i386: Prefer remote atomic insn for atomic_fetch{add, and, or, xor}

Add flag -mprefer-remote-atomic to control whether to generate raoint
insn for atomic operations.

gcc/ChangeLog:

	* config/i386/i386.opt:Add -mprefer-remote-atomic.
	* config/i386/sync.md (atomic_<plus_logic><mode>):
	New define_expand.
	(atomic_add<mode>): Rename to below one.
	(atomic_add<mode>_1): To this.
	(atomic_<logic><mode>): Ditto.
	(atomic_<logic><mode>_1): Ditto.
	* doc/invoke.texi: Add -mprefer-remote-atomic.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/raoint-atomic-fetch.c: New test.

4 files changed, 62 insertions, 4 deletions

diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index 415c52e..abb1e5e 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -1246,3 +1246,7 @@ Support PREFETCHI built-in functions and code generation.
 mraoint
 Target Mask(ISA2_RAOINT) Var(ix86_isa_flags2) Save
 Support RAOINT built-in functions and code generation.
+
+mprefer-remote-atomic
+Target Var(flag_prefer_remote_atomic) Init(0)
+Prefer use remote atomic insn for atomic operations.
diff --git a/gcc/config/i386/sync.md b/gcc/config/i386/sync.md
index e6543a5..2508991 100644
--- a/gcc/config/i386/sync.md
+++ b/gcc/config/i386/sync.md
@@ -791,7 +791,28 @@
 (define_code_iterator any_plus_logic [and ior xor plus])
 (define_code_attr plus_logic [(and "and") (ior "or") (xor "xor") (plus "add")])
 
-(define_insn "rao_a<plus_logic><mode>"
+(define_expand "atomic_<plus_logic><mode>"
+  [(match_operand:SWI 0 "memory_operand")
+   (any_plus_logic:SWI (match_dup 0)
+                      (match_operand:SWI 1 "nonmemory_operand"))
+   (match_operand:SI 2 "const_int_operand")]
+  ""
+{
+  if (flag_prefer_remote_atomic
+      && TARGET_RAOINT && operands[2] == const0_rtx
+      && (<MODE>mode == SImode || <MODE>mode == DImode))
+  {
+    if (CONST_INT_P (operands[1]))
+      operands[1] = force_reg (<MODE>mode, operands[1]);
+    emit_insn (maybe_gen_rao_a (<CODE>, <MODE>mode, operands[0], operands[1]));
+  }
+  else
+    emit_insn (gen_atomic_<plus_logic><mode>_1 (operands[0], operands[1],
+						operands[2]));
+  DONE;
+})
+
+(define_insn "@rao_a<plus_logic><mode>"
   [(set (match_operand:SWI48 0 "memory_operand" "+m")
        (unspec_volatile:SWI48
          [(any_plus_logic:SWI48 (match_dup 0)
@@ -801,7 +822,7 @@
   "TARGET_RAOINT"
   "a<plus_logic>\t{%1, %0|%0, %1}")
 
-(define_insn "atomic_add<mode>"
+(define_insn "atomic_add<mode>_1"
   [(set (match_operand:SWI 0 "memory_operand" "+m")
 	(unspec_volatile:SWI
 	  [(plus:SWI (match_dup 0)
@@ -855,7 +876,7 @@
   return "lock{%;} %K2sub{<imodesuffix>}\t{%1, %0|%0, %1}";
 })
 
-(define_insn "atomic_<logic><mode>"
+(define_insn "atomic_<logic><mode>_1"
   [(set (match_operand:SWI 0 "memory_operand" "+m")
 	(unspec_volatile:SWI
 	  [(any_logic:SWI (match_dup 0)
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 7417f52..fa6adfd 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1438,7 +1438,7 @@ See RS/6000 and PowerPC Options.
 -mrdseed  -msgx -mavx512vp2intersect -mserialize -mtsxldtrk@gol
 -mamx-tile  -mamx-int8  -mamx-bf16 -muintr -mhreset -mavxvnni@gol
 -mavx512fp16 -mavxifma -mavxvnniint8 -mavxneconvert -mcmpccxadd -mamx-fp16 @gol
--mprefetchi -mraoint @gol
+-mprefetchi -mraoint -mprefer-remote-atomic@gol
 -mcldemote  -mms-bitfields  -mno-align-stringops  -minline-all-stringops @gol
 -minline-stringops-dynamically  -mstringop-strategy=@var{alg} @gol
 -mkl -mwidekl @gol
@@ -33666,6 +33666,10 @@ execute pause if load value is not expected. This reduces excessive
 cachline bouncing when and works for all atomic logic fetch builtins
 that generates compare and swap loop.
 
+@item -mprefer-remote-atomic
+@opindex mprefer-remote-atomic
+Prefer use remote atomic insn for atomic operations.
+
 @item -mindirect-branch=@var{choice}
 @opindex mindirect-branch
 Convert indirect call and jump with @var{choice}.  The default is
diff --git a/gcc/testsuite/gcc.target/i386/raoint-atomic-fetch.c b/gcc/testsuite/gcc.target/i386/raoint-atomic-fetch.c
new file mode 100644
index 0000000..ac4099d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/raoint-atomic-fetch.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-options "-mraoint -O2 -mprefer-remote-atomic" } */
+/* { dg-final { scan-assembler-times "aadd" 2 { target {! ia32 } } } } */
+/* { dg-final { scan-assembler-times "aand" 2 { target {! ia32 } } } } */
+/* { dg-final { scan-assembler-times "aor" 2 { target {! ia32 } } } } */
+/* { dg-final { scan-assembler-times "axor" 2 { target {! ia32 } } } } */
+/* { dg-final { scan-assembler-times "aadd" 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "aand" 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "aor" 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "axor" 1 { target ia32 } } } */
+volatile int x;
+volatile long long y;
+int *a;
+long long *b;
+
+void extern
+rao_int_test (void)
+{
+  __atomic_add_fetch (a, x, __ATOMIC_RELAXED);
+  __atomic_and_fetch (a, x, __ATOMIC_RELAXED);
+  __atomic_or_fetch (a, x, __ATOMIC_RELAXED);
+  __atomic_xor_fetch (a, x, __ATOMIC_RELAXED);
+#ifdef __x86_64__
+  __atomic_add_fetch (b, y, __ATOMIC_RELAXED);
+  __atomic_and_fetch (b, y, __ATOMIC_RELAXED);
+  __atomic_or_fetch (b, y, __ATOMIC_RELAXED);
+  __atomic_xor_fetch (b, y, __ATOMIC_RELAXED);
+#endif
+}