-/* Generic partial redundancy elimination with lazy code motion
- support.
- Copyright (C) 1998 Free Software Foundation, Inc.
+/* Generic partial redundancy elimination with lazy code motion support.
+ Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc.
This file is part of GNU CC.
#include "config.h"
#include "system.h"
-
#include "rtl.h"
#include "regs.h"
#include "hard-reg-set.h"
#include "insn-config.h"
#include "recog.h"
#include "basic-block.h"
+#include "tm_p.h"
+
+/* We want target macros for the mode switching code to be able to refer
+ to instruction attribute values. */
+#include "insn-attr.h"
/* Edge based LCM routines. */
-static void compute_antinout_edge PROTO ((sbitmap *, sbitmap *,
- sbitmap *, sbitmap *));
-static void compute_earliest PROTO((struct edge_list *, int, sbitmap *,
- sbitmap *, sbitmap *, sbitmap *,
- sbitmap *));
-static void compute_laterin PROTO((struct edge_list *, sbitmap *,
- sbitmap *, sbitmap *, sbitmap *));
-static void compute_insert_delete PROTO ((struct edge_list *edge_list,
- sbitmap *, sbitmap *, sbitmap *,
- sbitmap *, sbitmap *));
+static void compute_antinout_edge PARAMS ((sbitmap *, sbitmap *,
+ sbitmap *, sbitmap *));
+static void compute_earliest PARAMS ((struct edge_list *, int,
+ sbitmap *, sbitmap *,
+ sbitmap *, sbitmap *,
+ sbitmap *));
+static void compute_laterin PARAMS ((struct edge_list *, sbitmap *,
+ sbitmap *, sbitmap *,
+ sbitmap *));
+static void compute_insert_delete PARAMS ((struct edge_list *edge_list,
+ sbitmap *, sbitmap *,
+ sbitmap *, sbitmap *,
+ sbitmap *));
/* Edge based LCM routines on a reverse flowgraph. */
-static void compute_farthest PROTO ((struct edge_list *, int, sbitmap *,
- sbitmap *, sbitmap*, sbitmap *,
- sbitmap *));
-static void compute_nearerout PROTO((struct edge_list *, sbitmap *,
- sbitmap *, sbitmap *, sbitmap *));
-static void compute_rev_insert_delete PROTO ((struct edge_list *edge_list,
- sbitmap *, sbitmap *, sbitmap *,
- sbitmap *, sbitmap *));
-
+static void compute_farthest PARAMS ((struct edge_list *, int,
+ sbitmap *, sbitmap *,
+ sbitmap*, sbitmap *,
+ sbitmap *));
+static void compute_nearerout PARAMS ((struct edge_list *, sbitmap *,
+ sbitmap *, sbitmap *,
+ sbitmap *));
+static void compute_rev_insert_delete PARAMS ((struct edge_list *edge_list,
+ sbitmap *, sbitmap *,
+ sbitmap *, sbitmap *,
+ sbitmap *));
\f
/* Edge based lcm routines. */
/* Allocate a worklist array/queue. Entries are only added to the
list if they were not already on the list. So the size is
bounded by the number of basic blocks. */
- tos = worklist = (basic_block *) xmalloc (sizeof (basic_block)
- * n_basic_blocks);
+ tos = worklist
+ = (basic_block *) xmalloc (sizeof (basic_block) * n_basic_blocks);
/* We want a maximal solution, so make an optimistic initialization of
ANTIN. */
bb = b->index;
if (b->aux == EXIT_BLOCK_PTR)
- {
- /* Do not clear the aux field for blocks which are
- predecessors of the EXIT block. That way we never
- add then to the worklist again. */
- sbitmap_zero (antout[bb]);
- }
+ /* Do not clear the aux field for blocks which are predecessors of
+ the EXIT block. That way we never add then to the worklist
+ again. */
+ sbitmap_zero (antout[bb]);
else
{
/* Clear the aux field of this block so that it can be added to
}
if (sbitmap_a_or_b_and_c (antin[bb], antloc[bb], transp[bb], antout[bb]))
- {
- /* If the in state of this block changed, then we need
- to add the predecessors of this block to the worklist
- if they are not already on the worklist. */
- for (e = b->pred; e; e = e->pred_next)
+ /* If the in state of this block changed, then we need
+ to add the predecessors of this block to the worklist
+ if they are not already on the worklist. */
+ for (e = b->pred; e; e = e->pred_next)
+ if (!e->src->aux && e->src != ENTRY_BLOCK_PTR)
{
- if (!e->src->aux && e->src != ENTRY_BLOCK_PTR)
- {
- *tos++ = e->src;
- e->src->aux = e;
- }
+ *tos++ = e->src;
+ e->src->aux = e;
}
- }
}
+
free (tos);
}
/* Compute the earliest vector for edge based lcm. */
+
static void
compute_earliest (edge_list, n_exprs, antin, antout, avout, kill, earliest)
struct edge_list *edge_list;
else
{
if (succ == EXIT_BLOCK_PTR)
- {
- sbitmap_zero (earliest[x]);
- }
+ sbitmap_zero (earliest[x]);
else
{
sbitmap_difference (difference, antin[succ->index],
avout[pred->index]);
sbitmap_not (temp_bitmap, antout[pred->index]);
- sbitmap_a_and_b_or_c (earliest[x], difference, kill[pred->index],
- temp_bitmap);
+ sbitmap_a_and_b_or_c (earliest[x], difference,
+ kill[pred->index], temp_bitmap);
}
}
}
+
free (temp_bitmap);
free (difference);
}
/* Allocate a worklist array/queue. Entries are only added to the
list if they were not already on the list. So the size is
bounded by the number of basic blocks. */
- tos = worklist = (basic_block *) xmalloc (sizeof (basic_block)
- * (n_basic_blocks + 1));
+ tos = worklist
+ = (basic_block *) xmalloc (sizeof (basic_block) * (n_basic_blocks + 1));
/* Initialize a mapping from each edge to its index. */
for (i = 0; i < num_edges; i++)
- INDEX_EDGE (edge_list, i)->aux = (void *)i;
+ INDEX_EDGE (edge_list, i)->aux = (void *) (size_t) i;
/* We want a maximal solution, so initially consider LATER true for
all edges. This allows propagation through a loop since the incoming
the entry block. That edge should always have a LATER value the
same as EARLIEST for that edge. */
for (e = ENTRY_BLOCK_PTR->succ; e; e = e->succ_next)
- sbitmap_copy (later[(int)e->aux], earliest[(int)e->aux]);
+ sbitmap_copy (later[(size_t) e->aux], earliest[(size_t) e->aux]);
/* Add all the blocks to the worklist. This prevents an early exit from
the loop given our optimistic initialization of LATER above. */
bb = b->index;
sbitmap_ones (laterin[bb]);
for (e = b->pred; e != NULL; e = e->pred_next)
- sbitmap_a_and_b (laterin[bb], laterin[bb], later[(int)e->aux]);
+ sbitmap_a_and_b (laterin[bb], laterin[bb], later[(size_t)e->aux]);
/* Calculate LATER for all outgoing edges. */
for (e = b->succ; e != NULL; e = e->succ_next)
- {
- if (sbitmap_union_of_diff (later[(int)e->aux],
- earliest[(int)e->aux],
- laterin[e->src->index],
- antloc[e->src->index]))
- {
- /* If LATER for an outgoing edge was changed, then we need
- to add the target of the outgoing edge to the worklist. */
- if (e->dest != EXIT_BLOCK_PTR && e->dest->aux == 0)
- {
- *tos++ = e->dest;
- e->dest->aux = e;
- }
- }
- }
+ if (sbitmap_union_of_diff (later[(size_t) e->aux],
+ earliest[(size_t) e->aux],
+ laterin[e->src->index],
+ antloc[e->src->index])
+ /* If LATER for an outgoing edge was changed, then we need
+ to add the target of the outgoing edge to the worklist. */
+ && e->dest != EXIT_BLOCK_PTR && e->dest->aux == 0)
+ {
+ *tos++ = e->dest;
+ e->dest->aux = e;
+ }
}
/* Computation of insertion and deletion points requires computing LATERIN
for (e = EXIT_BLOCK_PTR->pred; e != NULL; e = e->pred_next)
sbitmap_a_and_b (laterin[n_basic_blocks],
laterin[n_basic_blocks],
- later[(int)e->aux]);
+ later[(size_t) e->aux]);
free (tos);
}
/* Compute the insertion and deletion points for edge based LCM. */
+
static void
compute_insert_delete (edge_list, antloc, later, laterin,
insert, delete)
for (x = 0; x < NUM_EDGES (edge_list); x++)
{
basic_block b = INDEX_EDGE_SUCC_BB (edge_list, x);
+
if (b == EXIT_BLOCK_PTR)
sbitmap_difference (insert[x], later[x], laterin[n_basic_blocks]);
else
}
}
-/* Given local properties TRANSP, ANTLOC, AVOUT, KILL return the
- insert and delete vectors for edge based LCM. Returns an
- edgelist which is used to map the insert vector to what edge
- an expression should be inserted on. */
+/* Given local properties TRANSP, ANTLOC, AVOUT, KILL return the insert and
+ delete vectors for edge based LCM. Returns an edgelist which is used to
+ map the insert vector to what edge an expression should be inserted on. */
struct edge_list *
pre_edge_lcm (file, n_exprs, transp, avloc, antloc, kill, insert, delete)
avin = sbitmap_vector_alloc (n_basic_blocks, n_exprs);
avout = sbitmap_vector_alloc (n_basic_blocks, n_exprs);
compute_available (avloc, kill, avout, avin);
-
-
free (avin);
/* Compute global anticipatability. */
free (avout);
later = sbitmap_vector_alloc (num_edges, n_exprs);
+
/* Allocate an extra element for the exit block in the laterin vector. */
laterin = sbitmap_vector_alloc (n_basic_blocks + 1, n_exprs);
compute_laterin (edge_list, earliest, antloc, later, laterin);
-
#ifdef LCM_DEBUG_INFO
if (file)
{
if (file)
{
dump_sbitmap_vector (file, "pre_insert_map", "", *insert, num_edges);
- dump_sbitmap_vector (file, "pre_delete_map", "", *delete, n_basic_blocks);
+ dump_sbitmap_vector (file, "pre_delete_map", "", *delete,
+ n_basic_blocks);
}
#endif
/* Compute the AVIN and AVOUT vectors from the AVLOC and KILL vectors.
Return the number of passes we performed to iterate to a solution. */
+
void
compute_available (avloc, kill, avout, avin)
sbitmap *avloc, *kill, *avout, *avin;
/* Allocate a worklist array/queue. Entries are only added to the
list if they were not already on the list. So the size is
bounded by the number of basic blocks. */
- tos = worklist = (basic_block *) xmalloc (sizeof (basic_block)
- * n_basic_blocks);
+ tos = worklist
+ = (basic_block *) xmalloc (sizeof (basic_block) * n_basic_blocks);
/* We want a maximal solution. */
sbitmap_vector_ones (avout, n_basic_blocks);
intersection of avouts is the null set. We can identify such blocks
by the special value in the AUX field in the block structure. */
if (b->aux == ENTRY_BLOCK_PTR)
- {
- /* Do not clear the aux field for blocks which are
- successors of the ENTRY block. That way we never
- add then to the worklist again. */
- sbitmap_zero (avin[bb]);
- }
+ /* Do not clear the aux field for blocks which are successors of the
+ ENTRY block. That way we never add then to the worklist again. */
+ sbitmap_zero (avin[bb]);
else
{
/* Clear the aux field of this block so that it can be added to
}
if (sbitmap_union_of_diff (avout[bb], avloc[bb], avin[bb], kill[bb]))
- {
- /* If the out state of this block changed, then we need
- to add the successors of this block to the worklist
- if they are not already on the worklist. */
- for (e = b->succ; e; e = e->succ_next)
+ /* If the out state of this block changed, then we need
+ to add the successors of this block to the worklist
+ if they are not already on the worklist. */
+ for (e = b->succ; e; e = e->succ_next)
+ if (!e->dest->aux && e->dest != EXIT_BLOCK_PTR)
{
- if (!e->dest->aux && e->dest != EXIT_BLOCK_PTR)
- {
- *tos++ = e->dest;
- e->dest->aux = e;
- }
+ *tos++ = e->dest;
+ e->dest->aux = e;
}
- }
}
+
free (tos);
}
/* Compute the farthest vector for edge based lcm. */
+
static void
compute_farthest (edge_list, n_exprs, st_avout, st_avin, st_antin,
kill, farthest)
else
{
if (pred == ENTRY_BLOCK_PTR)
- {
- sbitmap_zero (farthest[x]);
- }
+ sbitmap_zero (farthest[x]);
else
{
sbitmap_difference (difference, st_avout[pred->index],
}
}
}
+
free (temp_bitmap);
free (difference);
}
/* Allocate a worklist array/queue. Entries are only added to the
list if they were not already on the list. So the size is
bounded by the number of basic blocks. */
- tos = worklist = (basic_block *) xmalloc (sizeof (basic_block)
- * (n_basic_blocks + 1));
+ tos = worklist
+ = (basic_block *) xmalloc (sizeof (basic_block) * (n_basic_blocks + 1));
/* Initialize NEARER for each edge and build a mapping from an edge to
its index. */
for (i = 0; i < num_edges; i++)
- INDEX_EDGE (edge_list, i)->aux = (void *)i;
+ INDEX_EDGE (edge_list, i)->aux = (void *) (size_t) i;
/* We want a maximal solution. */
sbitmap_vector_ones (nearer, num_edges);
the exit block. That edge should always have a NEARER value the
same as FARTHEST for that edge. */
for (e = EXIT_BLOCK_PTR->pred; e; e = e->pred_next)
- sbitmap_copy (nearer[(int)e->aux], farthest[(int)e->aux]);
+ sbitmap_copy (nearer[(size_t)e->aux], farthest[(size_t)e->aux]);
/* Add all the blocks to the worklist. This prevents an early exit
from the loop given our optimistic initialization of NEARER. */
bb = b->index;
sbitmap_ones (nearerout[bb]);
for (e = b->succ; e != NULL; e = e->succ_next)
- sbitmap_a_and_b (nearerout[bb], nearerout[bb], nearer[(int)e->aux]);
+ sbitmap_a_and_b (nearerout[bb], nearerout[bb],
+ nearer[(size_t) e->aux]);
/* Calculate NEARER for all incoming edges. */
for (e = b->pred; e != NULL; e = e->pred_next)
- {
- if (sbitmap_union_of_diff (nearer[(int)e->aux],
- farthest[(int)e->aux],
- nearerout[e->dest->index],
- st_avloc[e->dest->index]))
- {
- /* If NEARER for an incoming edge was changed, then we need
- to add the source of the incoming edge to the worklist. */
- if (e->src != ENTRY_BLOCK_PTR && e->src->aux == 0)
- {
- *tos++ = e->src;
- e->src->aux = e;
- }
- }
- }
+ if (sbitmap_union_of_diff (nearer[(size_t) e->aux],
+ farthest[(size_t) e->aux],
+ nearerout[e->dest->index],
+ st_avloc[e->dest->index])
+ /* If NEARER for an incoming edge was changed, then we need
+ to add the source of the incoming edge to the worklist. */
+ && e->src != ENTRY_BLOCK_PTR && e->src->aux == 0)
+ {
+ *tos++ = e->src;
+ e->src->aux = e;
+ }
}
/* Computation of insertion and deletion points requires computing NEAREROUT
for (e = ENTRY_BLOCK_PTR->succ; e != NULL; e = e->succ_next)
sbitmap_a_and_b (nearerout[n_basic_blocks],
nearerout[n_basic_blocks],
- nearer[(int)e->aux]);
+ nearer[(size_t) e->aux]);
free (tos);
}
/* Compute the insertion and deletion points for edge based LCM. */
+
static void
compute_rev_insert_delete (edge_list, st_avloc, nearer, nearerout,
insert, delete)
free (st_avout);
nearer = sbitmap_vector_alloc (num_edges, n_exprs);
+
/* Allocate an extra element for the entry block. */
nearerout = sbitmap_vector_alloc (n_basic_blocks + 1, n_exprs);
compute_nearerout (edge_list, farthest, st_avloc, nearer, nearerout);
*insert = sbitmap_vector_alloc (num_edges, n_exprs);
*delete = sbitmap_vector_alloc (n_basic_blocks, n_exprs);
- compute_rev_insert_delete (edge_list, st_avloc, nearer, nearerout, *insert, *delete);
+ compute_rev_insert_delete (edge_list, st_avloc, nearer, nearerout,
+ *insert, *delete);
free (nearerout);
free (nearer);
if (file)
{
dump_sbitmap_vector (file, "pre_insert_map", "", *insert, num_edges);
- dump_sbitmap_vector (file, "pre_delete_map", "", *delete, n_basic_blocks);
+ dump_sbitmap_vector (file, "pre_delete_map", "", *delete,
+ n_basic_blocks);
}
#endif
return edge_list;
}
+
+/* Mode switching:
+
+ The algorithm for setting the modes consists of scanning the insn list
+ and finding all the insns which require a specific mode. Each insn gets
+ a unique struct seginfo element. These structures are inserted into a list
+ for each basic block. For each entity, there is an array of bb_info over
+ the flow graph basic blocks (local var 'bb_info'), and contains a list
+ of all insns within that basic block, in the order they are encountered.
+
+ For each entity, any basic block WITHOUT any insns requiring a specific
+ mode are given a single entry, without a mode. (Each basic block
+ in the flow graph must have at least one entry in the segment table.)
+
+ The LCM algorithm is then run over the flow graph to determine where to
+ place the sets to the highest-priority value in respect of first the first
+ insn in any one block. Any adjustments required to the transparancy
+ vectors are made, then the next iteration starts for the next-lower
+ priority mode, till for each entity all modes are exhasted.
+
+ More details are located in the code for optimize_mode_switching(). */
+
+/* This structure contains the information for each insn which requires
+ either single or double mode to be set.
+ MODE is the mode this insn must be executed in.
+ INSN_PTR is the insn to be executed.
+ BBNUM is the flow graph basic block this insn occurs in.
+ NEXT is the next insn in the same basic block. */
+struct seginfo
+{
+ int mode;
+ rtx insn_ptr;
+ int bbnum;
+ struct seginfo *next;
+ HARD_REG_SET regs_live;
+};
+
+struct bb_info
+{
+ struct seginfo *seginfo;
+ int computing;
+};
+
+/* These bitmaps are used for the LCM algorithm. */
+
+#ifdef OPTIMIZE_MODE_SWITCHING
+static sbitmap *antic;
+static sbitmap *transp;
+static sbitmap *comp;
+static sbitmap *delete;
+static sbitmap *insert;
+
+static struct seginfo * new_seginfo PARAMS ((int, rtx, int, HARD_REG_SET));;
+static void add_seginfo PARAMS ((struct bb_info *, struct seginfo *));
+static void reg_dies PARAMS ((rtx, HARD_REG_SET));
+static void reg_becomes_live PARAMS ((rtx, rtx, void *));
+static void make_preds_opaque PARAMS ((basic_block, int));
+#endif
+\f
+#ifdef OPTIMIZE_MODE_SWITCHING
+
+/* This function will allocate a new BBINFO structure, initialized
+ with the FP_MODE, INSN, and basic block BB parameters. */
+
+static struct seginfo *
+new_seginfo (mode, insn, bb, regs_live)
+ int mode;
+ rtx insn;
+ int bb;
+ HARD_REG_SET regs_live;
+{
+ struct seginfo *ptr;
+ ptr = xmalloc (sizeof (struct seginfo));
+ ptr->mode = mode;
+ ptr->insn_ptr = insn;
+ ptr->bbnum = bb;
+ ptr->next = NULL;
+ COPY_HARD_REG_SET (ptr->regs_live, regs_live);
+ return ptr;
+}
+
+/* Add a seginfo element to the end of a list.
+ HEAD is a pointer to the list beginning.
+ INFO is the structure to be linked in. */
+
+static void
+add_seginfo (head, info)
+ struct bb_info *head;
+ struct seginfo *info;
+{
+ struct seginfo *ptr;
+
+ if (head->seginfo == NULL)
+ head->seginfo = info;
+ else
+ {
+ ptr = head->seginfo;
+ while (ptr->next != NULL)
+ ptr = ptr->next;
+ ptr->next = info;
+ }
+}
+
+/* Make all predecessors of basic block B opaque, recursively, till we hit
+ some that are already non-transparent, or an edge where aux is set; that
+ denotes that a mode set is to be done on that edge.
+ J is the bit number in the bitmaps that corresponds to the entity that
+ we are currently handling mode-switching for. */
+
+static void
+make_preds_opaque (b, j)
+ basic_block b;
+ int j;
+{
+ edge e;
+
+ for (e = b->pred; e; e = e->pred_next)
+ {
+ basic_block pb = e->src;
+
+ if (e->aux || ! TEST_BIT (transp[pb->index], j))
+ continue;
+
+ RESET_BIT (transp[pb->index], j);
+ make_preds_opaque (pb, j);
+ }
+}
+
+/* Record in LIVE that register REG died. */
+
+static void
+reg_dies (reg, live)
+ rtx reg;
+ HARD_REG_SET live;
+{
+ int regno, nregs;
+
+ if (GET_CODE (reg) != REG)
+ return;
+
+ regno = REGNO (reg);
+ if (regno < FIRST_PSEUDO_REGISTER)
+ for (nregs = HARD_REGNO_NREGS (regno, GET_MODE (reg)) - 1; nregs >= 0;
+ nregs--)
+ CLEAR_HARD_REG_BIT (live, regno + nregs);
+}
+
+/* Record in LIVE that register REG became live.
+ This is called via note_stores. */
+
+static void
+reg_becomes_live (reg, setter, live)
+ rtx reg;
+ rtx setter ATTRIBUTE_UNUSED;
+ void *live;
+{
+ int regno, nregs;
+
+ if (GET_CODE (reg) == SUBREG)
+ reg = SUBREG_REG (reg);
+
+ if (GET_CODE (reg) != REG)
+ return;
+
+ regno = REGNO (reg);
+ if (regno < FIRST_PSEUDO_REGISTER)
+ for (nregs = HARD_REGNO_NREGS (regno, GET_MODE (reg)) - 1; nregs >= 0;
+ nregs--)
+ SET_HARD_REG_BIT (* (HARD_REG_SET *) live, regno + nregs);
+}
+
+/* Find all insns that need a particular mode setting, and insert the
+ necessary mode switches. Return true if we did work. */
+
+int
+optimize_mode_switching (file)
+ FILE *file;
+{
+ rtx insn;
+ int bb, e;
+ edge eg;
+ int need_commit = 0;
+ sbitmap *kill;
+ struct edge_list *edge_list;
+ static int num_modes[] = NUM_MODES_FOR_MODE_SWITCHING;
+#define N_ENTITIES (sizeof num_modes / sizeof (int))
+ int entity_map[N_ENTITIES];
+ struct bb_info *bb_info[N_ENTITIES];
+ int i, j;
+ int n_entities;
+ int max_num_modes = 0;
+
+ for (e = N_ENTITIES - 1, n_entities = 0; e >= 0; e--)
+ if (OPTIMIZE_MODE_SWITCHING (e))
+ {
+ /* Create the list of segments within each basic block. */
+ bb_info[n_entities]
+ = (struct bb_info *) xcalloc (n_basic_blocks, sizeof **bb_info);
+ entity_map[n_entities++] = e;
+ if (num_modes[e] > max_num_modes)
+ max_num_modes = num_modes[e];
+ }
+
+ if (! n_entities)
+ return 0;
+
+#ifdef MODE_USES_IN_EXIT_BLOCK
+ /* For some ABIs a particular mode setting is required at function exit. */
+
+ for (eg = EXIT_BLOCK_PTR->pred; eg; eg = eg->pred_next)
+ {
+ int bb = eg->src->index;
+ rtx insn = BLOCK_END (bb);
+ rtx use = MODE_USES_IN_EXIT_BLOCK;
+
+ /* If the block ends with the use of the return value
+ and / or a return, insert the new use(s) in front of them. */
+ while ((GET_CODE (insn) == INSN && GET_CODE (PATTERN (insn)) == USE)
+ || GET_CODE (insn) == JUMP_INSN)
+ insn = PREV_INSN (insn);
+
+ use = emit_insn_after (use, insn);
+ if (insn == BLOCK_END (bb))
+ BLOCK_END (bb) = use;
+ else if (NEXT_INSN (use) == BLOCK_HEAD (bb))
+ BLOCK_HEAD (bb) = NEXT_INSN (insn);
+ }
+#endif /* MODE_USES_IN_EXIT_BLOCK */
+
+ /* Create the bitmap vectors. */
+
+ antic = sbitmap_vector_alloc (n_basic_blocks, n_entities);
+ transp = sbitmap_vector_alloc (n_basic_blocks, n_entities);
+ comp = sbitmap_vector_alloc (n_basic_blocks, n_entities);
+
+ sbitmap_vector_ones (transp, n_basic_blocks);
+
+ for (j = n_entities - 1; j >= 0; j--)
+ {
+ int e = entity_map[j];
+ int no_mode = num_modes[e];
+ struct bb_info *info = bb_info[j];
+
+ /* Determine what the first use (if any) need for a mode of entity E is.
+ This will be the mode that is anticipatable for this block.
+ Also compute the initial transparency settings. */
+ for (bb = 0 ; bb < n_basic_blocks; bb++)
+ {
+ struct seginfo *ptr;
+ int last_mode = no_mode;
+ HARD_REG_SET live_now;
+
+ REG_SET_TO_HARD_REG_SET (live_now,
+ BASIC_BLOCK (bb)->global_live_at_start);
+ for (insn = BLOCK_HEAD (bb);
+ insn != NULL && insn != NEXT_INSN (BLOCK_END (bb));
+ insn = NEXT_INSN (insn))
+ {
+ if (GET_RTX_CLASS (GET_CODE (insn)) == 'i')
+ {
+ int mode = MODE_NEEDED (e, insn);
+ rtx link;
+
+ if (mode != no_mode && mode != last_mode)
+ {
+ last_mode = mode;
+ ptr = new_seginfo (mode, insn, bb, live_now);
+ add_seginfo (info + bb, ptr);
+ RESET_BIT (transp[bb], j);
+ }
+
+ /* Update LIVE_NOW. */
+ for (link = REG_NOTES (insn); link; link = XEXP (link, 1))
+ if (REG_NOTE_KIND (link) == REG_DEAD)
+ reg_dies (XEXP (link, 0), live_now);
+
+ note_stores (PATTERN (insn), reg_becomes_live, &live_now);
+ for (link = REG_NOTES (insn); link; link = XEXP (link, 1))
+ if (REG_NOTE_KIND (link) == REG_UNUSED)
+ reg_dies (XEXP (link, 0), live_now);
+ }
+ }
+
+ info[bb].computing = last_mode;
+ /* Check for blocks without ANY mode requirements. */
+ if (last_mode == no_mode)
+ {
+ ptr = new_seginfo (no_mode, insn, bb, live_now);
+ add_seginfo (info + bb, ptr);
+ }
+ }
+#ifdef MODE_AT_ENTRY
+ {
+ int mode = MODE_AT_ENTRY (e);
+
+ if (mode != no_mode)
+ {
+ for (eg = ENTRY_BLOCK_PTR->succ; eg; eg = eg->succ_next)
+ {
+ bb = eg->dest->index;
+
+ /* By always making this nontransparent, we save
+ an extra check in make_preds_opaque. We also
+ need this to avoid confusing pre_edge_lcm when
+ antic is cleared but transp and comp are set. */
+ RESET_BIT (transp[bb], j);
+
+ /* If the block already has MODE, pretend it
+ has none (because we don't need to set it),
+ but retain whatever mode it computes. */
+ if (info[bb].seginfo->mode == mode)
+ info[bb].seginfo->mode = no_mode;
+
+ /* Insert a fake computing definition of MODE into entry
+ blocks which compute no mode. This represents the mode on
+ entry. */
+ else if (info[bb].computing == no_mode)
+ {
+ info[bb].computing = mode;
+ info[bb].seginfo->mode = no_mode;
+ }
+ }
+ }
+ }
+#endif /* MODE_AT_ENTRY */
+ }
+
+ kill = sbitmap_vector_alloc (n_basic_blocks, n_entities);
+ for (i = 0; i < max_num_modes; i++)
+ {
+ int current_mode[N_ENTITIES];
+
+ /* Set the anticipatable and computing arrays. */
+ sbitmap_vector_zero (antic, n_basic_blocks);
+ sbitmap_vector_zero (comp, n_basic_blocks);
+ for (j = n_entities - 1; j >= 0; j--)
+ {
+ int m = current_mode[j] = MODE_PRIORITY_TO_MODE (entity_map[j], i);
+ struct bb_info *info = bb_info[j];
+
+ for (bb = 0 ; bb < n_basic_blocks; bb++)
+ {
+ if (info[bb].seginfo->mode == m)
+ SET_BIT (antic[bb], j);
+
+ if (info[bb].computing == m)
+ SET_BIT (comp[bb], j);
+ }
+ }
+
+ /* Calculate the optimal locations for the
+ placement mode switches to modes with priority I. */
+
+ for (bb = n_basic_blocks - 1; bb >= 0; bb--)
+ sbitmap_not (kill[bb], transp[bb]);
+ edge_list = pre_edge_lcm (file, 1, transp, comp, antic,
+ kill, &insert, &delete);
+
+ for (j = n_entities - 1; j >= 0; j--)
+ {
+ /* Insert all mode sets that have been inserted by lcm. */
+ int no_mode = num_modes[entity_map[j]];
+
+ /* Wherever we have moved a mode setting upwards in the flow graph,
+ the blocks between the new setting site and the now redundant
+ computation ceases to be transparent for any lower-priority
+ mode of the same entity. First set the aux field of each
+ insertion site edge non-transparent, then propagate the new
+ non-transparency from the redundant computation upwards till
+ we hit an insertion site or an already non-transparent block. */
+ for (e = NUM_EDGES (edge_list) - 1; e >= 0; e--)
+ {
+ edge eg = INDEX_EDGE (edge_list, e);
+ int mode;
+ basic_block src_bb;
+ HARD_REG_SET live_at_edge;
+ rtx mode_set;
+
+ eg->aux = 0;
+
+ if (! TEST_BIT (insert[e], j))
+ continue;
+
+ eg->aux = (void *)1;
+
+ mode = current_mode[j];
+ src_bb = eg->src;
+
+ REG_SET_TO_HARD_REG_SET (live_at_edge,
+ src_bb->global_live_at_end);
+
+ start_sequence ();
+ EMIT_MODE_SET (entity_map[j], mode, live_at_edge);
+ mode_set = gen_sequence ();
+ end_sequence ();
+
+ /* If this is an abnormal edge, we'll insert at the end of the
+ previous block. */
+ if (eg->flags & EDGE_ABNORMAL)
+ {
+ src_bb->end = emit_insn_after (mode_set, src_bb->end);
+ bb_info[j][src_bb->index].computing = mode;
+ RESET_BIT (transp[src_bb->index], j);
+ }
+ else
+ {
+ need_commit = 1;
+ insert_insn_on_edge (mode_set, eg);
+ }
+ }
+
+ for (bb = n_basic_blocks - 1; bb >= 0; bb--)
+ if (TEST_BIT (delete[bb], j))
+ {
+ make_preds_opaque (BASIC_BLOCK (bb), j);
+ /* Cancel the 'deleted' mode set. */
+ bb_info[j][bb].seginfo->mode = no_mode;
+ }
+ }
+
+ free_edge_list (edge_list);
+ }
+
+ /* Now output the remaining mode sets in all the segments. */
+ for (j = n_entities - 1; j >= 0; j--)
+ {
+ for (bb = n_basic_blocks - 1; bb >= 0; bb--)
+ {
+ struct seginfo *ptr, *next;
+ for (ptr = bb_info[j][bb].seginfo; ptr; ptr = next)
+ {
+ next = ptr->next;
+ if (ptr->mode != FP_MODE_NONE)
+ {
+ rtx mode_set;
+
+ start_sequence ();
+ EMIT_MODE_SET (entity_map[j], ptr->mode, ptr->regs_live);
+ mode_set = gen_sequence ();
+ end_sequence ();
+
+ emit_block_insn_before (mode_set, ptr->insn_ptr,
+ BASIC_BLOCK (ptr->bbnum));
+ }
+
+ free (ptr);
+ }
+ }
+
+ free (bb_info[j]);
+ }
+
+ /* Finished. Free up all the things we've allocated. */
+
+ sbitmap_vector_free (kill);
+ sbitmap_vector_free (antic);
+ sbitmap_vector_free (transp);
+ sbitmap_vector_free (comp);
+ sbitmap_vector_free (delete);
+ sbitmap_vector_free (insert);
+
+ if (need_commit)
+ commit_edge_insertions ();
+
+ /* Ideally we'd figure out what blocks were affected and start from
+ there, but this is enormously complicated by commit_edge_insertions,
+ which would screw up any indicies we'd collected, and also need to
+ be involved in the update. Bail and recompute global life info for
+ everything. */
+
+ allocate_reg_life_data ();
+ update_life_info (NULL, UPDATE_LIFE_GLOBAL_RM_NOTES,
+ (PROP_DEATH_NOTES | PROP_KILL_DEAD_CODE
+ | PROP_SCAN_DEAD_CODE | PROP_REG_INFO));
+
+ return 1;
+}
+#endif /* OPTIMIZE_MODE_SWITCHING */
OSDN Git Service
