[APX NF] Add a pass to convert legacy insn to NF insns

For APX ccmp, current infrastructure will always generate cstore for
the ccmp flag user, like

	cmpe    %rcx, %r8
	ccmpnel %rax, %rbx
	seta	%dil
	add	%rcx, %r9
	add     %r9, %rdx
	testb   %dil, %dil
	je	.L2

For such case, the legacy add clobbers FLAGS_REG so there should have
extra cstore to avoid the flag be reset before using it. If the
instructions between flag producer and user are NF insns, the setcc/
test sequence is not required.

Add a pass to convert legacy flag clobber insns to their NF counterpart.
The convertion only happens when
1. APX_NF enabled.
2. For a BB, cstore was find, and there are insns between such cstore
and next explicit set insn to FLAGS_REG (test or cmp).
3. All the insns found should have NF counterpart.

The pass was added after rtl-ifcvt which eliminates some branch when
profitable, which could cause some flag-clobbering insn put between
cstore and jcc.

gcc/ChangeLog:

	* config/i386/i386.md (has_nf): New define_attr, add to all
	nf related patterns.
	* config/i386/i386-features.cc (apx_nf_convert): New function
	to convert Non-NF insns to their NF counterparts.
	(class pass_apx_nf_convert): New pass class.
	(make_pass_apx_nf_convert): New.
	* config/i386/i386-passes.def: Add pass_apx_nf_convert after
	rtl_ifcvt.
	* config/i386/i386-protos.h (make_pass_apx_nf_convert): Declare.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-nf-2.c: New test.

5 files changed, 259 insertions, 5 deletions

diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index fc224ed..3da56dd 100644
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -3259,6 +3259,169 @@ make_pass_remove_partial_avx_dependency (gcc::context *ctxt)
   return new pass_remove_partial_avx_dependency (ctxt);
 }
 
+/* Convert legacy instructions that clobbers EFLAGS to APX_NF
+   instructions when there are no flag set between a flag
+   producer and user.  */
+
+static unsigned int
+ix86_apx_nf_convert (void)
+{
+  timevar_push (TV_MACH_DEP);
+
+  basic_block bb;
+  rtx_insn *insn;
+  hash_map <rtx_insn *, rtx> converting_map;
+  auto_vec <rtx_insn *> current_convert_list;
+
+  bool converting_seq = false;
+  rtx cc = gen_rtx_REG (CCmode, FLAGS_REG);
+
+  FOR_EACH_BB_FN (bb, cfun)
+    {
+      /* Reset conversion for each bb.  */
+      converting_seq = false;
+      FOR_BB_INSNS (bb, insn)
+	{
+	  if (!NONDEBUG_INSN_P (insn))
+	    continue;
+
+	  if (recog_memoized (insn) < 0)
+	    continue;
+
+	  /* Convert candidate insns after cstore, which should
+	     satisify the two conditions:
+	     1. Is not flag user or producer, only clobbers
+	     FLAGS_REG.
+	     2. Have corresponding nf pattern.  */
+
+	  rtx pat = PATTERN (insn);
+
+	  /* Starting convertion at first cstorecc.  */
+	  rtx set = NULL_RTX;
+	  if (!converting_seq
+	      && (set = single_set (insn))
+	      && ix86_comparison_operator (SET_SRC (set), VOIDmode)
+	      && reg_overlap_mentioned_p (cc, SET_SRC (set))
+	      && !reg_overlap_mentioned_p (cc, SET_DEST (set)))
+	    {
+	      converting_seq = true;
+	      current_convert_list.truncate (0);
+	    }
+	  /* Terminate at the next explicit flag set.  */
+	  else if (reg_set_p (cc, pat)
+		   && GET_CODE (set_of (cc, pat)) != CLOBBER)
+	    converting_seq = false;
+
+	  if (!converting_seq)
+	    continue;
+
+	  if (get_attr_has_nf (insn)
+	      && GET_CODE (pat) == PARALLEL)
+	    {
+	      /* Record the insn to candidate map.  */
+	      current_convert_list.safe_push (insn);
+	      converting_map.put (insn, pat);
+	    }
+	  /* If the insn clobbers flags but has no nf_attr,
+	     revoke all previous candidates.  */
+	  else if (!get_attr_has_nf (insn)
+		   && reg_set_p (cc, pat)
+		   && GET_CODE (set_of (cc, pat)) == CLOBBER)
+	    {
+	      for (auto item : current_convert_list)
+		converting_map.remove (item);
+	      converting_seq = false;
+	    }
+	}
+    }
+
+  if (!converting_map.is_empty ())
+    {
+      for (auto iter = converting_map.begin ();
+	   iter != converting_map.end (); ++iter)
+	{
+	  rtx_insn *replace = (*iter).first;
+	  rtx pat = (*iter).second;
+	  int i, n = 0, len = XVECLEN (pat, 0);
+	  rtx *new_elems = XALLOCAVEC (rtx, len);
+	  rtx new_pat;
+	  for (i = 0; i < len; i++)
+	    {
+	      rtx temp = XVECEXP (pat, 0, i);
+	      if (! (GET_CODE (temp) == CLOBBER
+		     && reg_overlap_mentioned_p (cc,
+						 XEXP (temp, 0))))
+		{
+		  new_elems[n] = temp;
+		  n++;
+		}
+	    }
+
+	  if (n == 1)
+	    new_pat = new_elems[0];
+	  else
+	    new_pat =
+	      gen_rtx_PARALLEL (VOIDmode,
+				gen_rtvec_v (n,
+					     new_elems));
+
+	  PATTERN (replace) = new_pat;
+	  INSN_CODE (replace) = -1;
+	  recog_memoized (replace);
+	  df_insn_rescan (replace);
+	}
+    }
+
+  timevar_pop (TV_MACH_DEP);
+  return 0;
+}
+
+
+namespace {
+
+const pass_data pass_data_apx_nf_convert =
+{
+  RTL_PASS, /* type */
+  "apx_nfcvt", /* name */
+  OPTGROUP_NONE, /* optinfo_flags */
+  TV_MACH_DEP, /* tv_id */
+  0, /* properties_required */
+  0, /* properties_provided */
+  0, /* properties_destroyed */
+  0, /* todo_flags_start */
+  0, /* todo_flags_finish */
+};
+
+class pass_apx_nf_convert : public rtl_opt_pass
+{
+public:
+  pass_apx_nf_convert (gcc::context *ctxt)
+    : rtl_opt_pass (pass_data_apx_nf_convert, ctxt)
+  {}
+
+  /* opt_pass methods: */
+  bool gate (function *) final override
+    {
+      return (TARGET_APX_NF
+	      && optimize
+	      && optimize_function_for_speed_p (cfun));
+    }
+
+  unsigned int execute (function *) final override
+    {
+      return ix86_apx_nf_convert ();
+    }
+}; // class pass_rpad
+
+} // anon namespace
+
+rtl_opt_pass *
+make_pass_apx_nf_convert (gcc::context *ctxt)
+{
+  return new pass_apx_nf_convert (ctxt);
+}
+
+
 /* This compares the priority of target features in function DECL1
    and DECL2.  It returns positive value if DECL1 is higher priority,
    negative value if DECL2 is higher priority and 0 if they are the
diff --git a/gcc/config/i386/i386-passes.def b/gcc/config/i386/i386-passes.def
index 2d29f65..99fc880 100644
--- a/gcc/config/i386/i386-passes.def
+++ b/gcc/config/i386/i386-passes.def
@@ -33,3 +33,4 @@ along with GCC; see the file COPYING3.  If not see
   INSERT_PASS_BEFORE (pass_shorten_branches, 1, pass_insert_endbr_and_patchable_area);
 
   INSERT_PASS_AFTER (pass_late_combine, 1, pass_remove_partial_avx_dependency);
+  INSERT_PASS_AFTER (pass_rtl_ifcvt, 1, pass_apx_nf_convert);
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 68f5739..a3629b3 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -423,6 +423,7 @@ extern rtl_opt_pass *make_pass_insert_endbr_and_patchable_area
   (gcc::context *);
 extern rtl_opt_pass *make_pass_remove_partial_avx_dependency
   (gcc::context *);
+extern rtl_opt_pass *make_pass_apx_nf_convert (gcc::context *);
 
 extern bool ix86_has_no_direct_extern_access;
 extern bool ix86_rpad_gate ();
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index de9f4ba..90d3aa4 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -992,6 +992,9 @@
 (define_attr "preferred_for_size" "" (const_int 1))
 (define_attr "preferred_for_speed" "" (const_int 1))
 
+;; Define attribute to mark the insn has nf variant.
+(define_attr "has_nf" "0,1" (const_string "0"))
+
 ;; Describe a user's asm statement.
 (define_asm_attributes
   [(set_attr "length" "128")
@@ -6565,6 +6568,7 @@
 	(and (eq_attr "type" "alu") (match_operand 2 "const128_operand"))
 	(const_string "1")
 	(const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; It may seem that nonimmediate operand is proper one for operand 1.
@@ -6682,6 +6686,7 @@
 	(and (eq_attr "type" "alu") (match_operand 2 "const128_operand"))
 	(const_string "1")
 	(const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "HI,HI,HI,SI,HI,HI")])
 
 (define_insn "*addqi_1<nf_name>"
@@ -6750,6 +6755,7 @@
 	(and (eq_attr "type" "alu") (match_operand 2 "const128_operand"))
 	(const_string "1")
 	(const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "QI,QI,QI,SI,SI,SI,QI,QI")
    ;; Potential partial reg stall on alternatives 3 and 4.
    (set (attr "preferred_for_speed")
@@ -7963,6 +7969,7 @@
   <nf_prefix>sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd,apx_ndd")
    (set_attr "type" "alu")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*subsi_1_zext"
@@ -10186,6 +10193,7 @@
 	  (match_test "<MODE>mode == HImode")
 	    (const_string "double")
 	    (const_string "direct")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*imulhi<mode>zu<nf_name>"
@@ -10253,6 +10261,7 @@
         (const_string "direct")))
    (set_attr "amdfam10_decode" "direct")
    (set_attr "bdver1_decode" "direct")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "QI")])
 
 ;; Multiply with jump on overflow.
@@ -11417,6 +11426,7 @@
   ""
   "<sgnprefix>div{<imodesuffix>}\t%3"
   [(set_attr "type" "idiv")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*<u>divmodsi4_noext_zext_1"
@@ -11569,6 +11579,7 @@
    && <nf_condition>"
   "<nf_prefix><sgnprefix>div{b}\t%2"
   [(set_attr "type" "idiv")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "QI")])
 
 ;; We cannot use div/idiv for double division, because it causes
@@ -12114,6 +12125,7 @@
 		 (match_operand 1 "ext_QIreg_operand")))
        (const_string "1")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI,SI,DI,DI,DI,DI,DI,DI,SI,DI")])
 
 (define_insn_and_split "*anddi_1_btr"
@@ -12220,6 +12232,7 @@
 		 (match_operand 1 "ext_QIreg_operand")))
        (const_string "1")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>,<MODE>,<MODE>,<MODE>,<MODE>,<MODE>,SI,<MODE>")])
 
 (define_insn "*andqi_1<nf_name>"
@@ -12237,6 +12250,7 @@
    #"
   [(set_attr "type" "alu,alu,alu,alu,alu,msklog")
    (set_attr "isa" "*,*,*,apx_ndd,apx_ndd,*")
+   (set_attr "has_nf" "1")
    (set (attr "mode")
 	(cond [(eq_attr "alternative" "2")
 		 (const_string "SI")
@@ -13113,6 +13127,7 @@
    #"
   [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd,apx_ndd,<kmov_isa>")
    (set_attr "type" "alu,alu, alu, alu, alu, alu, msklog")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn_and_split "*notxor<mode>_1"
@@ -13273,6 +13288,7 @@
    #"
   [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd,avx512f")
    (set_attr "type" "alu,alu,alu,alu,alu,msklog")
+   (set_attr "has_nf" "1")
    (set (attr "mode")
 	(cond [(eq_attr "alternative" "2")
 		 (const_string "SI")
@@ -13839,6 +13855,7 @@
   <nf_prefix>neg{<imodesuffix>}\t{%1, %0|%0, %1}"
   [(set_attr "type" "negnot")
    (set_attr "isa" "*,apx_ndd")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*negsi_1_zext"
@@ -14852,6 +14869,7 @@
   "<nf_prefix>shld{q}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")
    (set_attr "athlon_decode" "vector")
    (set_attr "amdfam10_decode" "vector")
@@ -14871,6 +14889,7 @@
   "TARGET_APX_NDD && <nf_condition>"
   "<nf_prefix>shld{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")])
 
 (define_insn "x86_64_shld_1<nf_name>"
@@ -14888,6 +14907,7 @@
   "<nf_prefix>shld{q}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")
    (set_attr "length_immediate" "1")
    (set_attr "athlon_decode" "vector")
@@ -14908,6 +14928,7 @@
    && <nf_condition>"
   "<nf_prefix>shld{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")
    (set_attr "length_immediate" "1")])
 
@@ -15017,7 +15038,8 @@
      emit_move_insn (operands[0], tmp);
    }
    DONE;
-})
+}
+  [(set_attr "has_nf" "1")])
 
 (define_insn_and_split "*x86_64_shld_2"
   [(set (match_operand:DI 0 "nonimmediate_operand")
@@ -15082,6 +15104,7 @@
   "<nf_prefix>shld{l}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")
    (set_attr "pent_pair" "np")
    (set_attr "athlon_decode" "vector")
@@ -15102,6 +15125,7 @@
   "TARGET_APX_NDD && <nf_condition>"
   "<nf_prefix>shld{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")])
 
 
@@ -15120,6 +15144,7 @@
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")
    (set_attr "pent_pair" "np")
    (set_attr "athlon_decode" "vector")
@@ -15141,6 +15166,7 @@
   "<nf_prefix>shld{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")])
 
 (define_insn_and_split "*x86_shld_shrd_1_nozext_nf"
@@ -15248,7 +15274,8 @@
      emit_move_insn (operands[0], tmp);
    }
    DONE;
-})
+}
+  [(set_attr "has_nf" "1")])
 
 (define_insn_and_split "*x86_shld_2"
   [(set (match_operand:SI 0 "nonimmediate_operand")
@@ -15464,6 +15491,7 @@
 			   (match_test "optimize_function_for_size_p (cfun)")))))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; Convert shift to the shiftx pattern to avoid flags dependency.
@@ -15620,6 +15648,7 @@
 			   (match_test "optimize_function_for_size_p (cfun)")))))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "HI,SI,HI,HI")])
 
 (define_insn "*ashlqi3_1<nf_name>"
@@ -15691,6 +15720,7 @@
 			   (match_test "optimize_function_for_size_p (cfun)")))))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "QI,SI,SI,QI,QI")
    ;; Potential partial reg stall on alternative 1.
    (set (attr "preferred_for_speed")
@@ -16292,7 +16322,8 @@
   operands[4] = GEN_INT ((<MODE_SIZE> * BITS_PER_UNIT) - INTVAL (operands[2]));
   if (!rtx_equal_p (operands[0], operands[1]))
     emit_move_insn (operands[0], operands[1]);
-})
+}
+  [(set_attr "has_nf" "1")])
 
 (define_insn "x86_64_shrd<nf_name>"
   [(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
@@ -16309,6 +16340,7 @@
   "<nf_prefix>shrd{q}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")
    (set_attr "athlon_decode" "vector")
    (set_attr "amdfam10_decode" "vector")
@@ -16328,6 +16360,7 @@
   "TARGET_APX_NDD && <nf_condition>"
   "<nf_prefix>shrd{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")])
 
 (define_insn "x86_64_shrd_1<nf_name>"
@@ -16346,6 +16379,7 @@
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")
    (set_attr "athlon_decode" "vector")
    (set_attr "amdfam10_decode" "vector")
@@ -16366,6 +16400,7 @@
   "<nf_prefix>shrd{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "DI")])
 
 (define_insn_and_split "*x86_64_shrd_shld_1_nozext_nf"
@@ -16474,7 +16509,8 @@
      emit_move_insn (operands[0], tmp);
    }
    DONE;
-})
+}
+  [(set_attr "has_nf" "1")])
 
 (define_insn_and_split "*x86_64_shrd_2"
   [(set (match_operand:DI 0 "nonimmediate_operand")
@@ -16539,6 +16575,7 @@
   "<nf_prefix>shrd{l}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")
    (set_attr "pent_pair" "np")
    (set_attr "athlon_decode" "vector")
@@ -16559,6 +16596,7 @@
   "TARGET_APX_NDD && <nf_condition>"
   "<nf_prefix>shrd{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")])
 
 (define_insn "x86_shrd_1<nf_name>"
@@ -16576,6 +16614,7 @@
   [(set_attr "type" "ishift")
    (set_attr "prefix_0f" "1")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")
    (set_attr "pent_pair" "np")
    (set_attr "athlon_decode" "vector")
@@ -16597,6 +16636,7 @@
   "<nf_prefix>shrd{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
   [(set_attr "type" "ishift")
    (set_attr "length_immediate" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "SI")])
 
 (define_insn_and_split "*x86_shrd_shld_1_nozext_nf"
@@ -16704,7 +16744,8 @@
      emit_move_insn (operands[0], tmp);
    }
    DONE;
-})
+}
+  [(set_attr "has_nf" "1")])
 
 (define_insn_and_split "*x86_shrd_2"
   [(set (match_operand:SI 0 "nonimmediate_operand")
@@ -16776,6 +16817,7 @@
    (set_attr "prefix_0f" "0,*,*")
    (set_attr "length_immediate" "0,*,*")
    (set_attr "modrm" "0,1,1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*ashrsi3_cvt_zext"
@@ -16869,6 +16911,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; Specialization of *lshr<mode>3_1 below, extracting the SImode
@@ -16932,6 +16975,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; Convert shift to the shiftx pattern to avoid flags dependency.
@@ -17047,6 +17091,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*lshrqi3_1<nf_name>"
@@ -17084,6 +17129,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "QI")])
 
 (define_insn "*lshrhi3_1<nf_name>"
@@ -17121,6 +17167,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "HI")])
 
 ;; Alternative 1 is needed to work around LRA limitation, see PR82524.
@@ -17670,6 +17717,7 @@
 		      (match_test "optimize_function_for_size_p (cfun)"))))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; Convert rotate to the rotatex pattern to avoid flags dependency.
@@ -17814,6 +17862,7 @@
 		 (match_test "optimize_function_for_size_p (cfun)")))
        (const_string "0")
        (const_string "*")))
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ;; Alternative 1 is needed to work around LRA limitation, see PR82524.
@@ -20605,6 +20654,7 @@
   "ix86_expand_clear (operands[0]);"
   [(set_attr "prefix_rep" "1")
    (set_attr "type" "bitmanip")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ; False dependency happens when destination is only updated by tzcnt,
@@ -20633,6 +20683,7 @@
   "lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
   [(set_attr "prefix_rep" "1")
    (set_attr "type" "bitmanip")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn_and_split "*clzsi2_lzcnt_zext"
@@ -20766,6 +20817,7 @@
   [(set_attr "type" "<lt_zcnt_type>")
    (set_attr "prefix_0f" "1")
    (set_attr "prefix_rep" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ; False dependency happens when destination is only updated by tzcnt,
@@ -20796,6 +20848,7 @@
   [(set_attr "type" "<lt_zcnt_type>")
    (set_attr "prefix_0f" "1")
    (set_attr "prefix_rep" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "<lt_zcnt>_hi<nf_name>"
@@ -20807,6 +20860,7 @@
   [(set_attr "type" "<lt_zcnt_type>")
    (set_attr "prefix_0f" "1")
    (set_attr "prefix_rep" "1")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "HI")])
 
 ;; BMI instructions.
@@ -21269,6 +21323,7 @@
   "ix86_expand_clear (operands[0]);"
   [(set_attr "prefix_rep" "1")
    (set_attr "type" "bitmanip")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 ; False dependency happens when destination is only updated by tzcnt,
@@ -21309,6 +21364,7 @@
 }
   [(set_attr "prefix_rep" "1")
    (set_attr "type" "bitmanip")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "<MODE>")])
 
 (define_insn_and_split "*popcountsi2_zext"
@@ -21463,6 +21519,7 @@
 }
   [(set_attr "prefix_rep" "1")
    (set_attr "type" "bitmanip")
+   (set_attr "has_nf" "1")
    (set_attr "mode" "HI")])
 
 (define_expand "bswapdi2"
diff --git a/gcc/testsuite/gcc.target/i386/apx-nf-2.c b/gcc/testsuite/gcc.target/i386/apx-nf-2.c
new file mode 100644
index 0000000..8f5b8f6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/apx-nf-2.c
@@ -0,0 +1,32 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O3 -mapxf" } */
+
+int foo(int a, int b, int c, int d)
+{
+  int sum = a;
+
+  if (a != c)
+    {
+      c += d;
+      a += b;
+      sum += a + c;
+      if (b != d && sum < c || sum > d)
+	{
+	  b -= d;
+	  sum -= b;
+	}
+    }
+
+  return sum;
+}
+
+int foo2 (unsigned a, unsigned b, unsigned d, unsigned e, int *p)
+{
+  unsigned r;
+  int c = __builtin_mul_overflow (a, b, &r);
+  *p += a;
+  return c ? d : e;
+}
+
+/* { dg-final { scan-assembler-not "set" } } */
+