II cycles (i.e. use register copies to prevent a def from overwriting
itself before reaching the use).
- SMS works with countable loops whose loop count can be easily
- adjusted. This is because we peel a constant number of iterations
- into a prologue and epilogue for which we want to avoid emitting
- the control part, and a kernel which is to iterate that constant
- number of iterations less than the original loop. So the control
- part should be a set of insns clearly identified and having its
- own iv, not otherwise used in the loop (at-least for now), which
+ SMS works with countable loops (1) whose control part can be easily
+ decoupled from the rest of the loop and (2) whose loop count can
+ be easily adjusted. This is because we peel a constant number of
+ iterations into a prologue and epilogue for which we want to avoid
+ emitting the control part, and a kernel which is to iterate that
+ constant number of iterations less than the original loop. So the
+ control part should be a set of insns clearly identified and having
+ its own iv, not otherwise used in the loop (at-least for now), which
initializes a register before the loop to the number of iterations.
Currently SMS relies on the do-loop pattern to recognize such loops,
where (1) the control part comprises of all insns defining and/or
ps_insn_ptr next_in_row,
prev_in_row;
- /* The number of nodes in the same row that come after this node. */
- int row_rest_count;
};
/* Holds the partial schedule as an array of II rows. Each entry of the
/* rows[i] points to linked list of insns scheduled in row i (0<=i<ii). */
ps_insn_ptr *rows;
+ /* rows_length[i] holds the number of instructions in the row.
+ It is used only (as an optimization) to back off quickly from
+ trying to schedule a node in a full row; that is, to avoid running
+ through futile DFA state transitions. */
+ int *rows_length;
+
/* The earliest absolute cycle of an insn in the partial schedule. */
int min_cycle;
rtx, rtx);
static void duplicate_insns_of_cycles (partial_schedule_ptr,
int, int, int, rtx);
-static int calculate_stage_count (partial_schedule_ptr ps);
+static int calculate_stage_count (partial_schedule_ptr, int);
+static void calculate_must_precede_follow (ddg_node_ptr, int, int,
+ int, int, sbitmap, sbitmap, sbitmap);
+static int get_sched_window (partial_schedule_ptr, ddg_node_ptr,
+ sbitmap, int, int *, int *, int *);
+static bool try_scheduling_node_in_cycle (partial_schedule_ptr, ddg_node_ptr,
+ int, int, sbitmap, int *, sbitmap,
+ sbitmap);
+static bool remove_node_from_ps (partial_schedule_ptr, ps_insn_ptr);
+
#define SCHED_ASAP(x) (((node_sched_params_ptr)(x)->aux.info)->asap)
#define SCHED_TIME(x) (((node_sched_params_ptr)(x)->aux.info)->time)
#define SCHED_FIRST_REG_MOVE(x) \
static void
compute_jump_reg_dependencies (rtx insn ATTRIBUTE_UNUSED,
- regset cond_exec ATTRIBUTE_UNUSED,
- regset used ATTRIBUTE_UNUSED,
- regset set ATTRIBUTE_UNUSED)
+ regset used ATTRIBUTE_UNUSED)
{
}
0, 0,
NULL, NULL, NULL, NULL,
+ NULL, NULL,
0
};
}
}
+/* Update the sched_params (time, row and stage) for node U using the II,
+ the CYCLE of U and MIN_CYCLE.
+ We're not simply taking the following
+ SCHED_STAGE (u) = CALC_STAGE_COUNT (SCHED_TIME (u), min_cycle, ii);
+ because the stages may not be aligned on cycle 0. */
+static void
+update_node_sched_params (ddg_node_ptr u, int ii, int cycle, int min_cycle)
+{
+ int sc_until_cycle_zero;
+ int stage;
+
+ SCHED_TIME (u) = cycle;
+ SCHED_ROW (u) = SMODULO (cycle, ii);
+
+ /* The calculation of stage count is done adding the number
+ of stages before cycle zero and after cycle zero. */
+ sc_until_cycle_zero = CALC_STAGE_COUNT (-1, min_cycle, ii);
+
+ if (SCHED_TIME (u) < 0)
+ {
+ stage = CALC_STAGE_COUNT (-1, SCHED_TIME (u), ii);
+ SCHED_STAGE (u) = sc_until_cycle_zero - stage;
+ }
+ else
+ {
+ stage = CALC_STAGE_COUNT (SCHED_TIME (u), 0, ii);
+ SCHED_STAGE (u) = sc_until_cycle_zero + stage - 1;
+ }
+}
+
/* Bump the SCHED_TIMEs of all nodes by AMOUNT. Set the values of
SCHED_ROW and SCHED_STAGE. Instruction scheduled on cycle AMOUNT
will move to cycle zero. */
ddg_node_ptr u = crr_insn->node;
int normalized_time = SCHED_TIME (u) - amount;
int new_min_cycle = PS_MIN_CYCLE (ps) - amount;
- int sc_until_cycle_zero, stage;
if (dump_file)
{
/* Print the scheduling times after the rotation. */
fprintf (dump_file, "crr_insn->node=%d (insn id %d), "
"crr_insn->cycle=%d, min_cycle=%d", crr_insn->node->cuid,
- INSN_UID (crr_insn->node->insn), SCHED_TIME (u),
- normalized_time);
+ INSN_UID (crr_insn->node->insn), normalized_time,
+ new_min_cycle);
if (JUMP_P (crr_insn->node->insn))
fprintf (dump_file, " (branch)");
fprintf (dump_file, "\n");
gcc_assert (SCHED_TIME (u) >= ps->min_cycle);
gcc_assert (SCHED_TIME (u) <= ps->max_cycle);
- SCHED_TIME (u) = normalized_time;
- SCHED_ROW (u) = SMODULO (normalized_time, ii);
-
- /* The calculation of stage count is done adding the number
- of stages before cycle zero and after cycle zero. */
- sc_until_cycle_zero = CALC_STAGE_COUNT (-1, new_min_cycle, ii);
-
- if (SCHED_TIME (u) < 0)
- {
- stage = CALC_STAGE_COUNT (-1, SCHED_TIME (u), ii);
- SCHED_STAGE (u) = sc_until_cycle_zero - stage;
- }
- else
- {
- stage = CALC_STAGE_COUNT (SCHED_TIME (u), 0, ii);
- SCHED_STAGE (u) = sc_until_cycle_zero + stage - 1;
- }
+
+ crr_insn->cycle = normalized_time;
+ update_node_sched_params (u, ii, normalized_time, new_min_cycle);
}
}
PREV_INSN (last));
}
+/* Set bitmaps TMP_FOLLOW and TMP_PRECEDE to MUST_FOLLOW and MUST_PRECEDE
+ respectively only if cycle C falls on the border of the scheduling
+ window boundaries marked by START and END cycles. STEP is the
+ direction of the window. */
+static inline void
+set_must_precede_follow (sbitmap *tmp_follow, sbitmap must_follow,
+ sbitmap *tmp_precede, sbitmap must_precede, int c,
+ int start, int end, int step)
+{
+ *tmp_precede = NULL;
+ *tmp_follow = NULL;
+
+ if (c == start)
+ {
+ if (step == 1)
+ *tmp_precede = must_precede;
+ else /* step == -1. */
+ *tmp_follow = must_follow;
+ }
+ if (c == end - step)
+ {
+ if (step == 1)
+ *tmp_follow = must_follow;
+ else /* step == -1. */
+ *tmp_precede = must_precede;
+ }
+
+}
+
+/* Return True if the branch can be moved to row ii-1 while
+ normalizing the partial schedule PS to start from cycle zero and thus
+ optimize the SC. Otherwise return False. */
+static bool
+optimize_sc (partial_schedule_ptr ps, ddg_ptr g)
+{
+ int amount = PS_MIN_CYCLE (ps);
+ sbitmap sched_nodes = sbitmap_alloc (g->num_nodes);
+ int start, end, step;
+ int ii = ps->ii;
+ bool ok = false;
+ int stage_count, stage_count_curr;
+
+ /* Compare the SC after normalization and SC after bringing the branch
+ to row ii-1. If they are equal just bail out. */
+ stage_count = calculate_stage_count (ps, amount);
+ stage_count_curr =
+ calculate_stage_count (ps, SCHED_TIME (g->closing_branch) - (ii - 1));
+
+ if (stage_count == stage_count_curr)
+ {
+ if (dump_file)
+ fprintf (dump_file, "SMS SC already optimized.\n");
+
+ ok = false;
+ goto clear;
+ }
+
+ if (dump_file)
+ {
+ fprintf (dump_file, "SMS Trying to optimize branch location\n");
+ fprintf (dump_file, "SMS partial schedule before trial:\n");
+ print_partial_schedule (ps, dump_file);
+ }
+
+ /* First, normalize the partial scheduling. */
+ reset_sched_times (ps, amount);
+ rotate_partial_schedule (ps, amount);
+ if (dump_file)
+ {
+ fprintf (dump_file,
+ "SMS partial schedule after normalization (ii, %d, SC %d):\n",
+ ii, stage_count);
+ print_partial_schedule (ps, dump_file);
+ }
+
+ if (SMODULO (SCHED_TIME (g->closing_branch), ii) == ii - 1)
+ {
+ ok = true;
+ goto clear;
+ }
+
+ sbitmap_ones (sched_nodes);
+
+ /* Calculate the new placement of the branch. It should be in row
+ ii-1 and fall into it's scheduling window. */
+ if (get_sched_window (ps, g->closing_branch, sched_nodes, ii, &start,
+ &step, &end) == 0)
+ {
+ bool success;
+ ps_insn_ptr next_ps_i;
+ int branch_cycle = SCHED_TIME (g->closing_branch);
+ int row = SMODULO (branch_cycle, ps->ii);
+ int num_splits = 0;
+ sbitmap must_precede, must_follow, tmp_precede, tmp_follow;
+ int c;
+
+ if (dump_file)
+ fprintf (dump_file, "\nTrying to schedule node %d "
+ "INSN = %d in (%d .. %d) step %d\n",
+ g->closing_branch->cuid,
+ (INSN_UID (g->closing_branch->insn)), start, end, step);
+
+ gcc_assert ((step > 0 && start < end) || (step < 0 && start > end));
+ if (step == 1)
+ {
+ c = start + ii - SMODULO (start, ii) - 1;
+ gcc_assert (c >= start);
+ if (c >= end)
+ {
+ ok = false;
+ if (dump_file)
+ fprintf (dump_file,
+ "SMS failed to schedule branch at cycle: %d\n", c);
+ goto clear;
+ }
+ }
+ else
+ {
+ c = start - SMODULO (start, ii) - 1;
+ gcc_assert (c <= start);
+
+ if (c <= end)
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ "SMS failed to schedule branch at cycle: %d\n", c);
+ ok = false;
+ goto clear;
+ }
+ }
+
+ must_precede = sbitmap_alloc (g->num_nodes);
+ must_follow = sbitmap_alloc (g->num_nodes);
+
+ /* Try to schedule the branch is it's new cycle. */
+ calculate_must_precede_follow (g->closing_branch, start, end,
+ step, ii, sched_nodes,
+ must_precede, must_follow);
+
+ set_must_precede_follow (&tmp_follow, must_follow, &tmp_precede,
+ must_precede, c, start, end, step);
+
+ /* Find the element in the partial schedule related to the closing
+ branch so we can remove it from it's current cycle. */
+ for (next_ps_i = ps->rows[row];
+ next_ps_i; next_ps_i = next_ps_i->next_in_row)
+ if (next_ps_i->node->cuid == g->closing_branch->cuid)
+ break;
+
+ gcc_assert (next_ps_i);
+ gcc_assert (remove_node_from_ps (ps, next_ps_i));
+ success =
+ try_scheduling_node_in_cycle (ps, g->closing_branch,
+ g->closing_branch->cuid, c,
+ sched_nodes, &num_splits,
+ tmp_precede, tmp_follow);
+ gcc_assert (num_splits == 0);
+ if (!success)
+ {
+ if (dump_file)
+ fprintf (dump_file,
+ "SMS failed to schedule branch at cycle: %d, "
+ "bringing it back to cycle %d\n", c, branch_cycle);
+
+ /* The branch was failed to be placed in row ii - 1.
+ Put it back in it's original place in the partial
+ schedualing. */
+ set_must_precede_follow (&tmp_follow, must_follow, &tmp_precede,
+ must_precede, branch_cycle, start, end,
+ step);
+ success =
+ try_scheduling_node_in_cycle (ps, g->closing_branch,
+ g->closing_branch->cuid,
+ branch_cycle, sched_nodes,
+ &num_splits, tmp_precede,
+ tmp_follow);
+ gcc_assert (success && (num_splits == 0));
+ ok = false;
+ }
+ else
+ {
+ /* The branch is placed in row ii - 1. */
+ if (dump_file)
+ fprintf (dump_file,
+ "SMS success in moving branch to cycle %d\n", c);
+
+ update_node_sched_params (g->closing_branch, ii, c,
+ PS_MIN_CYCLE (ps));
+ ok = true;
+ }
+
+ free (must_precede);
+ free (must_follow);
+ }
+
+clear:
+ free (sched_nodes);
+ return ok;
+}
+
static void
duplicate_insns_of_cycles (partial_schedule_ptr ps, int from_stage,
int to_stage, int for_prolog, rtx count_reg)
int mii, rec_mii;
unsigned stage_count = 0;
HOST_WIDEST_INT loop_count = 0;
+ bool opt_sc_p = false;
if (! (g = g_arr[loop->num]))
continue;
set_node_sched_params (g);
ps = sms_schedule_by_order (g, mii, maxii, node_order);
-
- if (ps)
- {
- stage_count = calculate_stage_count (ps);
- gcc_assert(stage_count >= 1);
- PS_STAGE_COUNT(ps) = stage_count;
- }
-
+
+ if (ps)
+ {
+ /* Try to achieve optimized SC by normalizing the partial
+ schedule (having the cycles start from cycle zero).
+ The branch location must be placed in row ii-1 in the
+ final scheduling. If failed, shift all instructions to
+ position the branch in row ii-1. */
+ opt_sc_p = optimize_sc (ps, g);
+ if (opt_sc_p)
+ stage_count = calculate_stage_count (ps, 0);
+ else
+ {
+ /* Bring the branch to cycle ii-1. */
+ int amount = SCHED_TIME (g->closing_branch) - (ps->ii - 1);
+
+ if (dump_file)
+ fprintf (dump_file, "SMS schedule branch at cycle ii-1\n");
+
+ stage_count = calculate_stage_count (ps, amount);
+ }
+
+ gcc_assert (stage_count >= 1);
+ PS_STAGE_COUNT (ps) = stage_count;
+ }
+
/* The default value of PARAM_SMS_MIN_SC is 2 as stage count of
1 means that there is no interleaving between iterations thus
we let the scheduling passes do the job in this case. */
else
{
struct undo_replace_buff_elem *reg_move_replaces;
- int amount = SCHED_TIME (g->closing_branch) + 1;
+
+ if (!opt_sc_p)
+ {
+ /* Rotate the partial schedule to have the branch in row ii-1. */
+ int amount = SCHED_TIME (g->closing_branch) - (ps->ii - 1);
+
+ reset_sched_times (ps, amount);
+ rotate_partial_schedule (ps, amount);
+ }
- /* Set the stage boundaries. The closing_branch was scheduled
- and should appear in the last (ii-1) row. */
- reset_sched_times (ps, amount);
- rotate_partial_schedule (ps, amount);
set_columns_for_ps (ps);
canon_loop (loop);
scheduling window is empty and zero otherwise. */
static int
-get_sched_window (partial_schedule_ptr ps, int *nodes_order, int i,
- sbitmap sched_nodes, int ii, int *start_p, int *step_p, int *end_p)
+get_sched_window (partial_schedule_ptr ps, ddg_node_ptr u_node,
+ sbitmap sched_nodes, int ii, int *start_p, int *step_p,
+ int *end_p)
{
int start, step, end;
+ int early_start, late_start;
ddg_edge_ptr e;
- int u = nodes_order [i];
- ddg_node_ptr u_node = &ps->g->nodes[u];
sbitmap psp = sbitmap_alloc (ps->g->num_nodes);
sbitmap pss = sbitmap_alloc (ps->g->num_nodes);
sbitmap u_node_preds = NODE_PREDECESSORS (u_node);
sbitmap u_node_succs = NODE_SUCCESSORS (u_node);
int psp_not_empty;
int pss_not_empty;
+ int count_preds;
+ int count_succs;
/* 1. compute sched window for u (start, end, step). */
sbitmap_zero (psp);
psp_not_empty = sbitmap_a_and_b_cg (psp, u_node_preds, sched_nodes);
pss_not_empty = sbitmap_a_and_b_cg (pss, u_node_succs, sched_nodes);
- if (psp_not_empty && !pss_not_empty)
- {
- int early_start = INT_MIN;
-
- end = INT_MAX;
- for (e = u_node->in; e != 0; e = e->next_in)
- {
- ddg_node_ptr v_node = e->src;
+ /* We first compute a forward range (start <= end), then decide whether
+ to reverse it. */
+ early_start = INT_MIN;
+ late_start = INT_MAX;
+ start = INT_MIN;
+ end = INT_MAX;
+ step = 1;
- if (dump_file)
- {
- fprintf (dump_file, "\nProcessing edge: ");
- print_ddg_edge (dump_file, e);
- fprintf (dump_file,
- "\nScheduling %d (%d) in psp_not_empty,"
- " checking p %d (%d): ", u_node->cuid,
- INSN_UID (u_node->insn), v_node->cuid, INSN_UID
- (v_node->insn));
- }
+ count_preds = 0;
+ count_succs = 0;
- if (TEST_BIT (sched_nodes, v_node->cuid))
- {
- int p_st = SCHED_TIME (v_node);
-
- early_start =
- MAX (early_start, p_st + e->latency - (e->distance * ii));
-
- if (dump_file)
- fprintf (dump_file,
- "pred st = %d; early_start = %d; latency: %d",
- p_st, early_start, e->latency);
-
- if (e->data_type == MEM_DEP)
- end = MIN (end, SCHED_TIME (v_node) + ii - 1);
- }
- else if (dump_file)
- fprintf (dump_file, "the node is not scheduled\n");
- }
- start = early_start;
- end = MIN (end, early_start + ii);
- /* Schedule the node close to it's predecessors. */
- step = 1;
-
- if (dump_file)
- fprintf (dump_file,
- "\nScheduling %d (%d) in a window (%d..%d) with step %d\n",
- u_node->cuid, INSN_UID (u_node->insn), start, end, step);
- }
-
- else if (!psp_not_empty && pss_not_empty)
+ if (dump_file && (psp_not_empty || pss_not_empty))
{
- int late_start = INT_MAX;
-
- end = INT_MIN;
- for (e = u_node->out; e != 0; e = e->next_out)
- {
- ddg_node_ptr v_node = e->dest;
-
- if (dump_file)
- {
- fprintf (dump_file, "\nProcessing edge:");
- print_ddg_edge (dump_file, e);
- fprintf (dump_file,
- "\nScheduling %d (%d) in pss_not_empty,"
- " checking s %d (%d): ", u_node->cuid,
- INSN_UID (u_node->insn), v_node->cuid, INSN_UID
- (v_node->insn));
- }
-
- if (TEST_BIT (sched_nodes, v_node->cuid))
- {
- int s_st = SCHED_TIME (v_node);
-
- late_start = MIN (late_start,
- s_st - e->latency + (e->distance * ii));
-
- if (dump_file)
- fprintf (dump_file,
- "succ st = %d; late_start = %d; latency = %d",
- s_st, late_start, e->latency);
-
- if (e->data_type == MEM_DEP)
- end = MAX (end, SCHED_TIME (v_node) - ii + 1);
- if (dump_file)
- fprintf (dump_file, "end = %d\n", end);
-
- }
- else if (dump_file)
- fprintf (dump_file, "the node is not scheduled\n");
-
- }
- start = late_start;
- end = MAX (end, late_start - ii);
- /* Schedule the node close to it's successors. */
- step = -1;
-
- if (dump_file)
- fprintf (dump_file,
- "\nScheduling %d (%d) in a window (%d..%d) with step %d\n",
- u_node->cuid, INSN_UID (u_node->insn), start, end, step);
-
+ fprintf (dump_file, "\nAnalyzing dependencies for node %d (INSN %d)"
+ "; ii = %d\n\n", u_node->cuid, INSN_UID (u_node->insn), ii);
+ fprintf (dump_file, "%11s %11s %11s %11s %5s\n",
+ "start", "early start", "late start", "end", "time");
+ fprintf (dump_file, "=========== =========== =========== ==========="
+ " =====\n");
}
+ /* Calculate early_start and limit end. Both bounds are inclusive. */
+ if (psp_not_empty)
+ for (e = u_node->in; e != 0; e = e->next_in)
+ {
+ ddg_node_ptr v_node = e->src;
- else if (psp_not_empty && pss_not_empty)
- {
- int early_start = INT_MIN;
- int late_start = INT_MAX;
- int count_preds = 0;
- int count_succs = 0;
-
- start = INT_MIN;
- end = INT_MAX;
- for (e = u_node->in; e != 0; e = e->next_in)
- {
- ddg_node_ptr v_node = e->src;
-
- if (dump_file)
- {
- fprintf (dump_file, "\nProcessing edge:");
- print_ddg_edge (dump_file, e);
- fprintf (dump_file,
- "\nScheduling %d (%d) in psp_pss_not_empty,"
- " checking p %d (%d): ", u_node->cuid, INSN_UID
- (u_node->insn), v_node->cuid, INSN_UID
- (v_node->insn));
- }
-
- if (TEST_BIT (sched_nodes, v_node->cuid))
- {
- int p_st = SCHED_TIME (v_node);
+ if (TEST_BIT (sched_nodes, v_node->cuid))
+ {
+ int p_st = SCHED_TIME (v_node);
+ int earliest = p_st + e->latency - (e->distance * ii);
+ int latest = (e->data_type == MEM_DEP ? p_st + ii - 1 : INT_MAX);
- early_start = MAX (early_start,
- p_st + e->latency
- - (e->distance * ii));
+ if (dump_file)
+ {
+ fprintf (dump_file, "%11s %11d %11s %11d %5d",
+ "", earliest, "", latest, p_st);
+ print_ddg_edge (dump_file, e);
+ fprintf (dump_file, "\n");
+ }
- if (dump_file)
- fprintf (dump_file,
- "pred st = %d; early_start = %d; latency = %d",
- p_st, early_start, e->latency);
+ early_start = MAX (early_start, earliest);
+ end = MIN (end, latest);
- if (e->type == TRUE_DEP && e->data_type == REG_DEP)
- count_preds++;
+ if (e->type == TRUE_DEP && e->data_type == REG_DEP)
+ count_preds++;
+ }
+ }
- if (e->data_type == MEM_DEP)
- end = MIN (end, SCHED_TIME (v_node) + ii - 1);
- }
- else if (dump_file)
- fprintf (dump_file, "the node is not scheduled\n");
+ /* Calculate late_start and limit start. Both bounds are inclusive. */
+ if (pss_not_empty)
+ for (e = u_node->out; e != 0; e = e->next_out)
+ {
+ ddg_node_ptr v_node = e->dest;
- }
- for (e = u_node->out; e != 0; e = e->next_out)
- {
- ddg_node_ptr v_node = e->dest;
+ if (TEST_BIT (sched_nodes, v_node->cuid))
+ {
+ int s_st = SCHED_TIME (v_node);
+ int earliest = (e->data_type == MEM_DEP ? s_st - ii + 1 : INT_MIN);
+ int latest = s_st - e->latency + (e->distance * ii);
- if (dump_file)
- {
- fprintf (dump_file, "\nProcessing edge:");
- print_ddg_edge (dump_file, e);
- fprintf (dump_file,
- "\nScheduling %d (%d) in psp_pss_not_empty,"
- " checking s %d (%d): ", u_node->cuid, INSN_UID
- (u_node->insn), v_node->cuid, INSN_UID
- (v_node->insn));
- }
+ if (dump_file)
+ {
+ fprintf (dump_file, "%11d %11s %11d %11s %5d",
+ earliest, "", latest, "", s_st);
+ print_ddg_edge (dump_file, e);
+ fprintf (dump_file, "\n");
+ }
- if (TEST_BIT (sched_nodes, v_node->cuid))
- {
- int s_st = SCHED_TIME (v_node);
+ start = MAX (start, earliest);
+ late_start = MIN (late_start, latest);
- late_start = MIN (late_start,
- s_st - e->latency
- + (e->distance * ii));
+ if (e->type == TRUE_DEP && e->data_type == REG_DEP)
+ count_succs++;
+ }
+ }
- if (dump_file)
- fprintf (dump_file,
- "succ st = %d; late_start = %d; latency = %d",
- s_st, late_start, e->latency);
+ if (dump_file && (psp_not_empty || pss_not_empty))
+ {
+ fprintf (dump_file, "----------- ----------- ----------- -----------"
+ " -----\n");
+ fprintf (dump_file, "%11d %11d %11d %11d %5s %s\n",
+ start, early_start, late_start, end, "",
+ "(max, max, min, min)");
+ }
- if (e->type == TRUE_DEP && e->data_type == REG_DEP)
- count_succs++;
+ /* Get a target scheduling window no bigger than ii. */
+ if (early_start == INT_MIN && late_start == INT_MAX)
+ early_start = SCHED_ASAP (u_node);
+ else if (early_start == INT_MIN)
+ early_start = late_start - (ii - 1);
+ late_start = MIN (late_start, early_start + (ii - 1));
- if (e->data_type == MEM_DEP)
- start = MAX (start, SCHED_TIME (v_node) - ii + 1);
- }
- else if (dump_file)
- fprintf (dump_file, "the node is not scheduled\n");
+ /* Apply memory dependence limits. */
+ start = MAX (start, early_start);
+ end = MIN (end, late_start);
- }
- start = MAX (start, early_start);
- end = MIN (end, MIN (early_start + ii, late_start + 1));
- step = 1;
- /* If there are more successors than predecessors schedule the
- node close to it's successors. */
- if (count_succs >= count_preds)
- {
- int old_start = start;
+ if (dump_file && (psp_not_empty || pss_not_empty))
+ fprintf (dump_file, "%11s %11d %11d %11s %5s final window\n",
+ "", start, end, "", "");
- start = end - 1;
- end = old_start - 1;
- step = -1;
- }
- }
- else /* psp is empty && pss is empty. */
+ /* If there are at least as many successors as predecessors, schedule the
+ node close to its successors. */
+ if (pss_not_empty && count_succs >= count_preds)
{
- start = SCHED_ASAP (u_node);
- end = start + ii;
- step = 1;
+ int tmp = end;
+ end = start;
+ start = tmp;
+ step = -1;
}
+ /* Now that we've finalized the window, make END an exclusive rather
+ than an inclusive bound. */
+ end += step;
+
*start_p = start;
*step_p = step;
*end_p = end;
if (dump_file)
fprintf (dump_file, "\nEmpty window: start=%d, end=%d, step=%d\n",
start, end, step);
- return -1;
+ return -1;
}
- return 0;
+ return 0;
}
/* Calculate MUST_PRECEDE/MUST_FOLLOW bitmaps of U_NODE; which is the
/* Try to get non-empty scheduling window. */
success = 0;
- if (get_sched_window (ps, nodes_order, i, sched_nodes, ii, &start,
+ if (get_sched_window (ps, u_node, sched_nodes, ii, &start,
&step, &end) == 0)
{
if (dump_file)
- fprintf (dump_file, "\nTrying to schedule node %d \
- INSN = %d in (%d .. %d) step %d\n", u, (INSN_UID
+ fprintf (dump_file, "\nTrying to schedule node %d "
+ "INSN = %d in (%d .. %d) step %d\n", u, (INSN_UID
(g->nodes[u].insn)), start, end, step);
gcc_assert ((step > 0 && start < end)
for (c = start; c != end; c += step)
{
- sbitmap tmp_precede = NULL;
- sbitmap tmp_follow = NULL;
-
- if (c == start)
- {
- if (step == 1)
- tmp_precede = must_precede;
- else /* step == -1. */
- tmp_follow = must_follow;
- }
- if (c == end - step)
- {
- if (step == 1)
- tmp_follow = must_follow;
- else /* step == -1. */
- tmp_precede = must_precede;
- }
+ sbitmap tmp_precede, tmp_follow;
+ set_must_precede_follow (&tmp_follow, must_follow,
+ &tmp_precede, must_precede,
+ c, start, end, step);
success =
try_scheduling_node_in_cycle (ps, u_node, u, c,
sched_nodes,
int ii = ps->ii;
int new_ii = ii + 1;
int row;
+ int *rows_length_new;
verify_partial_schedule (ps, sched_nodes);
rotate_partial_schedule (ps, PS_MIN_CYCLE (ps));
rows_new = (ps_insn_ptr *) xcalloc (new_ii, sizeof (ps_insn_ptr));
+ rows_length_new = (int *) xcalloc (new_ii, sizeof (int));
for (row = 0; row < split_row; row++)
{
rows_new[row] = ps->rows[row];
+ rows_length_new[row] = ps->rows_length[row];
ps->rows[row] = NULL;
for (crr_insn = rows_new[row];
crr_insn; crr_insn = crr_insn->next_in_row)
for (row = split_row; row < ii; row++)
{
rows_new[row + 1] = ps->rows[row];
+ rows_length_new[row + 1] = ps->rows_length[row];
ps->rows[row] = NULL;
for (crr_insn = rows_new[row + 1];
crr_insn; crr_insn = crr_insn->next_in_row)
+ (SMODULO (ps->max_cycle, ii) >= split_row ? 1 : 0);
free (ps->rows);
ps->rows = rows_new;
+ free (ps->rows_length);
+ ps->rows_length = rows_length_new;
ps->ii = new_ii;
gcc_assert (ps->min_cycle >= 0);
ps_insn_ptr crr_insn;
for (row = 0; row < ps->ii; row++)
- for (crr_insn = ps->rows[row]; crr_insn; crr_insn = crr_insn->next_in_row)
- {
- ddg_node_ptr u = crr_insn->node;
-
- gcc_assert (TEST_BIT (sched_nodes, u->cuid));
- /* ??? Test also that all nodes of sched_nodes are in ps, perhaps by
- popcount (sched_nodes) == number of insns in ps. */
- gcc_assert (SCHED_TIME (u) >= ps->min_cycle);
- gcc_assert (SCHED_TIME (u) <= ps->max_cycle);
- }
+ {
+ int length = 0;
+
+ for (crr_insn = ps->rows[row]; crr_insn; crr_insn = crr_insn->next_in_row)
+ {
+ ddg_node_ptr u = crr_insn->node;
+
+ length++;
+ gcc_assert (TEST_BIT (sched_nodes, u->cuid));
+ /* ??? Test also that all nodes of sched_nodes are in ps, perhaps by
+ popcount (sched_nodes) == number of insns in ps. */
+ gcc_assert (SCHED_TIME (u) >= ps->min_cycle);
+ gcc_assert (SCHED_TIME (u) <= ps->max_cycle);
+ }
+
+ gcc_assert (ps->rows_length[row] == length);
+ }
}
\f
{
partial_schedule_ptr ps = XNEW (struct partial_schedule);
ps->rows = (ps_insn_ptr *) xcalloc (ii, sizeof (ps_insn_ptr));
+ ps->rows_length = (int *) xcalloc (ii, sizeof (int));
ps->ii = ii;
ps->history = history;
ps->min_cycle = INT_MAX;
return;
free_ps_insns (ps);
free (ps->rows);
+ free (ps->rows_length);
free (ps);
}
ps->rows = (ps_insn_ptr *) xrealloc (ps->rows, new_ii
* sizeof (ps_insn_ptr));
memset (ps->rows, 0, new_ii * sizeof (ps_insn_ptr));
+ ps->rows_length = (int *) xrealloc (ps->rows_length, new_ii * sizeof (int));
+ memset (ps->rows_length, 0, new_ii * sizeof (int));
ps->ii = new_ii;
ps->min_cycle = INT_MAX;
ps->max_cycle = INT_MIN;
fprintf (dump, "\n[ROW %d ]: ", i);
while (ps_i)
{
- fprintf (dump, "%d, ",
- INSN_UID (ps_i->node->insn));
+ if (JUMP_P (ps_i->node->insn))
+ fprintf (dump, "%d (branch), ",
+ INSN_UID (ps_i->node->insn));
+ else
+ fprintf (dump, "%d, ",
+ INSN_UID (ps_i->node->insn));
+
ps_i = ps_i->next_in_row;
}
}
/* Creates an object of PS_INSN and initializes it to the given parameters. */
static ps_insn_ptr
-create_ps_insn (ddg_node_ptr node, int rest_count, int cycle)
+create_ps_insn (ddg_node_ptr node, int cycle)
{
ps_insn_ptr ps_i = XNEW (struct ps_insn);
ps_i->node = node;
ps_i->next_in_row = NULL;
ps_i->prev_in_row = NULL;
- ps_i->row_rest_count = rest_count;
ps_i->cycle = cycle;
return ps_i;
if (ps_i->next_in_row)
ps_i->next_in_row->prev_in_row = ps_i->prev_in_row;
}
+
+ ps->rows_length[row] -= 1;
free (ps_i);
return true;
}
sbitmap must_precede, sbitmap must_follow)
{
ps_insn_ptr ps_i;
- int rest_count = 1;
int row = SMODULO (cycle, ps->ii);
- if (ps->rows[row]
- && ps->rows[row]->row_rest_count >= issue_rate)
+ if (ps->rows_length[row] >= issue_rate)
return NULL;
- if (ps->rows[row])
- rest_count += ps->rows[row]->row_rest_count;
-
- ps_i = create_ps_insn (node, rest_count, cycle);
+ ps_i = create_ps_insn (node, cycle);
/* Finds and inserts PS_I according to MUST_FOLLOW and
MUST_PRECEDE. */
return NULL;
}
+ ps->rows_length[row] += 1;
return ps_i;
}
}
/* Calculate the stage count of the partial schedule PS. The calculation
- takes into account the rotation to bring the closing branch to row
- ii-1. */
+ takes into account the rotation amount passed in ROTATION_AMOUNT. */
int
-calculate_stage_count (partial_schedule_ptr ps)
+calculate_stage_count (partial_schedule_ptr ps, int rotation_amount)
{
- int rotation_amount = (SCHED_TIME (ps->g->closing_branch)) + 1;
int new_min_cycle = PS_MIN_CYCLE (ps) - rotation_amount;
int new_max_cycle = PS_MAX_CYCLE (ps) - rotation_amount;
int stage_count = CALC_STAGE_COUNT (-1, new_min_cycle, ps->ii);
for (i = 0; i < backward_rotates; i++)
{
ps_insn_ptr first_row = ps->rows[0];
+ int first_row_length = ps->rows_length[0];
for (row = 0; row < last_row; row++)
- ps->rows[row] = ps->rows[row+1];
+ {
+ ps->rows[row] = ps->rows[row + 1];
+ ps->rows_length[row] = ps->rows_length[row + 1];
+ }
ps->rows[last_row] = first_row;
+ ps->rows_length[last_row] = first_row_length;
}
ps->max_cycle -= start_cycle;
OSDN Git Service
