This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Peeling loops at tree level?, Lno branch merge patches ping
Hello,
> On Mon, Sep 13, 2004 at 05:05:42PM +0200, Zdenek Dvorak wrote:
> > http://gcc.gnu.org/ml/gcc-patches/2004-08/msg00325.html (part 10)
>
> This patch isn't up-to-date wrt force_gimple_operand and
> others. Would you please regenerate?
here it is. Great part of the patch was already comitted with other
patches, the functions to split iterations of a loop and to align number
of iterations of a loop are so far only used in my experiments, so
I left them out as unused.
Zdenek
* cfgloop.h (update_single_exits_after_duplication): Declare.
(loopify, split_loop_bb): Declaration changed.
* cfgloopmanip.c (split_loop_bb): Take void * as an argument instead
of rtx.
(loopify): Added redirect_all_edges argument.
(update_single_exits_after_duplication): Export.
* loop-unswitch.c (unswitch_loop): Changed due to loopify change.
* tree-flow.h (tree_duplicate_loop_to_header_edge,
tree_ssa_loop_version): Declare.
* tree-ssa-loop-manip.c (copy_phi_node_args, rename_variables,
set_phi_def_stmts, tree_duplicate_loop_to_header_edge,
lv_adjust_loop_header_phi, lv_adjust_loop_entry_edge,
lv_update_pending_stmts, tree_ssa_loop_version): New functions.
Index: cfgloop.h
===================================================================
RCS file: /cvs/gcc/gcc/gcc/cfgloop.h,v
retrieving revision 1.31
diff -c -3 -p -r1.31 cfgloop.h
*** cfgloop.h 16 Sep 2004 16:16:13 -0000 1.31
--- cfgloop.h 16 Sep 2004 21:57:02 -0000
*************** extern int flow_loop_scan (struct loop *
*** 254,259 ****
--- 254,261 ----
extern void flow_loop_free (struct loop *);
void mark_irreducible_loops (struct loops *);
void mark_single_exit_loops (struct loops *);
+ void update_single_exits_after_duplication (basic_block *, unsigned,
+ struct loop *);
extern void create_loop_notes (void);
/* Loop data structure manipulation/querying. */
*************** extern struct loop * duplicate_loop (str
*** 313,322 ****
extern int duplicate_loop_to_header_edge (struct loop *, edge, struct loops *,
unsigned, sbitmap, edge, edge *,
unsigned *, int);
! extern struct loop *loopify (struct loops *, edge, edge, basic_block);
extern void unloop (struct loops *, struct loop *);
extern bool remove_path (struct loops *, edge);
! extern edge split_loop_bb (basic_block, rtx);
/* Induction variable analysis. */
--- 315,324 ----
extern int duplicate_loop_to_header_edge (struct loop *, edge, struct loops *,
unsigned, sbitmap, edge, edge *,
unsigned *, int);
! extern struct loop *loopify (struct loops *, edge, edge, basic_block, bool);
extern void unloop (struct loops *, struct loop *);
extern bool remove_path (struct loops *, edge);
! extern edge split_loop_bb (basic_block, void *);
/* Induction variable analysis. */
Index: cfgloopmanip.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/cfgloopmanip.c,v
retrieving revision 1.31
diff -c -3 -p -r1.31 cfgloopmanip.c
*** cfgloopmanip.c 16 Sep 2004 16:16:13 -0000 1.31
--- cfgloopmanip.c 16 Sep 2004 21:57:02 -0000
*************** static void fix_irreducible_loops (basic
*** 53,59 ****
/* Splits basic block BB after INSN, returns created edge. Updates loops
and dominators. */
edge
! split_loop_bb (basic_block bb, rtx insn)
{
edge e;
--- 53,59 ----
/* Splits basic block BB after INSN, returns created edge. Updates loops
and dominators. */
edge
! split_loop_bb (basic_block bb, void *insn)
{
edge e;
*************** scale_loop_frequencies (struct loop *loo
*** 486,492 ****
struct loop *
loopify (struct loops *loops, edge latch_edge, edge header_edge,
! basic_block switch_bb)
{
basic_block succ_bb = latch_edge->dest;
basic_block pred_bb = header_edge->src;
--- 486,492 ----
struct loop *
loopify (struct loops *loops, edge latch_edge, edge header_edge,
! basic_block switch_bb, bool redirect_all_edges)
{
basic_block succ_bb = latch_edge->dest;
basic_block pred_bb = header_edge->src;
*************** loopify (struct loops *loops, edge latch
*** 513,524 ****
loop_redirect_edge (latch_edge, loop->header);
loop_redirect_edge (BRANCH_EDGE (switch_bb), succ_bb);
! loop_redirect_edge (header_edge, switch_bb);
! loop_redirect_edge (FALLTHRU_EDGE (switch_bb), loop->header);
!
! /* Update dominators. */
! set_immediate_dominator (CDI_DOMINATORS, switch_bb, pred_bb);
! set_immediate_dominator (CDI_DOMINATORS, loop->header, switch_bb);
set_immediate_dominator (CDI_DOMINATORS, succ_bb, switch_bb);
--- 513,529 ----
loop_redirect_edge (latch_edge, loop->header);
loop_redirect_edge (BRANCH_EDGE (switch_bb), succ_bb);
! /* During loop versioning, one of the switch_bb edge is already properly
! set. Do not redirect it again unless redirect_all_edges is true. */
! if (redirect_all_edges)
! {
! loop_redirect_edge (header_edge, switch_bb);
! loop_redirect_edge (FALLTHRU_EDGE (switch_bb), loop->header);
!
! /* Update dominators. */
! set_immediate_dominator (CDI_DOMINATORS, switch_bb, pred_bb);
! set_immediate_dominator (CDI_DOMINATORS, loop->header, switch_bb);
! }
set_immediate_dominator (CDI_DOMINATORS, succ_bb, switch_bb);
*************** can_duplicate_loop_p (struct loop *loop)
*** 812,818 ****
/* The NBBS blocks in BBS will get duplicated and the copies will be placed
to LOOP. Update the single_exit information in superloops of LOOP. */
! static void
update_single_exits_after_duplication (basic_block *bbs, unsigned nbbs,
struct loop *loop)
{
--- 817,823 ----
/* The NBBS blocks in BBS will get duplicated and the copies will be placed
to LOOP. Update the single_exit information in superloops of LOOP. */
! void
update_single_exits_after_duplication (basic_block *bbs, unsigned nbbs,
struct loop *loop)
{
*************** update_single_exits_after_duplication (b
*** 834,840 ****
bbs[i]->rbi->duplicated = 0;
}
-
/* Duplicates body of LOOP to given edge E NDUPL times. Takes care of updating
LOOPS structure and dominators. E's destination must be LOOP header for
this to work, i.e. it must be entry or latch edge of this loop; these are
--- 839,844 ----
Index: loop-unswitch.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/loop-unswitch.c,v
retrieving revision 1.21
diff -c -3 -p -r1.21 loop-unswitch.c
*** loop-unswitch.c 10 Sep 2004 11:02:24 -0000 1.21
--- loop-unswitch.c 16 Sep 2004 21:57:02 -0000
*************** unswitch_loop (struct loops *loops, stru
*** 475,481 ****
/* Loopify from the copy of LOOP body, constructing the new loop. */
nloop = loopify (loops, latch_edge,
! loop->header->rbi->copy->pred, switch_bb);
/* Remove branches that are now unreachable in new loops. */
remove_path (loops, true_edge);
--- 475,481 ----
/* Loopify from the copy of LOOP body, constructing the new loop. */
nloop = loopify (loops, latch_edge,
! loop->header->rbi->copy->pred, switch_bb, true);
/* Remove branches that are now unreachable in new loops. */
remove_path (loops, true_edge);
Index: tree-flow.h
===================================================================
RCS file: /cvs/gcc/gcc/gcc/tree-flow.h,v
retrieving revision 2.46
diff -c -3 -p -r2.46 tree-flow.h
*** tree-flow.h 16 Sep 2004 21:29:38 -0000 2.46
--- tree-flow.h 16 Sep 2004 21:57:02 -0000
*************** void standard_iv_increment_position (str
*** 675,680 ****
--- 675,686 ----
bool *);
basic_block ip_end_pos (struct loop *);
basic_block ip_normal_pos (struct loop *);
+ bool tree_duplicate_loop_to_header_edge (struct loop *, edge, struct loops *,
+ unsigned int, sbitmap,
+ edge, edge *,
+ unsigned int *, int);
+ struct loop *tree_ssa_loop_version (struct loops *, struct loop *, tree,
+ basic_block *);
/* In tree-ssa-loop-im.c */
/* The possibilities of statement movement. */
Index: tree-ssa-loop-manip.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/tree-ssa-loop-manip.c,v
retrieving revision 2.6
diff -c -3 -p -r2.6 tree-ssa-loop-manip.c
*** tree-ssa-loop-manip.c 12 Sep 2004 20:20:58 -0000 2.6
--- tree-ssa-loop-manip.c 16 Sep 2004 21:57:02 -0000
*************** standard_iv_increment_position (struct l
*** 506,508 ****
--- 506,854 ----
*insert_after = false;
}
}
+
+ /* Copies phi node arguments for duplicated blocks. The index of the first
+ duplicated block is FIRST_NEW_BLOCK. */
+
+ static void
+ copy_phi_node_args (unsigned first_new_block)
+ {
+ unsigned i;
+
+ for (i = first_new_block; i < (unsigned) last_basic_block; i++)
+ BASIC_BLOCK (i)->rbi->duplicated = 1;
+
+ for (i = first_new_block; i < (unsigned) last_basic_block; i++)
+ add_phi_args_after_copy_bb (BASIC_BLOCK (i));
+
+ for (i = first_new_block; i < (unsigned) last_basic_block; i++)
+ BASIC_BLOCK (i)->rbi->duplicated = 0;
+ }
+
+ /* Renames variables in the area copied by tree_duplicate_loop_to_header_edge.
+ FIRST_NEW_BLOCK is the first block in the copied area. DEFINITIONS is
+ a bitmap of all ssa names defined inside the loop. */
+
+ static void
+ rename_variables (unsigned first_new_block, bitmap definitions)
+ {
+ unsigned i, copy_number = 0;
+ basic_block bb;
+ htab_t ssa_name_map = NULL;
+
+ for (i = first_new_block; i < (unsigned) last_basic_block; i++)
+ {
+ bb = BASIC_BLOCK (i);
+
+ /* We assume that first come all blocks from the first copy, then all
+ blocks from the second copy, etc. */
+ if (copy_number != (unsigned) bb->rbi->copy_number)
+ {
+ allocate_ssa_names (definitions, &ssa_name_map);
+ copy_number = bb->rbi->copy_number;
+ }
+
+ rewrite_to_new_ssa_names_bb (bb, ssa_name_map);
+ }
+
+ htab_delete (ssa_name_map);
+ }
+
+ /* Sets SSA_NAME_DEF_STMT for results of all phi nodes in BB. */
+
+ static void
+ set_phi_def_stmts (basic_block bb)
+ {
+ tree phi;
+
+ for (phi = phi_nodes (bb); phi; phi = TREE_CHAIN (phi))
+ SSA_NAME_DEF_STMT (PHI_RESULT (phi)) = phi;
+ }
+
+ /* The same ad cfgloopmanip.c:duplicate_loop_to_header_edge, but also updates
+ ssa. In order to achieve this, only loops whose exits all lead to the same
+ location are handled.
+
+ FIXME: we create some degenerate phi nodes that could be avoided by copy
+ propagating them instead. Unfortunately this is not completely
+ straightforward due to problems with constant folding. */
+
+ bool
+ tree_duplicate_loop_to_header_edge (struct loop *loop, edge e,
+ struct loops *loops,
+ unsigned int ndupl, sbitmap wont_exit,
+ edge orig, edge *to_remove,
+ unsigned int *n_to_remove, int flags)
+ {
+ unsigned first_new_block;
+ basic_block bb;
+ unsigned i;
+ tree phi, arg, map, def;
+ bitmap definitions;
+
+ if (!(loops->state & LOOPS_HAVE_SIMPLE_LATCHES))
+ return false;
+ if (!(loops->state & LOOPS_HAVE_PREHEADERS))
+ return false;
+
+ #ifdef ENABLE_CHECKING
+ verify_loop_closed_ssa ();
+ #endif
+
+ gcc_assert (!any_marked_for_rewrite_p ());
+
+ first_new_block = last_basic_block;
+ if (!duplicate_loop_to_header_edge (loop, e, loops, ndupl, wont_exit,
+ orig, to_remove, n_to_remove, flags))
+ return false;
+
+ /* Readd the removed phi args for e. */
+ map = PENDING_STMT (e);
+ PENDING_STMT (e) = NULL;
+
+ for (phi = phi_nodes (e->dest), arg = map;
+ phi;
+ phi = TREE_CHAIN (phi), arg = TREE_CHAIN (arg))
+ {
+ def = TREE_VALUE (arg);
+ add_phi_arg (&phi, def, e);
+ }
+ gcc_assert (arg == NULL);
+
+ /* Copy the phi node arguments. */
+ copy_phi_node_args (first_new_block);
+
+ /* Rename the variables. */
+ definitions = marked_ssa_names ();
+ rename_variables (first_new_block, definitions);
+ unmark_all_for_rewrite ();
+ BITMAP_XFREE (definitions);
+
+ /* For some time we have the identical ssa names as results in multiple phi
+ nodes. When phi node is resized, it sets SSA_NAME_DEF_STMT of its result
+ to the new copy. This means that we cannot easily ensure that the ssa
+ names defined in those phis are pointing to the right one -- so just
+ recompute SSA_NAME_DEF_STMT for them. */
+
+ for (i = first_new_block; i < (unsigned) last_basic_block; i++)
+ {
+ bb = BASIC_BLOCK (i);
+ set_phi_def_stmts (bb);
+ if (bb->rbi->copy_number == 1)
+ set_phi_def_stmts (bb->rbi->original);
+ }
+
+ scev_reset ();
+ #ifdef ENABLE_CHECKING
+ verify_loop_closed_ssa ();
+ #endif
+
+ return true;
+ }
+
+ /*---------------------------------------------------------------------------
+ Loop versioning
+ ---------------------------------------------------------------------------*/
+
+ /* Adjust phi nodes for 'first' basic block. 'second' basic block is a copy
+ of 'first'. Both of them are dominated by 'new_head' basic block. When
+ 'new_head' was created by 'second's incoming edge it received phi arguments
+ on the edge by split_edge(). Later, additional edge 'e' was created to
+ connect 'new_head' and 'first'. Now this routine adds phi args on this
+ additional edge 'e' that new_head to second edge received as part of edge
+ splitting.
+ */
+
+ static void
+ lv_adjust_loop_header_phi (basic_block first, basic_block second,
+ basic_block new_head, edge e)
+ {
+ tree phi1, phi2;
+
+ /* Browse all 'second' basic block phi nodes and add phi args to
+ edge 'e' for 'first' head. PHI args are always in correct order. */
+
+ for (phi2 = phi_nodes (second), phi1 = phi_nodes (first);
+ phi2 && phi1;
+ phi2 = TREE_CHAIN (phi2), phi1 = TREE_CHAIN (phi1))
+ {
+ int i;
+ for (i = 0; i < PHI_NUM_ARGS (phi2); i++)
+ {
+ if (PHI_ARG_EDGE (phi2, i)->src == new_head)
+ {
+ tree def = PHI_ARG_DEF (phi2, i);
+ add_phi_arg (&phi1, def, e);
+ }
+ }
+ }
+ }
+
+ /* Adjust entry edge for lv.
+
+ e is a incoming edge.
+
+ --- edge e ---- > [second_head]
+
+ Split it and insert new conditional expression and adjust edges.
+
+ --- edge e ---> [cond expr] ---> [first_head]
+ |
+ +---------> [second_head]
+
+ */
+
+ static basic_block
+ lv_adjust_loop_entry_edge (basic_block first_head,
+ basic_block second_head,
+ edge e,
+ tree cond_expr)
+ {
+ block_stmt_iterator bsi;
+ basic_block orig_head = e->src;
+ basic_block new_head = NULL;
+ tree goto1 = NULL_TREE;
+ tree goto2 = NULL_TREE;
+ tree new_cond_expr = NULL_TREE;
+ edge e0, e1;
+
+ /* Split edge 'e'. This will create a new basic block, where we can
+ insert conditional expr. */
+ new_head = split_edge (e);
+ set_immediate_dominator (CDI_DOMINATORS, new_head, orig_head);
+
+ /* Build new conditional expr */
+ goto1 = build1 (GOTO_EXPR, void_type_node, tree_block_label (first_head));
+ goto2 = build1 (GOTO_EXPR, void_type_node, tree_block_label (second_head));
+ new_cond_expr = build3 (COND_EXPR, void_type_node, cond_expr, goto1, goto2);
+
+ /* Add new cond. in new head. */
+ bsi = bsi_start (new_head);
+ bsi_insert_after (&bsi, new_cond_expr, BSI_NEW_STMT);
+
+ /* Adjust edges appropriately to connect new head with first head
+ as well as second head. */
+ e1 = make_edge (new_head, first_head, EDGE_TRUE_VALUE);
+ set_immediate_dominator (CDI_DOMINATORS, first_head, new_head);
+ make_edge (new_head, second_head, EDGE_FALSE_VALUE);
+ set_immediate_dominator (CDI_DOMINATORS, second_head, new_head);
+
+ /* Adjust loop header phi nodes. */
+ lv_adjust_loop_header_phi (first_head, second_head, new_head, e1);
+
+ /* When edge 'e' was split, it created a fall through edge
+ from new head to second head. Above created FALSE edge
+ from new head to second head and now we do not need the
+ fall through edge. */
+ for (e0 = new_head->succ; e0; e0 = e0->succ_next)
+ if (e0->dest == second_head)
+ e0->flags &= ~EDGE_FALLTHRU;
+
+ return new_head;
+ }
+
+ /* Add phi args using PENDINT_STMT list. */
+
+ static void
+ lv_update_pending_stmts (edge e)
+ {
+ basic_block dest;
+ tree phi, arg, def;
+
+ if (!PENDING_STMT (e))
+ return;
+
+ dest = e->dest;
+
+ for (phi = phi_nodes (dest), arg = PENDING_STMT (e);
+ phi;
+ phi = TREE_CHAIN (phi), arg = TREE_CHAIN (arg))
+ {
+ def = TREE_VALUE (arg);
+ add_phi_arg (&phi, def, e);
+ }
+
+ PENDING_STMT (e) = NULL;
+ }
+
+
+ /* Main entry point for Loop Versioning transformation.
+
+ This transformation given a condition and a loop, creates
+ -if (condition) { loop_copy1 } else { loop_copy2 },
+ where loop_copy1 is the loop transformed in one way, and loop_copy2
+ is the loop transformed in another way (or unchanged). 'condition'
+ may be a run time test for things that were not resolved by static
+ analysis (overlapping ranges (anti-aliasing), alignment, etc.). */
+
+ struct loop *
+ tree_ssa_loop_version (struct loops *loops, struct loop * loop,
+ tree cond_expr, basic_block *condition_bb)
+ {
+ edge entry, latch_edge, exit;
+ basic_block first_head, second_head;
+ int irred_flag;
+ struct loop *nloop;
+
+ /* CHECKME: Loop versioning does not handle nested loop at this point. */
+ if (loop->inner)
+ return NULL;
+
+ /* Record entry and latch edges for the loop */
+ entry = loop_preheader_edge (loop);
+
+ /* Note down head of loop as first_head. */
+ first_head = entry->dest;
+
+ /* Duplicate loop. */
+ irred_flag = entry->flags & EDGE_IRREDUCIBLE_LOOP;
+ entry->flags &= ~EDGE_IRREDUCIBLE_LOOP;
+ if (!tree_duplicate_loop_to_header_edge (loop, entry, loops, 1,
+ NULL, NULL, NULL, NULL, 0))
+ {
+ entry->flags |= irred_flag;
+ return NULL;
+ }
+
+ /* After duplication entry edge now points to new loop head block.
+ Note down new head as second_head. */
+ second_head = entry->dest;
+
+ /* Split loop entry edge and insert new block with cond expr. */
+ *condition_bb = lv_adjust_loop_entry_edge (first_head, second_head, entry,
+ cond_expr);
+
+ latch_edge = loop->latch->rbi->copy->succ;
+ nloop = loopify (loops,
+ latch_edge,
+ loop->header->rbi->copy->pred,
+ *condition_bb,
+ false /* Do not redirect all edges. */);
+
+ exit = loop->single_exit;
+ if (exit)
+ nloop->single_exit = find_edge (exit->src->rbi->copy, exit->dest);
+
+ /* loopify redirected latch_edge. Update its PENDING_STMTS. */
+ lv_update_pending_stmts (latch_edge);
+
+ /* loopify redirected condition_bb's succ edge. Update its PENDING_STMTS. */
+ lv_update_pending_stmts (FALLTHRU_EDGE (*condition_bb));
+
+ /* Adjust irreducible flag. */
+ if (irred_flag)
+ {
+ (*condition_bb)->flags |= BB_IRREDUCIBLE_LOOP;
+ loop_preheader_edge (loop)->flags |= EDGE_IRREDUCIBLE_LOOP;
+ loop_preheader_edge (nloop)->flags |= EDGE_IRREDUCIBLE_LOOP;
+ (*condition_bb)->pred->flags |= EDGE_IRREDUCIBLE_LOOP;
+ }
+
+ /* At this point condition_bb is loop predheader with two successors,
+ first_head and second_head. Make sure that loop predheader has only
+ one successor. */
+ loop_split_edge_with (loop_preheader_edge (loop), NULL);
+ loop_split_edge_with (loop_preheader_edge (nloop), NULL);
+
+ return nloop;
+ }