aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--gcc/ChangeLog10
-rw-r--r--gcc/haifa-sched.c49
-rw-r--r--gcc/sched-deps.c40
-rw-r--r--gcc/testsuite/ChangeLog7
-rw-r--r--gcc/testsuite/gcc.dg/macro-fusion-1.c13
-rw-r--r--gcc/testsuite/gcc.dg/macro-fusion-2.c16
-rw-r--r--gcc/testsuite/gcc.dg/pr59020.c15
7 files changed, 101 insertions, 49 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 0f350a4..51e1fa0 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,13 @@
+2013-12-03 Wei Mi <wmi@google.com>
+
+ PR rtl-optimization/59020
+ * sched-deps.c (try_group_insn): Move it from haifa-sched.c to here.
+ (sched_analyze_insn): Call try_group_insn.
+ (sched_analyze): Cleanup SCHED_GROUP_P before start the analysis.
+ * haifa-sched.c (try_group_insn): Moved to sched-deps.c.
+ (group_insns_for_macro_fusion): Removed.
+ (sched_init): Remove calling group_insns_for_macro_fusion.
+
2013-12-03 Peter Bergner <bergner@vnet.ibm.com>
* config/rs6000/htmintrin.h (_TEXASR_INSTRUCTION_FETCH_CONFLICT): Fix
diff --git a/gcc/haifa-sched.c b/gcc/haifa-sched.c
index d96d16c..8d47eb9 100644
--- a/gcc/haifa-sched.c
+++ b/gcc/haifa-sched.c
@@ -6553,50 +6553,6 @@ setup_sched_dump (void)
? stderr : dump_file);
}
-/* Try to group comparison and the following conditional jump INSN if
- they're already adjacent. This is to prevent scheduler from scheduling
- them apart. */
-
-static void
-try_group_insn (rtx insn)
-{
- unsigned int condreg1, condreg2;
- rtx cc_reg_1;
- rtx prev;
-
- if (!any_condjump_p (insn))
- return;
-
- targetm.fixed_condition_code_regs (&condreg1, &condreg2);
- cc_reg_1 = gen_rtx_REG (CCmode, condreg1);
- prev = prev_nonnote_nondebug_insn (insn);
- if (!reg_referenced_p (cc_reg_1, PATTERN (insn))
- || !prev
- || !modified_in_p (cc_reg_1, prev))
- return;
-
- /* Different microarchitectures support macro fusions for different
- combinations of insn pairs. */
- if (!targetm.sched.macro_fusion_pair_p
- || !targetm.sched.macro_fusion_pair_p (prev, insn))
- return;
-
- SCHED_GROUP_P (insn) = 1;
-}
-
-/* If the last cond jump and the cond register defining insn are consecutive
- before scheduling, we want them to be in a schedule group. This is good
- for performance on microarchitectures supporting macro-fusion. */
-
-static void
-group_insns_for_macro_fusion ()
-{
- basic_block bb;
-
- FOR_EACH_BB (bb)
- try_group_insn (BB_END (bb));
-}
-
/* Initialize some global state for the scheduler. This function works
with the common data shared between all the schedulers. It is called
from the scheduler specific initialization routine. */
@@ -6725,11 +6681,6 @@ sched_init (void)
}
curr_state = xmalloc (dfa_state_size);
-
- /* Group compare and branch insns for macro-fusion. */
- if (targetm.sched.macro_fusion_p
- && targetm.sched.macro_fusion_p ())
- group_insns_for_macro_fusion ();
}
static void haifa_init_only_bb (basic_block, basic_block);
diff --git a/gcc/sched-deps.c b/gcc/sched-deps.c
index 287b826..f818a83 100644
--- a/gcc/sched-deps.c
+++ b/gcc/sched-deps.c
@@ -2820,6 +2820,37 @@ sched_analyze_2 (struct deps_desc *deps, rtx x, rtx insn)
sched_deps_info->finish_rhs ();
}
+/* Try to group comparison and the following conditional jump INSN if
+ they're already adjacent. This is to prevent scheduler from scheduling
+ them apart. */
+
+static void
+try_group_insn (rtx insn)
+{
+ unsigned int condreg1, condreg2;
+ rtx cc_reg_1;
+ rtx prev;
+
+ if (!any_condjump_p (insn))
+ return;
+
+ targetm.fixed_condition_code_regs (&condreg1, &condreg2);
+ cc_reg_1 = gen_rtx_REG (CCmode, condreg1);
+ prev = prev_nonnote_nondebug_insn (insn);
+ if (!reg_referenced_p (cc_reg_1, PATTERN (insn))
+ || !prev
+ || !modified_in_p (cc_reg_1, prev))
+ return;
+
+ /* Different microarchitectures support macro fusions for different
+ combinations of insn pairs. */
+ if (!targetm.sched.macro_fusion_pair_p
+ || !targetm.sched.macro_fusion_pair_p (prev, insn))
+ return;
+
+ SCHED_GROUP_P (insn) = 1;
+}
+
/* Analyze an INSN with pattern X to find all dependencies. */
static void
sched_analyze_insn (struct deps_desc *deps, rtx x, rtx insn)
@@ -2843,6 +2874,11 @@ sched_analyze_insn (struct deps_desc *deps, rtx x, rtx insn)
can_start_lhs_rhs_p = (NONJUMP_INSN_P (insn)
&& code == SET);
+ /* Group compare and branch insns for macro-fusion. */
+ if (targetm.sched.macro_fusion_p
+ && targetm.sched.macro_fusion_p ())
+ try_group_insn (insn);
+
if (may_trap_p (x))
/* Avoid moving trapping instructions across function calls that might
not always return. */
@@ -3733,6 +3769,10 @@ sched_analyze (struct deps_desc *deps, rtx head, rtx tail)
{
/* And initialize deps_lists. */
sd_init_insn (insn);
+ /* Clean up SCHED_GROUP_P which may be set by last
+ scheduler pass. */
+ if (SCHED_GROUP_P (insn))
+ SCHED_GROUP_P (insn) = 0;
}
deps_analyze_insn (deps, insn);
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index a8ea26c..c1a0f54 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,10 @@
+2013-12-03 Wei Mi <wmi@google.com>
+
+ PR rtl-optimization/59020
+ * testsuite/gcc.dg/pr59020.c: New.
+ * testsuite/gcc.dg/macro-fusion-1.c: New.
+ * testsuite/gcc.dg/macro-fusion-2.c: New.
+
2013-12-03 Yury Gribov <y.gribov@samsung.com>
PR sanitizer/59063
diff --git a/gcc/testsuite/gcc.dg/macro-fusion-1.c b/gcc/testsuite/gcc.dg/macro-fusion-1.c
new file mode 100644
index 0000000..4ac9866
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/macro-fusion-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
+/* { dg-options "-O2 -mtune=corei7 -fdump-rtl-sched2" } */
+/* { dg-final { scan-rtl-dump-not "compare.*insn.*jump_insn.*jump_insn" "sched2" } } */
+
+int a[100];
+
+double bar (double sum)
+{
+ int i;
+ for (i = 0; i < 1000000; i++)
+ sum += (0.5 + (a[i%100] - 128));
+ return sum;
+}
diff --git a/gcc/testsuite/gcc.dg/macro-fusion-2.c b/gcc/testsuite/gcc.dg/macro-fusion-2.c
new file mode 100644
index 0000000..638350d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/macro-fusion-2.c
@@ -0,0 +1,16 @@
+/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
+/* { dg-options "-O2 -mtune=corei7-avx -fdump-rtl-sched2" } */
+/* { dg-final { scan-rtl-dump-not "compare.*insn.*jump_insn.*jump_insn" "sched2" } } */
+
+int a[100];
+
+double bar (double sum)
+{
+ int i = 100000;
+ while (i != 0)
+ {
+ sum += (0.5 + (a[i%100] - 128));
+ i--;
+ }
+ return sum;
+}
diff --git a/gcc/testsuite/gcc.dg/pr59020.c b/gcc/testsuite/gcc.dg/pr59020.c
new file mode 100644
index 0000000..696c9df
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr59020.c
@@ -0,0 +1,15 @@
+/* PR rtl-optimization/59020 */
+
+/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
+/* { dg-options "-O2 -fmodulo-sched -fno-inline -march=corei7" } */
+
+int a, b, d;
+unsigned c;
+
+void f()
+{
+ unsigned q;
+ for(; a; a++)
+ if(((c %= d && 1) ? : 1) & 1)
+ for(; b; q++);
+}
generated by cgit v1.1 at 2025-03-04 07:27:49 +0000