Makefile.in (loop-unroll.o): Add HASHTAB_H and RECOG_H dependency.

	* Makefile.in (loop-unroll.o): Add HASHTAB_H and RECOG_H dependency.
	* basic-block.h (struct reorder_block_def): Add copy_number field.
	* cfgloop.h (biv_p): Declare.
	* cfgloopmanip.c (duplicate_loop_to_header_edge): Set copy_number.
	* common.opt (fsplit-ivs-in-unroller): New flag.
	* loop-iv.c (biv_p): New function.
	* loop-unroll.c: Include hashtab.h and recog.h.
	(struct iv_to_split, struct split_ivs_info): New types.
	(analyze_ivs_to_split, si_info_start_duplication, split_ivs_in_copies,
	free_si_info, si_info_hash, si_info_eq, analyze_iv_to_split_insn,
	determine_split_iv_delta, get_ivts_expr, allocate_basic_variable,
	insert_base_initialization, split_iv): New functions.
	(peel_loop_completely, unroll_loop_constant_iterations,
	unroll_loop_runtime_iterations, peel_loop_simple, unroll_loop_stupid):
	Use them.
	* doc/invoke.texi (-fsplit-ivs-in-unroller): Document.

Co-Authored-By: Steven Bosscher <stevenb@suse.de>

From-SVN: r87487

gcc/ChangeLog

 2004-09-14  Zdenek Dvorak  <rakdver@atrey.karlin.mff.cuni.cz>
+	    Steven Bosscher  <stevenb@suse.de>
+
+	* Makefile.in (loop-unroll.o): Add HASHTAB_H and RECOG_H dependency.
+	* basic-block.h (struct reorder_block_def): Add copy_number field.
+	* cfgloop.h (biv_p): Declare.
+	* cfgloopmanip.c (duplicate_loop_to_header_edge): Set copy_number.
+	* common.opt (fsplit-ivs-in-unroller): New flag.
+	* loop-iv.c (biv_p): New function.
+	* loop-unroll.c: Include hashtab.h and recog.h.
+	(struct iv_to_split, struct split_ivs_info): New types.
+	(analyze_ivs_to_split, si_info_start_duplication, split_ivs_in_copies,
+	free_si_info, si_info_hash, si_info_eq, analyze_iv_to_split_insn,
+	determine_split_iv_delta, get_ivts_expr, allocate_basic_variable,
+	insert_base_initialization, split_iv): New functions.
+	(peel_loop_completely, unroll_loop_constant_iterations,
+	unroll_loop_runtime_iterations, peel_loop_simple, unroll_loop_stupid):
+	Use them.
+	* doc/invoke.texi (-fsplit-ivs-in-unroller): Document.
+
+2004-09-14  Zdenek Dvorak  <rakdver@atrey.karlin.mff.cuni.cz>
 
 	* tree-cfg.c (thread_jumps): Update dominators correctly in
 	case destination of threaded edge dominates its source.

gcc/Makefile.in

@@ -2028,7 +2028,7 @@ loop-unswitch.o : loop-unswitch.c $(CONFIG_H) $(SYSTEM_H) $(RTL_H) $(TM_H) \
    output.h $(EXPR_H) coretypes.h $(TM_H)
 loop-unroll.o: loop-unroll.c $(CONFIG_H) $(SYSTEM_H) $(RTL_H) $(TM_H) \
    $(BASIC_BLOCK_H) hard-reg-set.h $(CFGLOOP_H) $(CFGLAYOUT_H) $(PARAMS_H) \
-   output.h $(EXPR_H) coretypes.h $(TM_H)
+   output.h $(EXPR_H) coretypes.h $(TM_H) $(HASHTAB_H) $(RECOG_H)
 dominance.o : dominance.c $(CONFIG_H) $(SYSTEM_H) coretypes.h $(TM_H) $(RTL_H) \
    hard-reg-set.h $(BASIC_BLOCK_H) et-forest.h
 et-forest.o : et-forest.c $(CONFIG_H) $(SYSTEM_H) coretypes.h $(TM_H) et-forest.h alloc-pool.h

gcc/basic-block.h

@@ -295,6 +295,7 @@ typedef struct reorder_block_def
   /* Used by loop copying.  */
   basic_block copy;
   int duplicated;
+  int copy_number;
 
   /* These fields are used by bb-reorder pass.  */
   int visited;

gcc/cfgloop.h

@@ -410,6 +410,7 @@ extern void iv_analysis_loop_init (struct loop *);
 extern rtx iv_get_reaching_def (rtx, rtx);
 extern bool iv_analyze (rtx, rtx, struct rtx_iv *);
 extern rtx get_iv_value (struct rtx_iv *, rtx);
+extern bool biv_p (rtx, rtx);
 extern void find_simple_exit (struct loop *, struct niter_desc *);
 extern void iv_number_of_iterations (struct loop *, rtx, rtx,
 				     struct niter_desc *);

gcc/cfgloopmanip.c

@@ -991,6 +991,9 @@ duplicate_loop_to_header_edge (struct loop *loop, edge e, struct loops *loops,
       /* Copy bbs.  */
       copy_bbs (bbs, n, new_bbs, spec_edges, 2, new_spec_edges, loop);
 
+      for (i = 0; i < n; i++)
+	new_bbs[i]->rbi->copy_number = j + 1;
+
       /* Note whether the blocks and edges belong to an irreducible loop.  */
       if (add_irreducible_flag)
 	{
@@ -1069,6 +1072,8 @@ duplicate_loop_to_header_edge (struct loop *loop, edge e, struct loops *loops,
       int n_dom_bbs,j;
 
       bb = bbs[i];
+      bb->rbi->copy_number = 0;
+
       n_dom_bbs = get_dominated_by (CDI_DOMINATORS, bb, &dom_bbs);
       for (j = 0; j < n_dom_bbs; j++)
 	{

gcc/common.opt

@@ -744,6 +744,10 @@ fspeculative-prefetching
 Common Report Var(flag_speculative_prefetching)
 Use value profiling for speculative prefetching
 
+fsplit-ivs-in-unroller
+Common Report Var(flag_split_ivs_in_unroller) Init(1)
+Split lifetimes of induction variables when loops are unrolled.
+
 ; Emit code to probe the stack, to help detect stack overflow; also
 ; may cause large objects to be allocated dynamically.
 fstack-check

gcc/doc/invoke.texi

@@ -315,7 +315,7 @@ Objective-C and Objective-C++ Dialects}.
 -fsignaling-nans -fsingle-precision-constant  -fspeculative-prefetching @gol
 -fstrength-reduce  -fstrict-aliasing  -ftracer  -fthread-jumps @gol
 -funroll-all-loops  -funroll-loops  -fpeel-loops @gol
--funswitch-loops @gol
+-fsplit-ivs-in-unroller -funswitch-loops @gol
 -ftree-pre  -ftree-ccp  -ftree-dce -ftree-loop-optimize @gol
 -ftree-loop-linear -ftree-loop-im -ftree-loop-ivcanon -fivopts @gol
 -ftree-dominator-opts -ftree-dse -ftree-copyrename @gol
@@ -4696,6 +4696,20 @@ the loop is entered.  This usually makes programs run more slowly.
 @option{-funroll-all-loops} implies the same options as
 @option{-funroll-loops},
 
+@item -fsplit-ivs-in-unroller
+@opindex -fsplit-ivs-in-unroller
+Enables expressing of values of induction variables in later iterations
+of the unrolled loop using the value in the first iteration.  This breaks
+long dependency chains, thus improving efficiency of the scheduling passes
+(for best results, @option{-fweb} should be used as well).
+
+Combination of @option{-fweb} and CSE is often sufficient to obtain the
+same effect. However in cases the loop body is more complicated than
+a single basic block, this is not reliable.  It also does not work at all
+on some of the architectures due to restrictions in the CSE pass.
+
+This optimization is enabled by default.
+
 @item -fprefetch-loop-arrays
 @opindex fprefetch-loop-arrays
 If supported by the target machine, generate instructions to prefetch

gcc/loop-iv.c

@@ -1183,6 +1183,24 @@ iv_analyze (rtx insn, rtx def, struct rtx_iv *iv)
   return iv->base != NULL_RTX;
 }
 
+/* Checks whether definition of register REG in INSN a basic induction
+   variable.  IV analysis must have been initialized (via a call to
+   iv_analysis_loop_init) for this function to produce a result.  */
+
+bool
+biv_p (rtx insn, rtx reg)
+{
+  struct rtx_iv iv;
+
+  if (!REG_P (reg))
+    return false;
+
+  if (last_def[REGNO (reg)] != insn)
+    return false;
+
+  return iv_analyze_biv (reg, &iv);
+}
+
 /* Calculates value of IV at ITERATION-th iteration.  */
 
 rtx