" int printf (const char *, ...);
+extern "C" void abort (void);
+#else
+extern int printf (const char *, ...);
+extern void abort (void);
+#endif
+
+/* Define TRACE to 1 or 2 to get detailed tracing.
+   Define SINGLE_TEST to 1 or 2 to get a simple routine with
+   just one loop, called only one time or with multiple parameters,
+   to make debugging easier.  */
+#ifndef TRACE
+#define TRACE 0
+#endif
+
+#define loop(beg,step,beg2,cond1,cond2) \
+    do \
+      { \
+	sum = 0; \
+        for (i = (beg), j = (beg2); (cond1); i+=(step),j+=(step)) \
+          { \
+            if (cond2) { \
+	      if (TRACE > 1) printf ("a: %d %d\n", i, j); \
+              sum += a[i]; \
+	    } else { \
+	      if (TRACE > 1) printf ("b: %d %d\n", i, j); \
+              sum += b[i]; \
+	    } \
+          } \
+	if (TRACE > 0) printf ("sum: %d\n", sum); \
+	check = check * 47 + sum; \
+      } while (0)
+
+#ifndef SINGLE_TEST
+unsigned __attribute__((noinline, noclone)) dotest (int beg, int end, int step,
+					       int c, int *a, int *b, int beg2)
+{
+  unsigned check = 0;
+  int sum;
+  int i, j;
+  loop (beg, 1, beg2, i < end, j < c);
+  loop (beg, 1, beg2, i <= end, j < c);
+  loop (beg, 1, beg2, i < end, j <= c);
+  loop (beg, 1, beg2, i <= end, j <= c);
+  loop (beg, 1, beg2, i < end, j > c);
+  loop (beg, 1, beg2, i <= end, j > c);
+  loop (beg, 1, beg2, i < end, j >= c);
+  loop (beg, 1, beg2, i <= end, j >= c);
+  beg2 += end-beg;
+  loop (end, -1, beg2, i >= beg, j >= c);
+  loop (end, -1, beg2, i >= beg, j > c);
+  loop (end, -1, beg2, i > beg, j >= c);
+  loop (end, -1, beg2, i > beg, j > c);
+  loop (end, -1, beg2, i >= beg, j <= c);
+  loop (end, -1, beg2, i >= beg, j < c);
+  loop (end, -1, beg2, i > beg, j <= c);
+  loop (end, -1, beg2, i > beg, j < c);
+  return check;
+}
+
+#else
+
+int __attribute__((noinline, noclone)) f (int beg, int end, int step,
+					  int c, int *a, int *b, int beg2)
+{
+  int sum = 0;
+  int i, j;
+  //for (i = beg, j = beg2; i < end; i += 1, j++ /*step*/)
+  for (i = end, j = beg2 + (end-beg); i > beg; i += -1, j-- /*step*/)
+    {
+      // i - j == X --> i = X + j
+      // --> i < end == X+j < end == j < end - X
+      // --> newend = end - (i_init - j_init)
+      // j < end-X && j < c --> j < min(end-X,c)
+      // j < end-X && j <= c --> j <= min(end-X-1,c) or j < min(end-X,c+1{OF!})
+      //if (j < c)
+      if (j >= c)
+	printf ("a: %d %d\n", i, j);
+      /*else
+	printf ("b: %d %d\n", i, j);*/
+	/*sum += a[i];
+      else
+	sum += b[i];*/
+    }
+  return sum;
+}
+
+int __attribute__((noinline, noclone)) f2 (int *beg, int *end, int step,
+					  int *c, int *a, int *b, int *beg2)
+{
+  int sum = 0;
+  int *i, *j;
+  for (i = beg, j = beg2; i < end; i += 1, j++ /*step*/)
+    {
+      if (j <= c)
+	printf ("%d %d\n", i - beg, j - beg);
+	/*sum += a[i];
+      else
+	sum += b[i];*/
+    }
+  return sum;
+}
+#endif
+
+extern int printf (const char *, ...);
+
+int main ()
+{
+  int a[] = {0,0,0,0,0, 1,2,3,4,5,6,7,8,9,          0,0,0,0,0};
+  int b[] = {0,0,0,0,0, -1,-2,-3,-4,-5,-6,-7,-8,-9, 0,0,0,0,0,};
+  int c;
+  int diff = 0;
+  unsigned check = 0;
+#if defined(SINGLE_TEST) && (SINGLE_TEST == 1)
+  //dotest (0, 9, 1, -1, a+5, b+5, -1);
+  //return 0;
+  f (0, 9, 1, 5, a+5, b+5, -1);
+  return 0;
+#endif
+  for (diff = -5; diff <= 5; diff++)
+    {
+      for (c = -1; c <= 10; c++)
+	{
+#ifdef SINGLE_TEST
+	  int s = f (0, 9, 1, c, a+5, b+5, diff);
+	  //int s = f2 (a+0, a+9, 1, a+c, a+5, b+5, a+diff);
+	  printf ("%d ", s);
+#else
+	  if (TRACE > 0)
+	    printf ("check %d %d\n", c, diff);
+	  check = check * 51 + dotest (0, 9, 1, c, a+5, b+5, diff);
+#endif
+	}
+      //printf ("\n");
+    }
+  //printf ("%u\n", check);
+  if (check != 3213344948)
+    abort ();
+  return 0;
+}
+
+/* All 16 loops in dotest should be split.  */
+/* { dg-final { scan-tree-dump-times "Loop split" 16 "lsplit" } } */

gcc/testsuite/gcc.dg/tree-ssa/ifc-10.c

 /* { dg-do compile } */
-/* { dg-options "-Ofast -fdump-tree-ifcvt-stats" } */
+/* { dg-options "-Ofast -fno-split-loops -fdump-tree-ifcvt-stats" } */
 /* { dg-require-visibility "" } */
 
 int b[256] = {0}, y;

gcc/testsuite/gcc.dg/tree-ssa/ifc-9.c

 /* { dg-do compile } */
-/* { dg-options "-Ofast -fdump-tree-ifcvt-stats" } */
+/* { dg-options "-Ofast -fno-split-loops -fdump-tree-ifcvt-stats" } */
 /* { dg-require-visibility "" } */
 
 extern int b[256], y;

gcc/timevar.def

@@ -185,6 +185,7 @@ DEFTIMEVAR (TV_LIM                   , "tree loop invariant motion")
 DEFTIMEVAR (TV_TREE_LOOP_IVCANON     , "tree canonical iv")
 DEFTIMEVAR (TV_SCEV_CONST            , "scev constant prop")
 DEFTIMEVAR (TV_TREE_LOOP_UNSWITCH    , "tree loop unswitching")
+DEFTIMEVAR (TV_LOOP_SPLIT            , "loop splitting")
 DEFTIMEVAR (TV_COMPLETE_UNROLL       , "complete unrolling")
 DEFTIMEVAR (TV_TREE_PARALLELIZE_LOOPS, "tree parallelize loops")
 DEFTIMEVAR (TV_TREE_VECTORIZATION    , "tree vectorization")

gcc/tree-pass.h

@@ -367,6 +367,7 @@ extern gimple_opt_pass *make_pass_tree_no_loop (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_tree_loop_init (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_lim (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_tree_unswitch (gcc::context *ctxt);
+extern gimple_opt_pass *make_pass_loop_split (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_predcom (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_iv_canon (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_scev_cprop (gcc::context *ctxt);

gcc/tree-ssa-loop-manip.h

@@ -24,6 +24,8 @@ typedef void (*transform_callback)(struct loop *, void *);
 
 extern void create_iv (tree, tree, tree, struct loop *, gimple_stmt_iterator *,
 		       bool, tree *, tree *);
+extern void rewrite_into_loop_closed_ssa_1 (bitmap, unsigned, int,
+					    struct loop *);
 extern void rewrite_into_loop_closed_ssa (bitmap, unsigned);
 extern void rewrite_virtuals_into_loop_closed_ssa (struct loop *);
 extern void verify_loop_closed_ssa (bool);