Add flag -ftree-loop-if-convert-stores.

This patch adds a flag that controls the replacement of the memory
writes that are in predicated basic blocks with a full write:

for (...)
  if (cond)
    A[i] = foo

is replaced with:

for (...)
  A[i] = cond ? foo : A[i]

In order to do this, we have to call gimple_could_trap_p instead of
gimple_assign_rhs_could_trap_p, as we have to also check that the LHS
of assign stmts does not trap.

	* common.opt (ftree-loop-if-convert-stores): New flag.
	* doc/invoke.texi (ftree-loop-if-convert-stores): Documented.
	* tree-if-conv.c (ifc_temp_var): Pass an extra parameter GSI.  Insert
	the created statement before GSI.
	(if_convertible_phi_p): Allow virtual phi nodes when
	flag_loop_if_convert_stores is set.
	(if_convertible_gimple_assign_stmt_p): Allow memory reads and writes
	Do not handle types that do not match is_gimple_reg_type.
	Remove loop and bb parameters.  Call gimple_could_trap_p instead of
	when flag_loop_if_convert_stores is set, as LHS can contain
	memory refs.
	(if_convertible_stmt_p): Remove loop and bb parameters.  Update calls
	to if_convertible_gimple_assign_stmt_p.
	(if_convertible_loop_p): Update call to if_convertible_stmt_p.
	(replace_phi_with_cond_gimple_assign_stmt): Renamed
	predicate_scalar_phi.  Do not handle virtual phi nodes.
	(ifconvert_phi_nodes): Renamed predicate_all_scalar_phis.
	Call predicate_scalar_phi.
	(insert_gimplified_predicates): Insert the gimplified predicate of a BB
	just after the labels for flag_loop_if_convert_stores, otherwise
	insert the predicate in the end of the BB.
	(predicate_mem_writes): New.
	(combine_blocks): Call predicate_all_scalar_phis.  When
	flag_loop_if_convert_stores is set, call predicate_mem_writes.
	(tree_if_conversion): Call mark_sym_for_renaming when
	flag_loop_if_convert_stores is set.
	(main_tree_if_conversion): Return TODO_update_ssa_only_virtuals when
	flag_loop_if_convert_stores is set.

	* gcc.dg/tree-ssa/ifc-4.c: New.
	* gcc.dg/tree-ssa/ifc-7.c: New.

From-SVN: r163530

gcc/ChangeLog

+2010-08-24  Sebastian Pop  <sebastian.pop@amd.com>
+
+	* common.opt (ftree-loop-if-convert-stores): New flag.
+	* doc/invoke.texi (ftree-loop-if-convert-stores): Documented.
+	* tree-if-conv.c (ifc_temp_var): Pass an extra parameter GSI.  Insert
+	the created statement before GSI.
+	(if_convertible_phi_p): Allow virtual phi nodes when
+	flag_loop_if_convert_stores is set.
+	(if_convertible_gimple_assign_stmt_p): Allow memory reads and writes
+	Do not handle types that do not match is_gimple_reg_type.
+	Remove loop and bb parameters.  Call gimple_could_trap_p instead of
+	when flag_loop_if_convert_stores is set, as LHS can contain
+	memory refs.
+	(if_convertible_stmt_p): Remove loop and bb parameters.  Update calls
+	to if_convertible_gimple_assign_stmt_p.
+	(if_convertible_loop_p): Update call to if_convertible_stmt_p.
+	(replace_phi_with_cond_gimple_assign_stmt): Renamed
+	predicate_scalar_phi.  Do not handle virtual phi nodes.
+	(ifconvert_phi_nodes): Renamed predicate_all_scalar_phis.
+	Call predicate_scalar_phi.
+	(insert_gimplified_predicates): Insert the gimplified predicate of a BB
+	just after the labels for flag_loop_if_convert_stores, otherwise
+	insert the predicate in the end of the BB.
+	(predicate_mem_writes): New.
+	(combine_blocks): Call predicate_all_scalar_phis.  When
+	flag_loop_if_convert_stores is set, call predicate_mem_writes.
+	(tree_if_conversion): Call mark_sym_for_renaming when
+	flag_loop_if_convert_stores is set.
+	(main_tree_if_conversion): Return TODO_update_ssa_only_virtuals when
+	flag_loop_if_convert_stores is set.
+
 2010-08-24  Anatoly Sokolov  <aesok@post.ru>
 
 	* config/pa/pa.c (hppa_register_move_cost, pa_libcall_value,

gcc/common.opt

@@ -712,6 +712,10 @@ ftree-loop-if-convert
 Common Report Var(flag_tree_loop_if_convert) Init(-1) Optimization
 Convert conditional jumps in innermost loops to branchless equivalents
 
+ftree-loop-if-convert-stores
+Common Report Var(flag_tree_loop_if_convert_stores) Optimization
+Also if-convert conditional jumps containing memory writes
+
 ; -finhibit-size-directive inhibits output of .size for ELF.
 ; This is used only for compiling crtstuff.c,
 ; and it may be extended to other effects

gcc/doc/invoke.texi

@@ -383,7 +383,8 @@ Objective-C and Objective-C++ Dialects}.
 -fstrict-aliasing -fstrict-overflow -fthread-jumps -ftracer -ftree-bit-ccp @gol
 -ftree-builtin-call-dce -ftree-ccp -ftree-ch -ftree-copy-prop @gol
 -ftree-copyrename -ftree-dce -ftree-dominator-opts -ftree-dse @gol
--ftree-forwprop -ftree-fre -ftree-loop-if-convert -ftree-loop-im @gol
+-ftree-forwprop -ftree-fre -ftree-loop-if-convert @gol
+-ftree-loop-if-convert-memory-writes -ftree-loop-im @gol
 -ftree-phiprop -ftree-loop-distribution -ftree-loop-distribute-patterns @gol
 -ftree-loop-ivcanon -ftree-loop-linear -ftree-loop-optimize @gol
 -ftree-parallelize-loops=@var{n} -ftree-pre -ftree-pta -ftree-reassoc @gol
@@ -6931,6 +6932,23 @@ the innermost loops in order to improve the ability of the
 vectorization pass to handle these loops.  This is enabled by default
 if vectorization is enabled.
 
+@item -ftree-loop-if-convert-stores
+Attempt to also if-convert conditional jumps containing memory writes.
+This transformation can be unsafe for multi-threaded programs as it
+transforms conditional memory writes into unconditional memory writes.
+For example,
+@smallexample
+for (i = 0; i < N; i++)
+  if (cond)
+    A[i] = expr;
+@end smallexample
+would be transformed to
+@smallexample
+for (i = 0; i < N; i++)
+  A[i] = cond ? expr : A[i];
+@end smallexample
+potentially producing data races.
+
 @item -ftree-loop-distribution
 Perform loop distribution.  This flag can improve cache performance on
 big loop bodies and allow further loop optimizations, like

gcc/testsuite/ChangeLog

+2010-08-24  Sebastian Pop  <sebastian.pop@amd.com>
+
+	* gcc.dg/tree-ssa/ifc-4.c: New.
+	* gcc.dg/tree-ssa/ifc-7.c: New.
+
 2010-08-24  Mingjie Xing  <mingjie.xing@gmail.com>
 
 	* gcc.dg/vect/vect.exp: Check loongson targets

gcc/testsuite/gcc.dg/tree-ssa/ifc-4.c

+/* { dg-do compile } */
+/* { dg-options "-c -O2 -ftree-vectorize -fdump-tree-ifcvt-stats" { target *-*-* } } */
+
+struct ht
+{
+  void * (*alloc_subobject) (int);
+};
+typedef struct cpp_reader cpp_reader;
+typedef struct cpp_token cpp_token;
+typedef struct cpp_macro cpp_macro;
+enum cpp_ttype
+{
+    CPP_PASTE,
+};
+struct cpp_token {
+  __extension__ enum cpp_ttype type : 8;
+} cpp_comment_table;
+struct cpp_macro {
+  union cpp_macro_u
+  {
+    cpp_token * tokens;
+  } exp;
+  unsigned int count;
+};
+struct cpp_reader
+{
+  struct ht *hash_table;
+};
+create_iso_definition (cpp_reader *pfile, cpp_macro *macro)
+{
+  unsigned int num_extra_tokens = 0;
+  {
+    cpp_token *tokns =
+      (cpp_token *) pfile->hash_table->alloc_subobject (sizeof (cpp_token)
+							* macro->count);
+    {
+      cpp_token *normal_dest = tokns;
+      cpp_token *extra_dest = tokns + macro->count - num_extra_tokens;
+      unsigned int i;
+      for (i = 0; i < macro->count; i++)
+	{
+	  if (macro->exp.tokens[i].type == CPP_PASTE)
+	    *extra_dest++ = macro->exp.tokens[i];
+	  else
+	    *normal_dest++ = macro->exp.tokens[i];
+	}
+    }
+  }
+}
+
+/* This cannot be if-converted because the stores are to aggregate types.  */
+/* { dg-final { scan-tree-dump-times "Applying if-conversion" 0 "ifcvt" } } */
+/* { dg-final { cleanup-tree-dump "ifcvt" } } */

gcc/testsuite/gcc.dg/tree-ssa/ifc-7.c

+/* { dg-do compile } */
+/* { dg-options "-c -O2 -ftree-vectorize" { target *-*-* } } */
+
+typedef struct eqn_d
+{
+  int *coef;
+} *eqn;
+typedef struct omega_pb_d
+{
+  eqn subs;
+} *omega_pb;
+
+omega_pb omega_solve_problem (omega_pb);
+
+omega_pb
+omega_solve_geq (omega_pb pb, int n)
+{
+  int i, e;
+  int j = 0;
+
+  for (e = n - 1; e >= 0; e--)
+    if (pb->subs[e].coef[i] != pb->subs[e].coef[j])
+      {
+	pb->subs[e].coef[i] = j;
+	pb->subs[e].coef[j] = i;
+      }
+
+  return omega_solve_problem (pb);
+}