Model cache auto-prefetcher in scheduler

	* config/arm/arm-protos.h (struct tune_params): New field
	sched_autopref_queue_depth.
	* config/arm/arm.c (sched-int.h): Include header.
	(arm_first_cycle_multipass_dfa_lookahead_guard,)
	(TARGET_SCHED_FIRST_CYCLE_MULTIPASS_DFA_LOOKAHEAD_GUARD): Define hook.
	(arm_slowmul_tune, arm_fastmul_tune, arm_strongarm_tune,)
	(arm_xscale_tune, arm_9e_tune, arm_v6t2_tune, arm_cortex_tune,)
	(arm_cortex_a8_tune, arm_cortex_a7_tune, arm_cortex_a15_tune,)
	(arm_cortex_a53_tune, arm_cortex_a57_tune, arm_xgene1_tune,)
	(arm_cortex_a5_tune, arm_cortex_a9_tune, arm_cortex_a12_tune,)
	(arm_v7m_tune, arm_cortex_m7_tune, arm_v6m_tune, arm_fa726te_tune):
	Specify sched_autopref_queue_depth value.  Enabled for A15 and A57.
	* config/arm/t-arm (arm.o): Update.
	* haifa-sched.c (update_insn_after_change): Update.
	(rank_for_schedule): Use auto-prefetcher model, if requested.
	(autopref_multipass_init): New static function.
	(autopref_rank_for_schedule): New rank_for_schedule heuristic.
	(autopref_multipass_dfa_lookahead_guard_started_dump_p): New static
	variable for debug dumps.
	(autopref_multipass_dfa_lookahead_guard_1): New static helper function.
	(autopref_multipass_dfa_lookahead_guard): New global function that
	implements TARGET_SCHED_FIRST_CYCLE_MULTIPASS_DFA_LOOKAHEAD_GUARD hook.
	(init_h_i_d): Update.
	* params.def (PARAM_SCHED_AUTOPREF_QUEUE_DEPTH): New tuning knob.
	* sched-int.h (enum autopref_multipass_data_status): New const enum.
	(autopref_multipass_data_): Structure for auto-prefetcher data.
	(autopref_multipass_data_def, autopref_multipass_data_t): New typedefs.
	(struct _haifa_insn_data:autopref_multipass_data): New field.
	(INSN_AUTOPREF_MULTIPASS_DATA): New access macro.
	(autopref_multipass_dfa_lookahead_guard): Declare.

From-SVN: r219789

1 files changed, 34 insertions, 0 deletions

diff --git a/gcc/sched-int.h b/gcc/sched-int.h
index 9392d04..28e95ea 100644
--- a/gcc/sched-int.h
+++ b/gcc/sched-int.h
@@ -793,6 +793,32 @@ struct reg_set_data
   struct reg_set_data *next_insn_set;
 };
 
+enum autopref_multipass_data_status {
+  /* Entry is irrelevant for auto-prefetcher.  */
+  AUTOPREF_MULTIPASS_DATA_IRRELEVANT = -2,
+  /* Entry is uninitialized.  */
+  AUTOPREF_MULTIPASS_DATA_UNINITIALIZED = -1,
+  /* Entry is relevant for auto-prefetcher and insn can be delayed
+     to allow another insn through.  */
+  AUTOPREF_MULTIPASS_DATA_NORMAL = 0,
+  /* Entry is relevant for auto-prefetcher, but insn should not be
+     delayed as that will break scheduling.  */
+  AUTOPREF_MULTIPASS_DATA_DONT_DELAY = 1
+};
+
+/* Data for modeling cache auto-prefetcher.  */
+struct autopref_multipass_data_
+{
+  /* Base part of memory address.  */
+  rtx base;
+  /* Memory offset.  */
+  int offset;
+  /* Entry status.  */
+  enum autopref_multipass_data_status status;
+};
+typedef struct autopref_multipass_data_ autopref_multipass_data_def;
+typedef autopref_multipass_data_def *autopref_multipass_data_t;
+
 struct _haifa_insn_data
 {
   /* We can't place 'struct _deps_list' into h_i_d instead of deps_list_t
@@ -893,6 +919,10 @@ struct _haifa_insn_data
 
   /* The deciding reason for INSN's place in the ready list.  */
   int last_rfs_win;
+
+  /* Two entries for cache auto-prefetcher model: one for mem reads,
+     and one for mem writes.  */
+  autopref_multipass_data_def autopref_multipass_data[2];
 };
 
 typedef struct _haifa_insn_data haifa_insn_data_def;
@@ -915,6 +945,8 @@ extern vec<haifa_insn_data_def> h_i_d;
   (HID (INSN)->reg_pressure_excess_cost_change)
 #define INSN_PRIORITY_STATUS(INSN) (HID (INSN)->priority_status)
 #define INSN_MODEL_INDEX(INSN) (HID (INSN)->model_index)
+#define INSN_AUTOPREF_MULTIPASS_DATA(INSN) \
+  (HID (INSN)->autopref_multipass_data)
 
 typedef struct _haifa_deps_insn_data haifa_deps_insn_data_def;
 typedef haifa_deps_insn_data_def *haifa_deps_insn_data_t;
@@ -1363,6 +1395,8 @@ extern int cycle_issued_insns;
 extern int issue_rate;
 extern int dfa_lookahead;
 
+extern int autopref_multipass_dfa_lookahead_guard (rtx_insn *, int);
+
 extern void ready_sort (struct ready_list *);
 extern rtx_insn *ready_element (struct ready_list *, int);
 extern rtx_insn **ready_lastpos (struct ready_list *);