Re: Fwd: [PATCH] Scheduling result adjustment to enable macro-fusion

[Wei Mi <wmi at google dot com>]

>> Just notice another problem here:
>> processor_type only contains PROCESSOR_COREI7, so I cannot
>> differentiate Westmere and Sandybridge in x86-tune.def, which are
>> different for TARGET_FUSE_ALU_AND_BRANCH. So do I have to separate
>> m_SANDYBRIDGE out from m_COREI7?
>
> Yes, please.
>
> Thanks.
>
> --
> H.J.

I separate the change into two patches here:

Patch1 is to separate PROCESSOR_COREI7_AVX from PROCESSOR_COREI7.
PROCESSOR_COREI7_AVX includes Sandybridge and Ivybridge.

Patch2 is about the change for macro-fusion. Add three tune features here:
X86_TUNE_FUSE_CMP_AND_BRANCH_64:   CORE2 only support macrofusion for
32 bits. COREI7, COREI7_AVX and Haswell support 64 bits.
X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS: CORE2 only support macrofusion
for branch only checking Zero and Carry flags. COREI7, COREI7_AVX and
Haswell support branch checking Sign and Overflow flags.
X86_TUNE_FUSE_ALU_AND_BRANCH: COREI7 doesn't support macrofusion for
alu + branch. COREI7_AVX and Haswell support it.

bootstrap and regression ok for the two patches.

Thanks,
Wei Mi.


Patch1:

2013-09-16  Wei Mi  <wmi@google.com>

        * gcc/config/i386/i386-c.c (ix86_target_macros_internal): Separate
        PROCESSOR_COREI7_AVX out from PROCESSOR_COREI7.
        * gcc/config/i386/i386.c (ix86_option_override_internal): Ditto.
        (ix86_issue_rate): Ditto.
        (ia32_multipass_dfa_lookahead): Ditto.
        (ix86_sched_init_global): Ditto.
        (get_builtin_code_for_version): Ditto.
        * gcc/config/i386/i386.h (enum target_cpu_default): Ditto.
        (enum processor_type): Ditto.
        * gcc/config/i386/x86-tune.def (DEF_TUNE): Ditto.

diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
index 14349be..7ea68cc 100644
--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@@ -141,6 +141,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__corei7");
       def_or_undef (parse_in, "__corei7__");
       break;
+    case PROCESSOR_COREI7_AVX:
+      def_or_undef (parse_in, "__corei7_avx");
+      def_or_undef (parse_in, "__corei7_avx__");
+      break;
     case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__core_avx2");
       def_or_undef (parse_in, "__core_avx2__");
@@ -239,6 +243,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_COREI7:
       def_or_undef (parse_in, "__tune_corei7__");
       break;
+    case PROCESSOR_COREI7_AVX:
+      def_or_undef (parse_in, "__tune_corei7_avx__");
+      break;
     case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__tune_core_avx2__");
       break;
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 536c357..1fd3f60 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1908,8 +1908,9 @@ const struct processor_costs *ix86_cost = &pentium_cost;
 #define m_P4_NOCONA (m_PENT4 | m_NOCONA)
 #define m_CORE2 (1<<PROCESSOR_CORE2)
 #define m_COREI7 (1<<PROCESSOR_COREI7)
+#define m_COREI7_AVX (1<<PROCESSOR_COREI7_AVX)
 #define m_HASWELL (1<<PROCESSOR_HASWELL)
-#define m_CORE_ALL (m_CORE2 | m_COREI7  | m_HASWELL)
+#define m_CORE_ALL (m_CORE2 | m_COREI7  | m_COREI7_AVX | m_HASWELL)
 #define m_ATOM (1<<PROCESSOR_ATOM)
 #define m_SLM (1<<PROCESSOR_SLM)

@@ -1984,10 +1985,10 @@ static const unsigned int x86_arch_always_fancy_math_387
   = m_PENT | m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_ATOM | m_SLM |
m_AMD_MULTIPLE | m_GENERIC;

 static const unsigned int x86_avx256_split_unaligned_load
-  = m_COREI7 | m_GENERIC;
+  = m_COREI7 | m_COREI7_AVX | m_GENERIC;

 static const unsigned int x86_avx256_split_unaligned_store
-  = m_COREI7 | m_BDVER | m_GENERIC;
+  = m_COREI7 | m_COREI7_AVX | m_BDVER | m_GENERIC;

 /* In case the average insn count for single function invocation is
    lower than this constant, emit fast (but longer) prologue and
@@ -2377,6 +2378,8 @@ static const struct ptt
processor_target_table[PROCESSOR_max] =
   {&core_cost, 16, 10, 16, 10, 16},
   /* Core i7  */
   {&core_cost, 16, 10, 16, 10, 16},
+  /* Core i7 avx  */
+  {&core_cost, 16, 10, 16, 10, 16},
   /* Core avx2  */
   {&core_cost, 16, 10, 16, 10, 16},
   {&generic32_cost, 16, 7, 16, 7, 16},
@@ -2407,6 +2410,7 @@ static const char *const
cpu_names[TARGET_CPU_DEFAULT_max] =
   "nocona",
   "core2",
   "corei7",
+  "corei7-avx",
   "core-avx2",
   "atom",
   "slm",
@@ -3091,12 +3095,12 @@ ix86_option_override_internal (bool main_args_p)
       {"corei7", PROCESSOR_COREI7, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSSE3
        | PTA_SSE4_1 | PTA_SSE4_2 | PTA_CX16 | PTA_POPCNT | PTA_FXSR},
-      {"corei7-avx", PROCESSOR_COREI7, CPU_COREI7,
+      {"corei7-avx", PROCESSOR_COREI7_AVX, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
        | PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AVX
        | PTA_CX16 | PTA_POPCNT | PTA_AES | PTA_PCLMUL
        | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT},
-      {"core-avx-i", PROCESSOR_COREI7, CPU_COREI7,
+      {"core-avx-i", PROCESSOR_COREI7_AVX, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
        | PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AVX
        | PTA_CX16 | PTA_POPCNT | PTA_AES | PTA_PCLMUL | PTA_FSGSBASE
@@ -24477,6 +24481,7 @@ ix86_issue_rate (void)
     case PROCESSOR_PENTIUM4:
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
     case PROCESSOR_ATHLON:
     case PROCESSOR_K8:
@@ -24834,6 +24839,7 @@ ia32_multipass_dfa_lookahead (void)

     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
     case PROCESSOR_ATOM:
     case PROCESSOR_SLM:
@@ -25474,6 +25480,7 @@ ix86_sched_init_global (FILE *dump ATTRIBUTE_UNUSED,
     {
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
       /* Do not perform multipass scheduling for pre-reload schedule
          to save compile time.  */
@@ -29324,6 +29331,10 @@ get_builtin_code_for_version (tree decl, tree
*predicate_list)
              arg_str = "corei7";
              priority = P_PROC_SSE4_2;
              break;
+            case PROCESSOR_COREI7_AVX:
+              arg_str = "corei7-avx";
+              priority = P_PROC_SSE4_2;
+              break;
            case PROCESSOR_ATOM:
              arg_str = "atom";
              priority = P_PROC_SSSE3;
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index e820aa6..788cb8a 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -250,6 +250,7 @@ extern const struct processor_costs ix86_size_cost;
 #define TARGET_NOCONA (ix86_tune == PROCESSOR_NOCONA)
 #define TARGET_CORE2 (ix86_tune == PROCESSOR_CORE2)
 #define TARGET_COREI7 (ix86_tune == PROCESSOR_COREI7)
+#define TARGET_COREI7_AVX (ix86_tune == PROCESSOR_COREI7_AVX)
 #define TARGET_HASWELL (ix86_tune == PROCESSOR_HASWELL)
 #define TARGET_GENERIC32 (ix86_tune == PROCESSOR_GENERIC32)
 #define TARGET_GENERIC64 (ix86_tune == PROCESSOR_GENERIC64)
@@ -559,6 +560,7 @@ enum target_cpu_default
   TARGET_CPU_DEFAULT_nocona,
   TARGET_CPU_DEFAULT_core2,
   TARGET_CPU_DEFAULT_corei7,
+  TARGET_CPU_DEFAULT_corei7_avx,
   TARGET_CPU_DEFAULT_haswell,
   TARGET_CPU_DEFAULT_atom,
   TARGET_CPU_DEFAULT_slm,
@@ -2118,6 +2120,7 @@ enum processor_type
   PROCESSOR_NOCONA,
   PROCESSOR_CORE2,
   PROCESSOR_COREI7,
+  PROCESSOR_COREI7_AVX,
   PROCESSOR_HASWELL,
   PROCESSOR_GENERIC32,
   PROCESSOR_GENERIC64,
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index e3a34ee..4ae5f70 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -118,9 +118,9 @@ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY,
"sse_partial_reg_dependency",
           m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_ATOM | m_SLM | m_AMDFAM10
           | m_BDVER | m_GENERIC)
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
-          m_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM)
+          m_COREI7 | m_COREI7_AVX | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM)
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
-          m_COREI7 | m_BDVER | m_SLM)
+          m_COREI7 | m_COREI7_AVX | m_BDVER | m_SLM)
 DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL,
"sse_packed_single_insn_optimal",
           m_BDVER)
 /* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and dependencies


Patch2:

2013-09-16  Wei Mi  <wmi@google.com>

        * gcc/config/i386/i386.c (ix86_macro_fusion_p): New Function.
        (ix86_macro_fusion_pair_p): Ditto.
        * gcc/config/i386/i386.h: Add new tune features about macro-fusion.
        * gcc/config/i386/x86-tune.def (DEF_TUNE): Ditto.
        * gcc/doc/tm.texi: Generated.
        * gcc/doc/tm.texi.in: Ditto.
        * gcc/haifa-sched.c (try_group_insn): New function.
        (group_insns_for_macro_fusion): Ditto.
        (sched_init): Call group_insns_for_macro_fusion.
        * gcc/sched-rgn.c (add_branch_dependences): Keep insns in
        a SCHED_GROUP at the end of BB to remain their location.
        * gcc/target.def: Add two hooks: macro_fusion_p and
        macro_fusion_pair_p.

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 1fd3f60..85b7aa0 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -24856,6 +24856,90 @@ ia32_multipass_dfa_lookahead (void)
     }
 }

+/* Return true if target platform supports macro-fusion.  */
+
+static bool
+ix86_macro_fusion_p ()
+{
+  if (TARGET_FUSE_CMP_AND_BRANCH
+      && (!TARGET_64BIT || TARGET_FUSE_CMP_AND_BRANCH_64))
+    return true;
+  else
+    return false;
+}
+
+/* Check whether current microarchitecture support macro fusion
+   for insn pair "CONDGEN + CONDJMP". Refer to
+   "Intel Architectures Optimization Reference Manual". */
+
+static bool
+ix86_macro_fusion_pair_p (rtx condgen, rtx condjmp)
+{
+  rtx src;
+  rtx single_set = single_set (condgen);
+  enum rtx_code ccode;
+  rtx compare_set = NULL_RTX, test_if, cond;
+
+  if (single_set == NULL_RTX
+      && !TARGET_FUSE_ALU_AND_BRANCH)
+    return false;
+
+  if (single_set != NULL_RTX)
+    compare_set = single_set;
+  else
+    {
+      int i;
+      rtx pat = PATTERN (condgen);
+      for (i = 0; i < XVECLEN (pat, 0); i++)
+       if (GET_CODE (XVECEXP (pat, 0, i)) == SET
+           && GET_CODE (SET_SRC (XVECEXP (pat, 0, i))) == COMPARE)
+         compare_set = XVECEXP (pat, 0, i);
+    }
+  if (compare_set == NULL_RTX)
+    return false;
+  src = SET_SRC (compare_set);
+  if (GET_CODE (src) != COMPARE)
+    return false;
+
+  /* Macro-fusion for cmp/test MEM-IMM + conditional jmp is not
+     supported.  */
+  if ((MEM_P (XEXP (src, 0))
+       && CONST_INT_P (XEXP (src, 1)))
+      || (MEM_P (XEXP (src, 1))
+         && CONST_INT_P (XEXP (src, 0))))
+    return false;
+
+  test_if = SET_SRC (pc_set (condjmp));
+  cond = XEXP (test_if, 0);
+  ccode = GET_CODE (cond);
+  /* Check whether conditional jump use Sign or Overflow Flags.  */
+  if (!TARGET_FUSE_CMP_AND_BRANCH_SOFLAGS
+      && (ccode == GE
+          || ccode == GT
+         || ccode == LE
+         || ccode == LT))
+    return false;
+
+  if (get_attr_type (condgen) == TYPE_TEST
+      || get_attr_type (condgen) == TYPE_ICMP)
+    return true;
+
+  /* The following is the case that macro-fusion for alu + jmp.  */
+  if (!TARGET_FUSE_ALU_AND_BRANCH)
+    return false;
+
+  /* Macro-fusion for inc/dec + unsigned conditional jump is not
+     supported.  */
+  if (get_attr_type (condgen) == TYPE_INCDEC
+      && (ccode == GEU
+         || ccode == GTU
+         || ccode == LEU
+         || ccode == LTU))
+    return false;
+
+  return true;
+}
+
 /* Try to reorder ready list to take advantage of Atom pipelined IMUL
    execution. It is applied if
    (1) IMUL instruction is on the top of list;
@@ -42993,6 +43077,10 @@ ix86_memmodel_check (unsigned HOST_WIDE_INT val)
 #undef TARGET_SCHED_FIRST_CYCLE_MULTIPASS_DFA_LOOKAHEAD
 #define TARGET_SCHED_FIRST_CYCLE_MULTIPASS_DFA_LOOKAHEAD \
   ia32_multipass_dfa_lookahead
+#undef TARGET_SCHED_MACRO_FUSION_P
+#define TARGET_SCHED_MACRO_FUSION_P ix86_macro_fusion_p
+#undef TARGET_SCHED_MACRO_FUSION_PAIR_P
+#define TARGET_SCHED_MACRO_FUSION_PAIR_P ix86_macro_fusion_pair_p

 #undef TARGET_FUNCTION_OK_FOR_SIBCALL
 #define TARGET_FUNCTION_OK_FOR_SIBCALL ix86_function_ok_for_sibcall
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 788cb8a..048cc18 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -364,6 +364,12 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
        ix86_tune_features[X86_TUNE_USE_VECTOR_CONVERTS]
 #define TARGET_FUSE_CMP_AND_BRANCH \
        ix86_tune_features[X86_TUNE_FUSE_CMP_AND_BRANCH]
+#define TARGET_FUSE_CMP_AND_BRANCH_64 \
+       ix86_tune_features[X86_TUNE_FUSE_CMP_AND_BRANCH_64]
+#define TARGET_FUSE_CMP_AND_BRANCH_SOFLAGS \
+       ix86_tune_features[X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS]
+#define TARGET_FUSE_ALU_AND_BRANCH \
+       ix86_tune_features[X86_TUNE_FUSE_ALU_AND_BRANCH]
 #define TARGET_OPT_AGU ix86_tune_features[X86_TUNE_OPT_AGU]
 #define TARGET_VECTORIZE_DOUBLE \
        ix86_tune_features[X86_TUNE_VECTORIZE_DOUBLE]
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 4ae5f70..a60d0f4 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -196,7 +196,22 @@ DEF_TUNE (X86_TUNE_USE_VECTOR_CONVERTS,
"use_vector_converts", m_AMDFAM10)
 /* X86_TUNE_FUSE_CMP_AND_BRANCH: Fuse a compare or test instruction
    with a subsequent conditional jump instruction into a single
    compare-and-branch uop.  */
-DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH, "fuse_cmp_and_branch", m_BDVER)
+DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH, "fuse_cmp_and_branch",
+          m_CORE_ALL | m_BDVER)
+/* X86_TUNE_FUSE_CMP_AND_BRANCH_64: Fuse compare with a subsequent
+   conditional jump instruction for TARGET_64BIT.  */
+DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_64, "fuse_cmp_and_branch_64",
+          m_COREI7 | m_COREI7_AVX | m_HASWELL)
+/* X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS: Fuse compare with a
+   subsequent conditional jump instruction when the condition jump
+   check sign flag (SF) or overflow flag (OF).  */
+DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS, "fuse_cmp_and_branch_soflags",
+          m_COREI7 | m_COREI7_AVX | m_HASWELL)
+/* X86_TUNE_FUSE_ALU_AND_BRANCH: Fuse alu with a subsequent conditional
+   jump instruction when the alu instruction produces the CCFLAG consumed by
+   the conditional jump instruction. */
+DEF_TUNE (X86_TUNE_FUSE_ALU_AND_BRANCH, "fuse_alu_and_branch",
+          m_COREI7_AVX | m_HASWELL)
 /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag
    will impact LEA instruction selection. */
 DEF_TUNE (X86_TUNE_OPT_AGU, "opt_agu", m_ATOM | m_SLM)
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index d15f53c..66b45b9 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -6553,6 +6553,17 @@ scheduling one insn causes other insns to
become ready in the same
 cycle.  These other insns can then be taken into account properly.
 @end deftypefn

+@deftypefn {Target Hook} bool TARGET_SCHED_MACRO_FUSION_P (void)
+This hook is used to check whether target platform supports macro fusion.
+@end deftypefn
+
+@deftypefn {Target Hook} bool TARGET_SCHED_MACRO_FUSION_PAIR_P (rtx
@var{condgen}, rtx @var{condjmp})
+This hook is used to check whether two insns could be macro fused for
+target microarchitecture. If this hook returns true for the given insn pair
+(@var{condgen} and @var{condjmp}), scheduler will put them into a sched
+group, and they will not be scheduled apart.
+@end deftypefn
+
 @deftypefn {Target Hook} void
TARGET_SCHED_DEPENDENCIES_EVALUATION_HOOK (rtx @var{head}, rtx
@var{tail})
 This hook is called after evaluation forward dependencies of insns in
 chain given by two parameter values (@var{head} and @var{tail}
diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
index b51d7b3..361ee87 100644
--- a/gcc/doc/tm.texi.in
+++ b/gcc/doc/tm.texi.in
@@ -4940,6 +4940,10 @@ them: try the first ones in this list first.

 @hook TARGET_SCHED_REORDER2

+@hook TARGET_SCHED_MACRO_FUSION_P
+
+@hook TARGET_SCHED_MACRO_FUSION_PAIR_P
+
 @hook TARGET_SCHED_DEPENDENCIES_EVALUATION_HOOK

 @hook TARGET_SCHED_INIT
diff --git a/gcc/haifa-sched.c b/gcc/haifa-sched.c
index 61eaaef..d6726a9 100644
--- a/gcc/haifa-sched.c
+++ b/gcc/haifa-sched.c
@@ -6519,6 +6519,44 @@ setup_sched_dump (void)
                ? stderr : dump_file);
 }

+static void
+try_group_insn (rtx insn)
+{
+  unsigned int condreg1, condreg2;
+  rtx cc_reg_1;
+  rtx prev;
+
+  targetm.fixed_condition_code_regs (&condreg1, &condreg2);
+  cc_reg_1 = gen_rtx_REG (CCmode, condreg1);
+  prev = prev_nonnote_nondebug_insn (insn);
+  if (!any_condjump_p (insn)
+      || !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.  */
@@ -6645,6 +6683,11 @@ 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-rgn.c b/gcc/sched-rgn.c
index e1a2dce..156359e 100644
--- a/gcc/sched-rgn.c
+++ b/gcc/sched-rgn.c
@@ -2443,6 +2443,8 @@ add_branch_dependences (rtx head, rtx tail)
      cc0 setters remain at the end because they can't be moved away from
      their cc0 user.

+     Predecessors of SCHED_GROUP_P instructions at the end remain at the end.
+
      COND_EXEC insns cannot be moved past a branch (see e.g. PR17808).

      Insns setting TARGET_CLASS_LIKELY_SPILLED_P registers (usually return
@@ -2465,7 +2467,8 @@ add_branch_dependences (rtx head, rtx tail)
 #endif
                 || (!reload_completed
                     && sets_likely_spilled (PATTERN (insn)))))
-        || NOTE_P (insn))
+        || NOTE_P (insn)
+        || (last != 0 && SCHED_GROUP_P (last)))
     {
       if (!NOTE_P (insn))
        {
diff --git a/gcc/target.def b/gcc/target.def
index 6de513f..dae0378 100644
--- a/gcc/target.def
+++ b/gcc/target.def
@@ -1041,6 +1041,19 @@ scheduling one insn causes other insns to
become ready in the same\n\
 cycle.  These other insns can then be taken into account properly.",
  int, (FILE *file, int verbose, rtx *ready, int *n_readyp, int clock), NULL)

+DEFHOOK
+(macro_fusion_p,
+ "This hook is used to check whether target platform supports macro fusion.",
+ bool, (void), NULL)
+
+DEFHOOK
+(macro_fusion_pair_p,
+ "This hook is used to check whether two insns could be macro fused for\n\
+target microarchitecture. If this hook returns true for the given insn pair\n\
+(@var{condgen} and @var{condjmp}), scheduler will put them into a sched\n\
+group, and they will not be scheduled apart.",
+ bool, (rtx condgen, rtx condjmp), NULL)
+
 /* The following member value is a pointer to a function called
    after evaluation forward dependencies of insns in chain given
    by two parameter values (head and tail correspondingly).  */