This patch introduces balancing of long-running instructions that may clog the
pipeline.
gcc/ChangeLog:
2017-10-11 Robin Dapp <rd...@linux.vnet.ibm.com>
* config/s390/s390.c (NUM_SIDES): New constant.
(LONGRUNNING_THRESHOLD): New constant.
(LATENCY_FACTOR): New constant.
(s390_sched_score): Lower score for long-running instructions on same
side.
(s390_sched_variable_issue): Bookkeeping for long-running instructions.
---
gcc/config/s390/s390.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 63 insertions(+), 1 deletion(-)
diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c
index 36bc67d..2430933 100644
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -355,6 +355,18 @@ static rtx_insn *last_scheduled_insn;
#define MAX_SCHED_UNITS 3
static int last_scheduled_unit_distance[MAX_SCHED_UNITS];
+#define NUM_SIDES 2
+static int current_side = 1;
+#define LONGRUNNING_THRESHOLD 5
+
+/* Estimate of number of cycles a long-running insn occupies an
+ execution unit. */
+static unsigned fxu_longrunning[NUM_SIDES];
+static unsigned vfu_longrunning[NUM_SIDES];
+
+/* Factor to scale latencies by, determined by measurements. */
+#define LATENCY_FACTOR 4
+
/* The maximum score added for an instruction whose unit hasn't been
in use for MAX_SCHED_MIX_DISTANCE steps. Increase this value to
give instruction mix scheduling more priority over instruction
@@ -14483,7 +14495,24 @@ s390_sched_score (rtx_insn *insn)
if (m & unit_mask)
score += (last_scheduled_unit_distance[i] * MAX_SCHED_MIX_SCORE /
MAX_SCHED_MIX_DISTANCE);
+
+ unsigned latency = insn_default_latency (insn);
+
+ int other_side = 1 - current_side;
+
+ /* Try to delay long-running insns when side is busy. */
+ if (latency > LONGRUNNING_THRESHOLD)
+ {
+ if (get_attr_z13_unit_fxu (insn) && fxu_longrunning[current_side]
+ && fxu_longrunning[other_side] <= fxu_longrunning[current_side])
+ score = MAX (0, score - 10);
+
+ if (get_attr_z13_unit_vfu (insn) && vfu_longrunning[current_side]
+ && vfu_longrunning[other_side] <= vfu_longrunning[current_side])
+ score = MAX (0, score - 10);
+ }
}
+
return score;
}
@@ -14602,6 +14631,8 @@ s390_sched_variable_issue (FILE *file, int verbose,
rtx_insn *insn, int more)
{
last_scheduled_insn = insn;
+ bool starts_group = false;
+
if (s390_tune >= PROCESSOR_2827_ZEC12
&& reload_completed
&& recog_memoized (insn) >= 0)
@@ -14609,6 +14640,11 @@ s390_sched_variable_issue (FILE *file, int verbose,
rtx_insn *insn, int more)
unsigned int mask = s390_get_sched_attrmask (insn);
if ((mask & S390_SCHED_ATTR_MASK_CRACKED) != 0
+ || (mask & S390_SCHED_ATTR_MASK_EXPANDED) != 0
+ || (mask & S390_SCHED_ATTR_MASK_GROUPALONE) != 0)
+ starts_group = true;
+
+ if ((mask & S390_SCHED_ATTR_MASK_CRACKED) != 0
|| (mask & S390_SCHED_ATTR_MASK_EXPANDED) != 0)
s390_sched_state = S390_SCHED_STATE_CRACKED;
else if ((mask & S390_SCHED_ATTR_MASK_ENDGROUP) != 0
@@ -14623,8 +14659,13 @@ s390_sched_variable_issue (FILE *file, int verbose,
rtx_insn *insn, int more)
case 1:
case 2:
case S390_SCHED_STATE_NORMAL:
+ if (s390_sched_state == 0)
+ starts_group = true;
if (s390_sched_state == S390_SCHED_STATE_NORMAL)
- s390_sched_state = 1;
+ {
+ starts_group = true;
+ s390_sched_state = 1;
+ }
else
s390_sched_state++;
@@ -14650,6 +14691,27 @@ s390_sched_variable_issue (FILE *file, int verbose,
rtx_insn *insn, int more)
last_scheduled_unit_distance[i]++;
}
+ /* If this insn started a new group, the side flipped. */
+ if (starts_group)
+ current_side = current_side ? 0 : 1;
+
+ for (int i = 0; i < 2; i++)
+ {
+ if (fxu_longrunning[i] >= 1)
+ fxu_longrunning[i] -= 1;
+ if (vfu_longrunning[i] >= 1)
+ vfu_longrunning[i] -= 1;
+ }
+
+ unsigned latency = insn_default_latency (insn);
+ if (latency > LONGRUNNING_THRESHOLD)
+ {
+ if (get_attr_z13_unit_fxu (insn))
+ fxu_longrunning[current_side] = latency * LATENCY_FACTOR;
+ else
+ vfu_longrunning[current_side] = latency * LATENCY_FACTOR;
+ }
+
if (verbose > 5)
{
unsigned int sched_mask;
--
2.9.4
