[PATCH v7] RISCV: Inline subword atomic ops

[Patrick O'Neill <patrick@rivosinc.com>]

RISC-V has no support for subword atomic operations; code currently
generates libatomic library calls.

This patch changes the default behavior to inline subword atomic calls 
(using the same logic as the existing library call).
Behavior can be specified using the -minline-atomics and
-mno-inline-atomics command line flags.

gcc/libgcc/config/riscv/atomic.c has the same logic implemented in asm.
This will need to stay for backwards compatibility and the
-mno-inline-atomics flag.

2023-04-18 Patrick O'Neill <patrick@rivosinc.com>

	PR target/104338
	* riscv-protos.h: Add helper function stubs.
	* riscv.cc: Add helper functions for subword masking.
	* riscv.opt: Add command-line flag.
	* sync.md: Add masking logic and inline asm for fetch_and_op,
	fetch_and_nand, CAS, and exchange ops.
	* invoke.texi: Add blurb regarding command-line flag.
	* inline-atomics-1.c: New test.
	* inline-atomics-2.c: Likewise.
	* inline-atomics-3.c: Likewise.
	* inline-atomics-4.c: Likewise.
	* inline-atomics-5.c: Likewise.
	* inline-atomics-6.c: Likewise.
	* inline-atomics-7.c: Likewise.
	* inline-atomics-8.c: Likewise.
	* atomic.c: Add reference to duplicate logic.

Signed-off-by: Patrick O'Neill <patrick@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
Comment from Jeff Law that gives more context to this patch:
"So for others who may be interested.  The motivation here is that for a 
sub-word atomic we currently have to explicitly link in libatomic or we 
get undefined symbols.

This is particularly problematical for the distros because we're one of 
the few (only?) architectures supported by the distros that require 
linking in libatomic for these cases.  THe distros don't want to adjust 
each affected packages and be stuck carrying that change forward or 
negotiating with all the relevant upstreams.  The distros might tackle 
this problem by porting this patch into their compiler tree which has 
its own set of problems with long term maintenance.

The net is from a usability standpoint it's best if we get this problem 
addressed and backported to our gcc-13 RISC-V coordination branch.

We had held this up pending resolution of some other issues in the 
atomics space.  In retrospect that might have been a mistake."
  https://inbox.sourceware.org/gcc-patches/87y1mpb57m.fsf@igel.home/
---
v6: https://inbox.sourceware.org/gcc-patches/20230418163913.2429812-1-patrick@rivosinc.com/

Addressed Jeff Law's comments.
  https://inbox.sourceware.org/gcc-patches/87y1mpb57m.fsf@igel.home/

Changes:
- Simplified define_expand expressions/removed unneeded register
  constraints
- Improve comment describing riscv_subword_address
- Use #include "inline-atomics-1.c" in inline-atomics-2.c
- Use rtx addr_mask variable to describe the use of the -4 magic number.
- Misc. formatting/define_expand comments

No new failures on trunk.
---
The mapping implemented here matches Libatomic. That mapping changes if
"Implement ISA Manual Table A.6 Mappings" is merged. Depending on which
patch is merged first, I will update the other to make sure the
correct mapping is emitted.
  https://gcc.gnu.org/pipermail/gcc-patches/2023-April/615748.html
---
 gcc/config/riscv/riscv-protos.h               |   2 +
 gcc/config/riscv/riscv.cc                     |  49 ++
 gcc/config/riscv/riscv.opt                    |   4 +
 gcc/config/riscv/sync.md                      | 301 +++++++++
 gcc/doc/invoke.texi                           |  10 +-
 .../gcc.target/riscv/inline-atomics-1.c       |  18 +
 .../gcc.target/riscv/inline-atomics-2.c       |   9 +
 .../gcc.target/riscv/inline-atomics-3.c       | 569 ++++++++++++++++++
 .../gcc.target/riscv/inline-atomics-4.c       | 566 +++++++++++++++++
 .../gcc.target/riscv/inline-atomics-5.c       |  87 +++
 .../gcc.target/riscv/inline-atomics-6.c       |  87 +++
 .../gcc.target/riscv/inline-atomics-7.c       |  69 +++
 .../gcc.target/riscv/inline-atomics-8.c       |  69 +++
 libgcc/config/riscv/atomic.c                  |   2 +
 14 files changed, 1841 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-2.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-4.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-5.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-6.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-7.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-8.c

diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 5244e8dcbf0..02b33e02020 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -79,6 +79,8 @@ extern void riscv_reinit (void);
 extern poly_uint64 riscv_regmode_natural_size (machine_mode);
 extern bool riscv_v_ext_vector_mode_p (machine_mode);
 extern bool riscv_shamt_matches_mask_p (int, HOST_WIDE_INT);
+extern void riscv_subword_address (rtx, rtx *, rtx *, rtx *, rtx *);
+extern void riscv_lshift_subword (machine_mode, rtx, rtx, rtx *);
 
 /* Routines implemented in riscv-c.cc.  */
 void riscv_cpu_cpp_builtins (cpp_reader *);
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index cdb47e81e7c..61f019380ae 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -7148,6 +7148,55 @@ riscv_zero_call_used_regs (HARD_REG_SET need_zeroed_hardregs)
 							& ~zeroed_hardregs);
 }
 
+/* Given memory reference MEM, expand code to compute the aligned
+   memory address, shift and mask values and store them into
+   *ALIGNED_MEM, *SHIFT, *MASK and *NOT_MASK.  */
+
+void
+riscv_subword_address (rtx mem, rtx *aligned_mem, rtx *shift, rtx *mask,
+		       rtx *not_mask)
+{
+  /* Align the memory address to a word.  */
+  rtx addr = force_reg (Pmode, XEXP (mem, 0));
+
+  rtx addr_mask = gen_int_mode (-4, Pmode);
+
+  rtx aligned_addr = gen_reg_rtx (Pmode);
+  emit_move_insn (aligned_addr,  gen_rtx_AND (Pmode, addr, addr_mask));
+
+  *aligned_mem = change_address (mem, SImode, aligned_addr);
+
+  /* Calculate the shift amount.  */
+  emit_move_insn (*shift, gen_rtx_AND (SImode, gen_lowpart (SImode, addr),
+				       gen_int_mode (3, SImode)));
+  emit_move_insn (*shift, gen_rtx_ASHIFT (SImode, *shift,
+					  gen_int_mode (3, SImode)));
+
+  /* Calculate the mask.  */
+  int unshifted_mask = GET_MODE_MASK (GET_MODE (mem));
+
+  emit_move_insn (*mask, gen_int_mode (unshifted_mask, SImode));
+
+  emit_move_insn (*mask, gen_rtx_ASHIFT (SImode, *mask,
+					 gen_lowpart (QImode, *shift)));
+
+  emit_move_insn (*not_mask, gen_rtx_NOT(SImode, *mask));
+}
+
+/* Leftshift a subword within an SImode register.  */
+
+void
+riscv_lshift_subword (machine_mode mode, rtx value, rtx shift,
+		      rtx *shifted_value)
+{
+  rtx value_reg = gen_reg_rtx (SImode);
+  emit_move_insn (value_reg, simplify_gen_subreg (SImode, value,
+						  mode, 0));
+
+  emit_move_insn(*shifted_value, gen_rtx_ASHIFT (SImode, value_reg,
+						 gen_lowpart (QImode, shift)));
+}
+
 /* Initialize the GCC target structure.  */
 #undef TARGET_ASM_ALIGNED_HI_OP
 #define TARGET_ASM_ALIGNED_HI_OP "\t.half\t"
diff --git a/gcc/config/riscv/riscv.opt b/gcc/config/riscv/riscv.opt
index ff1dd4ddd4f..bc5e63ab3e6 100644
--- a/gcc/config/riscv/riscv.opt
+++ b/gcc/config/riscv/riscv.opt
@@ -254,3 +254,7 @@ Enum(isa_spec_class) String(20191213) Value(ISA_SPEC_CLASS_20191213)
 misa-spec=
 Target RejectNegative Joined Enum(isa_spec_class) Var(riscv_isa_spec) Init(TARGET_DEFAULT_ISA_SPEC)
 Set the version of RISC-V ISA spec.
+
+minline-atomics
+Target Var(TARGET_INLINE_SUBWORD_ATOMIC) Init(1)
+Always inline subword atomic operations.
diff --git a/gcc/config/riscv/sync.md b/gcc/config/riscv/sync.md
index c932ef87b9d..83be6431cb6 100644
--- a/gcc/config/riscv/sync.md
+++ b/gcc/config/riscv/sync.md
@@ -21,8 +21,11 @@
 
 (define_c_enum "unspec" [
   UNSPEC_COMPARE_AND_SWAP
+  UNSPEC_COMPARE_AND_SWAP_SUBWORD
   UNSPEC_SYNC_OLD_OP
+  UNSPEC_SYNC_OLD_OP_SUBWORD
   UNSPEC_SYNC_EXCHANGE
+  UNSPEC_SYNC_EXCHANGE_SUBWORD
   UNSPEC_ATOMIC_STORE
   UNSPEC_MEMORY_BARRIER
 ])
@@ -91,6 +94,135 @@
   [(set_attr "type" "atomic")
    (set (attr "length") (const_int 8))])
 
+(define_insn "subword_atomic_fetch_strong_<atomic_optab>"
+  [(set (match_operand:SI 0 "register_operand" "=&r")		   ;; old value at mem
+	(match_operand:SI 1 "memory_operand" "+A"))		   ;; mem location
+   (set (match_dup 1)
+	(unspec_volatile:SI
+	  [(any_atomic:SI (match_dup 1)
+		     (match_operand:SI 2 "register_operand" "rI")) ;; value for op
+	   (match_operand:SI 3 "register_operand" "rI")]	   ;; mask
+	 UNSPEC_SYNC_OLD_OP_SUBWORD))
+    (match_operand:SI 4 "register_operand" "rI")		   ;; not_mask
+    (clobber (match_scratch:SI 5 "=&r"))			   ;; tmp_1
+    (clobber (match_scratch:SI 6 "=&r"))]			   ;; tmp_2
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+  {
+    return "1:\;"
+	   "lr.w.aq\t%0, %1\;"
+	   "<insn>\t%5, %0, %2\;"
+	   "and\t%5, %5, %3\;"
+	   "and\t%6, %0, %4\;"
+	   "or\t%6, %6, %5\;"
+	   "sc.w.rl\t%5, %6, %1\;"
+	   "bnez\t%5, 1b";
+  }
+  [(set (attr "length") (const_int 28))])
+
+(define_expand "atomic_fetch_nand<mode>"
+  [(match_operand:SHORT 0 "register_operand")			      ;; old value at mem
+   (not:SHORT (and:SHORT (match_operand:SHORT 1 "memory_operand")     ;; mem location
+			 (match_operand:SHORT 2 "reg_or_0_operand"))) ;; value for op
+   (match_operand:SI 3 "const_int_operand")]			      ;; model
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+{
+  /* We have no QImode/HImode atomics, so form a mask, then use
+     subword_atomic_fetch_strong_nand to implement a LR/SC version of the
+     operation. */
+
+  /* Logic duplicated in gcc/libgcc/config/riscv/atomic.c for use when inlining
+     is disabled */
+
+  rtx old = gen_reg_rtx (SImode);
+  rtx mem = operands[1];
+  rtx value = operands[2];
+  rtx aligned_mem = gen_reg_rtx (SImode);
+  rtx shift = gen_reg_rtx (SImode);
+  rtx mask = gen_reg_rtx (SImode);
+  rtx not_mask = gen_reg_rtx (SImode);
+
+  riscv_subword_address (mem, &aligned_mem, &shift, &mask, &not_mask);
+
+  rtx shifted_value = gen_reg_rtx (SImode);
+  riscv_lshift_subword (<MODE>mode, value, shift, &shifted_value);
+
+  emit_insn (gen_subword_atomic_fetch_strong_nand (old, aligned_mem,
+						   shifted_value,
+						   mask, not_mask));
+
+  emit_move_insn (old, gen_rtx_ASHIFTRT (SImode, old,
+					 gen_lowpart (QImode, shift)));
+
+  emit_move_insn (operands[0], gen_lowpart (<MODE>mode, old));
+
+  DONE;
+})
+
+(define_insn "subword_atomic_fetch_strong_nand"
+  [(set (match_operand:SI 0 "register_operand" "=&r")			  ;; old value at mem
+	(match_operand:SI 1 "memory_operand" "+A"))			  ;; mem location
+   (set (match_dup 1)
+	(unspec_volatile:SI
+	  [(not:SI (and:SI (match_dup 1)
+			   (match_operand:SI 2 "register_operand" "rI"))) ;; value for op
+	   (match_operand:SI 3 "register_operand" "rI")]		  ;; mask
+	 UNSPEC_SYNC_OLD_OP_SUBWORD))
+    (match_operand:SI 4 "register_operand" "rI")			  ;; not_mask
+    (clobber (match_scratch:SI 5 "=&r"))				  ;; tmp_1
+    (clobber (match_scratch:SI 6 "=&r"))]				  ;; tmp_2
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+  {
+    return "1:\;"
+	   "lr.w.aq\t%0, %1\;"
+	   "and\t%5, %0, %2\;"
+	   "not\t%5, %5\;"
+	   "and\t%5, %5, %3\;"
+	   "and\t%6, %0, %4\;"
+	   "or\t%6, %6, %5\;"
+	   "sc.w.rl\t%5, %6, %1\;"
+	   "bnez\t%5, 1b";
+  }
+  [(set (attr "length") (const_int 32))])
+
+(define_expand "atomic_fetch_<atomic_optab><mode>"
+  [(match_operand:SHORT 0 "register_operand")			 ;; old value at mem
+   (any_atomic:SHORT (match_operand:SHORT 1 "memory_operand")	 ;; mem location
+		     (match_operand:SHORT 2 "reg_or_0_operand")) ;; value for op
+   (match_operand:SI 3 "const_int_operand")]			 ;; model
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+{
+  /* We have no QImode/HImode atomics, so form a mask, then use
+     subword_atomic_fetch_strong_<mode> to implement a LR/SC version of the
+     operation. */
+
+  /* Logic duplicated in gcc/libgcc/config/riscv/atomic.c for use when inlining
+     is disabled */
+
+  rtx old = gen_reg_rtx (SImode);
+  rtx mem = operands[1];
+  rtx value = operands[2];
+  rtx aligned_mem = gen_reg_rtx (SImode);
+  rtx shift = gen_reg_rtx (SImode);
+  rtx mask = gen_reg_rtx (SImode);
+  rtx not_mask = gen_reg_rtx (SImode);
+
+  riscv_subword_address (mem, &aligned_mem, &shift, &mask, &not_mask);
+
+  rtx shifted_value = gen_reg_rtx (SImode);
+  riscv_lshift_subword (<MODE>mode, value, shift, &shifted_value);
+
+  emit_insn (gen_subword_atomic_fetch_strong_<atomic_optab> (old, aligned_mem,
+							     shifted_value,
+							     mask, not_mask));
+
+  emit_move_insn (old, gen_rtx_ASHIFTRT (SImode, old,
+					 gen_lowpart (QImode, shift)));
+
+  emit_move_insn (operands[0], gen_lowpart (<MODE>mode, old));
+
+  DONE;
+})
+
 (define_insn "atomic_exchange<mode>"
   [(set (match_operand:GPR 0 "register_operand" "=&r")
 	(unspec_volatile:GPR
@@ -104,6 +236,56 @@
   [(set_attr "type" "atomic")
    (set (attr "length") (const_int 8))])
 
+(define_expand "atomic_exchange<mode>"
+  [(match_operand:SHORT 0 "register_operand") ;; old value at mem
+   (match_operand:SHORT 1 "memory_operand")   ;; mem location
+   (match_operand:SHORT 2 "register_operand") ;; value
+   (match_operand:SI 3 "const_int_operand")]  ;; model
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+{
+  rtx old = gen_reg_rtx (SImode);
+  rtx mem = operands[1];
+  rtx value = operands[2];
+  rtx aligned_mem = gen_reg_rtx (SImode);
+  rtx shift = gen_reg_rtx (SImode);
+  rtx mask = gen_reg_rtx (SImode);
+  rtx not_mask = gen_reg_rtx (SImode);
+
+  riscv_subword_address (mem, &aligned_mem, &shift, &mask, &not_mask);
+
+  rtx shifted_value = gen_reg_rtx (SImode);
+  riscv_lshift_subword (<MODE>mode, value, shift, &shifted_value);
+
+  emit_insn (gen_subword_atomic_exchange_strong (old, aligned_mem,
+						 shifted_value, not_mask));
+
+  emit_move_insn (old, gen_rtx_ASHIFTRT (SImode, old,
+					 gen_lowpart (QImode, shift)));
+
+  emit_move_insn (operands[0], gen_lowpart (<MODE>mode, old));
+  DONE;
+})
+
+(define_insn "subword_atomic_exchange_strong"
+  [(set (match_operand:SI 0 "register_operand" "=&r")	 ;; old value at mem
+	(match_operand:SI 1 "memory_operand" "+A"))	 ;; mem location
+   (set (match_dup 1)
+	(unspec_volatile:SI
+	  [(match_operand:SI 2 "reg_or_0_operand" "rI")  ;; value
+	   (match_operand:SI 3 "reg_or_0_operand" "rI")] ;; not_mask
+      UNSPEC_SYNC_EXCHANGE_SUBWORD))
+    (clobber (match_scratch:SI 4 "=&r"))]		 ;; tmp_1
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+  {
+    return "1:\;"
+	   "lr.w.aq\t%0, %1\;"
+	   "and\t%4, %0, %3\;"
+	   "or\t%4, %4, %2\;"
+	   "sc.w.rl\t%4, %4, %1\;"
+	   "bnez\t%4, 1b";
+  }
+  [(set (attr "length") (const_int 20))])
+
 (define_insn "atomic_cas_value_strong<mode>"
   [(set (match_operand:GPR 0 "register_operand" "=&r")
 	(match_operand:GPR 1 "memory_operand" "+A"))
@@ -153,6 +335,125 @@
   DONE;
 })
 
+(define_expand "atomic_compare_and_swap<mode>"
+  [(match_operand:SI 0 "register_operand")    ;; bool output
+   (match_operand:SHORT 1 "register_operand") ;; val output
+   (match_operand:SHORT 2 "memory_operand")   ;; memory
+   (match_operand:SHORT 3 "reg_or_0_operand") ;; expected value
+   (match_operand:SHORT 4 "reg_or_0_operand") ;; desired value
+   (match_operand:SI 5 "const_int_operand")   ;; is_weak
+   (match_operand:SI 6 "const_int_operand")   ;; mod_s
+   (match_operand:SI 7 "const_int_operand")]  ;; mod_f
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+{
+  emit_insn (gen_atomic_cas_value_strong<mode> (operands[1], operands[2],
+						operands[3], operands[4],
+						operands[6], operands[7]));
+
+  rtx val = gen_reg_rtx (SImode);
+  if (operands[1] != const0_rtx)
+    emit_move_insn (val, gen_rtx_SIGN_EXTEND (SImode, operands[1]));
+  else
+    emit_move_insn (val, const0_rtx);
+
+  rtx exp = gen_reg_rtx (SImode);
+  if (operands[3] != const0_rtx)
+    emit_move_insn (exp, gen_rtx_SIGN_EXTEND (SImode, operands[3]));
+  else
+    emit_move_insn (exp, const0_rtx);
+
+  rtx compare = val;
+  if (exp != const0_rtx)
+    {
+      rtx difference = gen_rtx_MINUS (SImode, val, exp);
+      compare = gen_reg_rtx (SImode);
+      emit_move_insn  (compare, difference);
+    }
+
+  if (word_mode != SImode)
+    {
+      rtx reg = gen_reg_rtx (word_mode);
+      emit_move_insn (reg, gen_rtx_SIGN_EXTEND (word_mode, compare));
+      compare = reg;
+    }
+
+  emit_move_insn (operands[0], gen_rtx_EQ (SImode, compare, const0_rtx));
+  DONE;
+})
+
+(define_expand "atomic_cas_value_strong<mode>"
+  [(match_operand:SHORT 0 "register_operand") ;; val output
+   (match_operand:SHORT 1 "memory_operand")   ;; memory
+   (match_operand:SHORT 2 "reg_or_0_operand") ;; expected value
+   (match_operand:SHORT 3 "reg_or_0_operand") ;; desired value
+   (match_operand:SI 4 "const_int_operand")   ;; mod_s
+   (match_operand:SI 5 "const_int_operand")   ;; mod_f
+   (match_scratch:SHORT 6)]
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+{
+  /* We have no QImode/HImode atomics, so form a mask, then use
+     subword_atomic_cas_strong<mode> to implement a LR/SC version of the
+     operation. */
+
+  /* Logic duplicated in gcc/libgcc/config/riscv/atomic.c for use when inlining
+     is disabled */
+
+  rtx old = gen_reg_rtx (SImode);
+  rtx mem = operands[1];
+  rtx aligned_mem = gen_reg_rtx (SImode);
+  rtx shift = gen_reg_rtx (SImode);
+  rtx mask = gen_reg_rtx (SImode);
+  rtx not_mask = gen_reg_rtx (SImode);
+
+  riscv_subword_address (mem, &aligned_mem, &shift, &mask, &not_mask);
+
+  rtx o = operands[2];
+  rtx n = operands[3];
+  rtx shifted_o = gen_reg_rtx (SImode);
+  rtx shifted_n = gen_reg_rtx (SImode);
+
+  riscv_lshift_subword (<MODE>mode, o, shift, &shifted_o);
+  riscv_lshift_subword (<MODE>mode, n, shift, &shifted_n);
+
+  emit_move_insn (shifted_o, gen_rtx_AND (SImode, shifted_o, mask));
+  emit_move_insn (shifted_n, gen_rtx_AND (SImode, shifted_n, mask));
+
+  emit_insn (gen_subword_atomic_cas_strong (old, aligned_mem,
+					    shifted_o, shifted_n,
+					    mask, not_mask));
+
+  emit_move_insn (old, gen_rtx_ASHIFTRT (SImode, old,
+					 gen_lowpart (QImode, shift)));
+
+  emit_move_insn (operands[0], gen_lowpart (<MODE>mode, old));
+
+  DONE;
+})
+
+(define_insn "subword_atomic_cas_strong"
+  [(set (match_operand:SI 0 "register_operand" "=&r")			   ;; old value at mem
+	(match_operand:SI 1 "memory_operand" "+A"))			   ;; mem location
+   (set (match_dup 1)
+	(unspec_volatile:SI [(match_operand:SI 2 "reg_or_0_operand" "rJ")  ;; expected value
+			     (match_operand:SI 3 "reg_or_0_operand" "rJ")] ;; desired value
+	 UNSPEC_COMPARE_AND_SWAP_SUBWORD))
+	(match_operand:SI 4 "register_operand" "rI")			   ;; mask
+	(match_operand:SI 5 "register_operand" "rI")			   ;; not_mask
+	(clobber (match_scratch:SI 6 "=&r"))]				   ;; tmp_1
+  "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC"
+  {
+    return "1:\;"
+	   "lr.w.aq\t%0, %1\;"
+	   "and\t%6, %0, %4\;"
+	   "bne\t%6, %z2, 1f\;"
+	   "and\t%6, %0, %5\;"
+	   "or\t%6, %6, %3\;"
+	   "sc.w.rl\t%6, %6, %1\;"
+	   "bnez\t%6, 1b\;"
+	   "1:";
+  }
+  [(set (attr "length") (const_int 28))])
+
 (define_expand "atomic_test_and_set"
   [(match_operand:QI 0 "register_operand" "")     ;; bool output
    (match_operand:QI 1 "memory_operand" "+A")    ;; memory
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index a38547f53e5..ba448dcb7ef 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1226,7 +1226,8 @@ See RS/6000 and PowerPC Options.
 -mbig-endian  -mlittle-endian
 -mstack-protector-guard=@var{guard}  -mstack-protector-guard-reg=@var{reg}
 -mstack-protector-guard-offset=@var{offset}
--mcsr-check -mno-csr-check}
+-mcsr-check -mno-csr-check
+-minline-atomics  -mno-inline-atomics}
 
 @emph{RL78 Options}
 @gccoptlist{-msim  -mmul=none  -mmul=g13  -mmul=g14  -mallregs
@@ -29006,6 +29007,13 @@ Do or don't use smaller but slower prologue and epilogue code that uses
 library function calls.  The default is to use fast inline prologues and
 epilogues.
 
+@opindex minline-atomics
+@item -minline-atomics
+@itemx -mno-inline-atomics
+Do or don't use smaller but slower subword atomic emulation code that uses
+libatomic function calls.  The default is to use fast inline subword atomics
+that do not require libatomic.
+
 @opindex mshorten-memrefs
 @item -mshorten-memrefs
 @itemx -mno-shorten-memrefs
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c
new file mode 100644
index 00000000000..5c5623d9b2f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-mno-inline-atomics" } */
+/* { dg-message "note: '__sync_fetch_and_nand' changed semantics in GCC 4.4" "fetch_and_nand" { target *-*-* } 0 } */
+/* { dg-final { scan-assembler "\tcall\t__sync_fetch_and_add_1" } } */
+/* { dg-final { scan-assembler "\tcall\t__sync_fetch_and_nand_1" } } */
+/* { dg-final { scan-assembler "\tcall\t__sync_bool_compare_and_swap_1" } } */
+
+char foo;
+char bar;
+char baz;
+
+int
+main ()
+{
+  __sync_fetch_and_add(&foo, 1);
+  __sync_fetch_and_nand(&bar, 1);
+  __sync_bool_compare_and_swap (&baz, 1, 2);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c
new file mode 100644
index 00000000000..01b43908692
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* Verify that subword atomics do not generate calls.  */
+/* { dg-options "-minline-atomics" } */
+/* { dg-message "note: '__sync_fetch_and_nand' changed semantics in GCC 4.4" "fetch_and_nand" { target *-*-* } 0 } */
+/* { dg-final { scan-assembler-not "\tcall\t__sync_fetch_and_add_1" } } */
+/* { dg-final { scan-assembler-not "\tcall\t__sync_fetch_and_nand_1" } } */
+/* { dg-final { scan-assembler-not "\tcall\t__sync_bool_compare_and_swap_1" } } */
+
+#include "inline-atomics-1.c"
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c
new file mode 100644
index 00000000000..709f3734377
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c
@@ -0,0 +1,569 @@
+/* Check all char alignments.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-op-1.c */
+/* Test __atomic routines for existence and proper execution on 1 byte
+   values with each valid memory model.  */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics -Wno-address-of-packed-member" } */
+
+/* Test the execution of the __atomic_*OP builtin routines for a char.  */
+
+extern void abort(void);
+
+char count, res;
+const char init = ~0;
+
+struct A
+{
+   char a;
+   char b;
+   char c;
+   char d;
+} __attribute__ ((packed)) A;
+
+/* The fetch_op routines return the original value before the operation.  */
+
+void
+test_fetch_add (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_RELAXED) != 0)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_CONSUME) != 1)
+    abort ();
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_ACQUIRE) != 2)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_RELEASE) != 3)
+    abort ();
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_ACQ_REL) != 4)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_SEQ_CST) != 5)
+    abort ();
+}
+
+
+void
+test_fetch_sub (char* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_RELAXED) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_CONSUME) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQUIRE) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_RELEASE) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQ_REL) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_SEQ_CST) !=  res--)
+    abort ();
+}
+
+void
+test_fetch_and (char* v)
+{
+  *v = init;
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, init, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_fetch_and (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_fetch_nand (char* v)
+{
+  *v = init;
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_ACQUIRE) !=  0 )
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL) !=  0)
+    abort ();
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+void
+test_fetch_xor (char* v)
+{
+  *v = init;
+  count = 0;
+
+  if (__atomic_fetch_xor (v, count, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE) !=  0)
+    abort ();
+
+  if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+void
+test_fetch_or (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_fetch_or (v, count, __ATOMIC_RELAXED) !=  0)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, 2, __ATOMIC_CONSUME) !=  1)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_ACQUIRE) !=  3)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, 8, __ATOMIC_RELEASE) !=  7)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_ACQ_REL) !=  15)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_SEQ_CST) !=  31)
+    abort ();
+}
+
+/* The OP_fetch routines return the new value after the operation.  */
+
+void
+test_add_fetch (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_RELAXED) != 1)
+    abort ();
+
+  if (__atomic_add_fetch (v, 1, __ATOMIC_CONSUME) != 2)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_ACQUIRE) != 3)
+    abort ();
+
+  if (__atomic_add_fetch (v, 1, __ATOMIC_RELEASE) != 4)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_ACQ_REL) != 5)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_SEQ_CST) != 6)
+    abort ();
+}
+
+
+void
+test_sub_fetch (char* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, 1, __ATOMIC_CONSUME) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQUIRE) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, 1, __ATOMIC_RELEASE) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_SEQ_CST) !=  --res)
+    abort ();
+}
+
+void
+test_and_fetch (char* v)
+{
+  *v = init;
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_RELAXED) !=  0)
+    abort ();
+
+  *v = init;
+  if (__atomic_and_fetch (v, init, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_and_fetch (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_and_fetch (v, 0, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_nand_fetch (char* v)
+{
+  *v = init;
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_RELEASE) !=  0)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+
+
+void
+test_xor_fetch (char* v)
+{
+  *v = init;
+  count = 0;
+
+  if (__atomic_xor_fetch (v, count, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_or_fetch (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_or_fetch (v, count, __ATOMIC_RELAXED) !=  1)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, 2, __ATOMIC_CONSUME) !=  3)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_ACQUIRE) !=  7)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, 8, __ATOMIC_RELEASE) !=  15)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_ACQ_REL) !=  31)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_SEQ_CST) !=  63)
+    abort ();
+}
+
+
+/* Test the OP routines with a result which isn't used. Use both variations
+   within each function.  */
+
+void
+test_add (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  __atomic_add_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != 1)
+    abort ();
+
+  __atomic_fetch_add (v, count, __ATOMIC_CONSUME);
+  if (*v != 2)
+    abort ();
+
+  __atomic_add_fetch (v, 1 , __ATOMIC_ACQUIRE);
+  if (*v != 3)
+    abort ();
+
+  __atomic_fetch_add (v, 1, __ATOMIC_RELEASE);
+  if (*v != 4)
+    abort ();
+
+  __atomic_add_fetch (v, count, __ATOMIC_ACQ_REL);
+  if (*v != 5)
+    abort ();
+
+  __atomic_fetch_add (v, count, __ATOMIC_SEQ_CST);
+  if (*v != 6)
+    abort ();
+}
+
+
+void
+test_sub (char* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  __atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, count + 1, __ATOMIC_CONSUME);
+  if (*v != --res)
+    abort ();
+
+  __atomic_sub_fetch (v, 1, __ATOMIC_ACQUIRE);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, 1, __ATOMIC_RELEASE);
+  if (*v != --res)
+    abort ();
+
+  __atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, count + 1, __ATOMIC_SEQ_CST);
+  if (*v != --res)
+    abort ();
+}
+
+void
+test_and (char* v)
+{
+  *v = init;
+
+  __atomic_and_fetch (v, 0, __ATOMIC_RELAXED);
+  if (*v != 0)
+    abort ();
+
+  *v = init;
+  __atomic_fetch_and (v, init, __ATOMIC_CONSUME);
+  if (*v != init)
+    abort ();
+
+  __atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != 0)
+    abort ();
+
+  *v = ~*v;
+  __atomic_fetch_and (v, init, __ATOMIC_RELEASE);
+  if (*v != init)
+    abort ();
+
+  __atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL);
+  if (*v != 0)
+    abort ();
+
+  *v = ~*v;
+  __atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST);
+  if (*v != 0)
+    abort ();
+}
+
+void
+test_nand (char* v)
+{
+  *v = init;
+
+  __atomic_fetch_nand (v, 0, __ATOMIC_RELAXED);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_nand (v, init, __ATOMIC_CONSUME);
+  if (*v != 0)
+    abort ();
+
+  __atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != init)
+    abort ();
+
+  __atomic_nand_fetch (v, init, __ATOMIC_RELEASE);
+  if (*v != 0)
+    abort ();
+
+  __atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL);
+  if (*v != init)
+    abort ();
+
+  __atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST);
+  if (*v != init)
+    abort ();
+}
+
+
+
+void
+test_xor (char* v)
+{
+  *v = init;
+  count = 0;
+
+  __atomic_xor_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME);
+  if (*v != 0)
+    abort ();
+
+  __atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != 0)
+    abort ();
+
+  __atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL);
+  if (*v != init)
+    abort ();
+
+  __atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST);
+  if (*v != 0)
+    abort ();
+}
+
+void
+test_or (char* v)
+{
+  *v = 0;
+  count = 1;
+
+  __atomic_or_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != 1)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, count, __ATOMIC_CONSUME);
+  if (*v != 3)
+    abort ();
+
+  count *= 2;
+  __atomic_or_fetch (v, 4, __ATOMIC_ACQUIRE);
+  if (*v != 7)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, 8, __ATOMIC_RELEASE);
+  if (*v != 15)
+    abort ();
+
+  count *= 2;
+  __atomic_or_fetch (v, count, __ATOMIC_ACQ_REL);
+  if (*v != 31)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, count, __ATOMIC_SEQ_CST);
+  if (*v != 63)
+    abort ();
+}
+
+int
+main ()
+{
+  char* V[] = {&A.a, &A.b, &A.c, &A.d};
+
+  for (int i = 0; i < 4; i++) {
+    test_fetch_add (V[i]);
+    test_fetch_sub (V[i]);
+    test_fetch_and (V[i]);
+    test_fetch_nand (V[i]);
+    test_fetch_xor (V[i]);
+    test_fetch_or (V[i]);
+
+    test_add_fetch (V[i]);
+    test_sub_fetch (V[i]);
+    test_and_fetch (V[i]);
+    test_nand_fetch (V[i]);
+    test_xor_fetch (V[i]);
+    test_or_fetch (V[i]);
+
+    test_add (V[i]);
+    test_sub (V[i]);
+    test_and (V[i]);
+    test_nand (V[i]);
+    test_xor (V[i]);
+    test_or (V[i]);
+  }
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c
new file mode 100644
index 00000000000..eecfaae5cc6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c
@@ -0,0 +1,566 @@
+/* Check all short alignments.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-op-2.c */
+/* Test __atomic routines for existence and proper execution on 2 byte
+   values with each valid memory model.  */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics -Wno-address-of-packed-member" } */
+
+/* Test the execution of the __atomic_*OP builtin routines for a short.  */
+
+extern void abort(void);
+
+short count, res;
+const short init = ~0;
+
+struct A
+{
+   short a;
+   short b;
+} __attribute__ ((packed)) A;
+
+/* The fetch_op routines return the original value before the operation.  */
+
+void
+test_fetch_add (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_RELAXED) != 0)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_CONSUME) != 1)
+    abort ();
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_ACQUIRE) != 2)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_RELEASE) != 3)
+    abort ();
+
+  if (__atomic_fetch_add (v, count, __ATOMIC_ACQ_REL) != 4)
+    abort ();
+
+  if (__atomic_fetch_add (v, 1, __ATOMIC_SEQ_CST) != 5)
+    abort ();
+}
+
+
+void
+test_fetch_sub (short* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_RELAXED) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_CONSUME) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQUIRE) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_RELEASE) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQ_REL) !=  res--)
+    abort ();
+
+  if (__atomic_fetch_sub (v, 1, __ATOMIC_SEQ_CST) !=  res--)
+    abort ();
+}
+
+void
+test_fetch_and (short* v)
+{
+  *v = init;
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, init, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_fetch_and (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_fetch_nand (short* v)
+{
+  *v = init;
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_ACQUIRE) !=  0 )
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL) !=  0)
+    abort ();
+
+  if (__atomic_fetch_nand (v, 0, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+void
+test_fetch_xor (short* v)
+{
+  *v = init;
+  count = 0;
+
+  if (__atomic_fetch_xor (v, count, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE) !=  0)
+    abort ();
+
+  if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_fetch_xor (v, ~count, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+void
+test_fetch_or (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_fetch_or (v, count, __ATOMIC_RELAXED) !=  0)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, 2, __ATOMIC_CONSUME) !=  1)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_ACQUIRE) !=  3)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, 8, __ATOMIC_RELEASE) !=  7)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_ACQ_REL) !=  15)
+    abort ();
+
+  count *= 2;
+  if (__atomic_fetch_or (v, count, __ATOMIC_SEQ_CST) !=  31)
+    abort ();
+}
+
+/* The OP_fetch routines return the new value after the operation.  */
+
+void
+test_add_fetch (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_RELAXED) != 1)
+    abort ();
+
+  if (__atomic_add_fetch (v, 1, __ATOMIC_CONSUME) != 2)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_ACQUIRE) != 3)
+    abort ();
+
+  if (__atomic_add_fetch (v, 1, __ATOMIC_RELEASE) != 4)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_ACQ_REL) != 5)
+    abort ();
+
+  if (__atomic_add_fetch (v, count, __ATOMIC_SEQ_CST) != 6)
+    abort ();
+}
+
+
+void
+test_sub_fetch (short* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, 1, __ATOMIC_CONSUME) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQUIRE) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, 1, __ATOMIC_RELEASE) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL) !=  --res)
+    abort ();
+
+  if (__atomic_sub_fetch (v, count + 1, __ATOMIC_SEQ_CST) !=  --res)
+    abort ();
+}
+
+void
+test_and_fetch (short* v)
+{
+  *v = init;
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_RELAXED) !=  0)
+    abort ();
+
+  *v = init;
+  if (__atomic_and_fetch (v, init, __ATOMIC_CONSUME) !=  init)
+    abort ();
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_and_fetch (v, init, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL) !=  0)
+    abort ();
+
+  *v = ~*v;
+  if (__atomic_and_fetch (v, 0, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_nand_fetch (short* v)
+{
+  *v = init;
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_RELEASE) !=  0)
+    abort ();
+
+  if (__atomic_nand_fetch (v, init, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST) !=  init)
+    abort ();
+}
+
+
+
+void
+test_xor_fetch (short* v)
+{
+  *v = init;
+  count = 0;
+
+  if (__atomic_xor_fetch (v, count, __ATOMIC_RELAXED) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_CONSUME) !=  0)
+    abort ();
+
+  if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE) !=  0)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_RELEASE) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQ_REL) !=  init)
+    abort ();
+
+  if (__atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST) !=  0)
+    abort ();
+}
+
+void
+test_or_fetch (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  if (__atomic_or_fetch (v, count, __ATOMIC_RELAXED) !=  1)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, 2, __ATOMIC_CONSUME) !=  3)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_ACQUIRE) !=  7)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, 8, __ATOMIC_RELEASE) !=  15)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_ACQ_REL) !=  31)
+    abort ();
+
+  count *= 2;
+  if (__atomic_or_fetch (v, count, __ATOMIC_SEQ_CST) !=  63)
+    abort ();
+}
+
+
+/* Test the OP routines with a result which isn't used. Use both variations
+   within each function.  */
+
+void
+test_add (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  __atomic_add_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != 1)
+    abort ();
+
+  __atomic_fetch_add (v, count, __ATOMIC_CONSUME);
+  if (*v != 2)
+    abort ();
+
+  __atomic_add_fetch (v, 1 , __ATOMIC_ACQUIRE);
+  if (*v != 3)
+    abort ();
+
+  __atomic_fetch_add (v, 1, __ATOMIC_RELEASE);
+  if (*v != 4)
+    abort ();
+
+  __atomic_add_fetch (v, count, __ATOMIC_ACQ_REL);
+  if (*v != 5)
+    abort ();
+
+  __atomic_fetch_add (v, count, __ATOMIC_SEQ_CST);
+  if (*v != 6)
+    abort ();
+}
+
+
+void
+test_sub (short* v)
+{
+  *v = res = 20;
+  count = 0;
+
+  __atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, count + 1, __ATOMIC_CONSUME);
+  if (*v != --res)
+    abort ();
+
+  __atomic_sub_fetch (v, 1, __ATOMIC_ACQUIRE);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, 1, __ATOMIC_RELEASE);
+  if (*v != --res)
+    abort ();
+
+  __atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL);
+  if (*v != --res)
+    abort ();
+
+  __atomic_fetch_sub (v, count + 1, __ATOMIC_SEQ_CST);
+  if (*v != --res)
+    abort ();
+}
+
+void
+test_and (short* v)
+{
+  *v = init;
+
+  __atomic_and_fetch (v, 0, __ATOMIC_RELAXED);
+  if (*v != 0)
+    abort ();
+
+  *v = init;
+  __atomic_fetch_and (v, init, __ATOMIC_CONSUME);
+  if (*v != init)
+    abort ();
+
+  __atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != 0)
+    abort ();
+
+  *v = ~*v;
+  __atomic_fetch_and (v, init, __ATOMIC_RELEASE);
+  if (*v != init)
+    abort ();
+
+  __atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL);
+  if (*v != 0)
+    abort ();
+
+  *v = ~*v;
+  __atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST);
+  if (*v != 0)
+    abort ();
+}
+
+void
+test_nand (short* v)
+{
+  *v = init;
+
+  __atomic_fetch_nand (v, 0, __ATOMIC_RELAXED);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_nand (v, init, __ATOMIC_CONSUME);
+  if (*v != 0)
+    abort ();
+
+  __atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != init)
+    abort ();
+
+  __atomic_nand_fetch (v, init, __ATOMIC_RELEASE);
+  if (*v != 0)
+    abort ();
+
+  __atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL);
+  if (*v != init)
+    abort ();
+
+  __atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST);
+  if (*v != init)
+    abort ();
+}
+
+
+
+void
+test_xor (short* v)
+{
+  *v = init;
+  count = 0;
+
+  __atomic_xor_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME);
+  if (*v != 0)
+    abort ();
+
+  __atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE);
+  if (*v != 0)
+    abort ();
+
+  __atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE);
+  if (*v != init)
+    abort ();
+
+  __atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL);
+  if (*v != init)
+    abort ();
+
+  __atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST);
+  if (*v != 0)
+    abort ();
+}
+
+void
+test_or (short* v)
+{
+  *v = 0;
+  count = 1;
+
+  __atomic_or_fetch (v, count, __ATOMIC_RELAXED);
+  if (*v != 1)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, count, __ATOMIC_CONSUME);
+  if (*v != 3)
+    abort ();
+
+  count *= 2;
+  __atomic_or_fetch (v, 4, __ATOMIC_ACQUIRE);
+  if (*v != 7)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, 8, __ATOMIC_RELEASE);
+  if (*v != 15)
+    abort ();
+
+  count *= 2;
+  __atomic_or_fetch (v, count, __ATOMIC_ACQ_REL);
+  if (*v != 31)
+    abort ();
+
+  count *= 2;
+  __atomic_fetch_or (v, count, __ATOMIC_SEQ_CST);
+  if (*v != 63)
+    abort ();
+}
+
+int
+main () {
+  short* V[] = {&A.a, &A.b};
+
+  for (int i = 0; i < 2; i++) {
+    test_fetch_add (V[i]);
+    test_fetch_sub (V[i]);
+    test_fetch_and (V[i]);
+    test_fetch_nand (V[i]);
+    test_fetch_xor (V[i]);
+    test_fetch_or (V[i]);
+
+    test_add_fetch (V[i]);
+    test_sub_fetch (V[i]);
+    test_and_fetch (V[i]);
+    test_nand_fetch (V[i]);
+    test_xor_fetch (V[i]);
+    test_or_fetch (V[i]);
+
+    test_add (V[i]);
+    test_sub (V[i]);
+    test_and (V[i]);
+    test_nand (V[i]);
+    test_xor (V[i]);
+    test_or (V[i]);
+  }
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c
new file mode 100644
index 00000000000..52093894a79
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c
@@ -0,0 +1,87 @@
+/* Test __atomic routines for existence and proper execution on 1 byte
+   values with each valid memory model.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-compare-exchange-1.c */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics" } */
+
+/* Test the execution of the __atomic_compare_exchange_n builtin for a char.  */
+
+extern void abort(void);
+
+char v = 0;
+char expected = 0;
+char max = ~0;
+char desired = ~0;
+char zero = 0;
+
+#define STRONG 0
+#define WEAK 1
+
+int
+main ()
+{
+
+  if (!__atomic_compare_exchange_n (&v, &expected, max, STRONG , __ATOMIC_RELAXED, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (__atomic_compare_exchange_n (&v, &expected, 0, STRONG , __ATOMIC_ACQUIRE, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != max)
+    abort ();
+
+  if (!__atomic_compare_exchange_n (&v, &expected, 0, STRONG , __ATOMIC_RELEASE, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != max)
+    abort ();
+  if (v != 0)
+    abort ();
+
+  if (__atomic_compare_exchange_n (&v, &expected, desired, WEAK, __ATOMIC_ACQ_REL, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (!__atomic_compare_exchange_n (&v, &expected, desired, STRONG , __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST))
+    abort ();
+  if (expected != 0)
+    abort ();
+  if (v != max)
+    abort ();
+
+  /* Now test the generic version.  */
+
+  v = 0;
+
+  if (!__atomic_compare_exchange (&v, &expected, &max, STRONG, __ATOMIC_RELAXED, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (__atomic_compare_exchange (&v, &expected, &zero, STRONG , __ATOMIC_ACQUIRE, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != max)
+    abort ();
+
+  if (!__atomic_compare_exchange (&v, &expected, &zero, STRONG , __ATOMIC_RELEASE, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != max)
+    abort ();
+  if (v != 0)
+    abort ();
+
+  if (__atomic_compare_exchange (&v, &expected, &desired, WEAK, __ATOMIC_ACQ_REL, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (!__atomic_compare_exchange (&v, &expected, &desired, STRONG , __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST))
+    abort ();
+  if (expected != 0)
+    abort ();
+  if (v != max)
+    abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c
new file mode 100644
index 00000000000..8fee8c44811
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c
@@ -0,0 +1,87 @@
+/* Test __atomic routines for existence and proper execution on 2 byte
+   values with each valid memory model.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-compare-exchange-2.c */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics" } */
+
+/* Test the execution of the __atomic_compare_exchange_n builtin for a short.  */
+
+extern void abort(void);
+
+short v = 0;
+short expected = 0;
+short max = ~0;
+short desired = ~0;
+short zero = 0;
+
+#define STRONG 0
+#define WEAK 1
+
+int
+main ()
+{
+
+  if (!__atomic_compare_exchange_n (&v, &expected, max, STRONG , __ATOMIC_RELAXED, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (__atomic_compare_exchange_n (&v, &expected, 0, STRONG , __ATOMIC_ACQUIRE, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != max)
+    abort ();
+
+  if (!__atomic_compare_exchange_n (&v, &expected, 0, STRONG , __ATOMIC_RELEASE, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != max)
+    abort ();
+  if (v != 0)
+    abort ();
+
+  if (__atomic_compare_exchange_n (&v, &expected, desired, WEAK, __ATOMIC_ACQ_REL, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (!__atomic_compare_exchange_n (&v, &expected, desired, STRONG , __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST))
+    abort ();
+  if (expected != 0)
+    abort ();
+  if (v != max)
+    abort ();
+
+  /* Now test the generic version.  */
+
+  v = 0;
+
+  if (!__atomic_compare_exchange (&v, &expected, &max, STRONG, __ATOMIC_RELAXED, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (__atomic_compare_exchange (&v, &expected, &zero, STRONG , __ATOMIC_ACQUIRE, __ATOMIC_RELAXED))
+    abort ();
+  if (expected != max)
+    abort ();
+
+  if (!__atomic_compare_exchange (&v, &expected, &zero, STRONG , __ATOMIC_RELEASE, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != max)
+    abort ();
+  if (v != 0)
+    abort ();
+
+  if (__atomic_compare_exchange (&v, &expected, &desired, WEAK, __ATOMIC_ACQ_REL, __ATOMIC_ACQUIRE))
+    abort ();
+  if (expected != 0)
+    abort ();
+
+  if (!__atomic_compare_exchange (&v, &expected, &desired, STRONG , __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST))
+    abort ();
+  if (expected != 0)
+    abort ();
+  if (v != max)
+    abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c
new file mode 100644
index 00000000000..24c344c0ce3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c
@@ -0,0 +1,69 @@
+/* Test __atomic routines for existence and proper execution on 1 byte
+   values with each valid memory model.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-exchange-1.c */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics" } */
+
+/* Test the execution of the __atomic_exchange_n builtin for a char.  */
+
+extern void abort(void);
+
+char v, count, ret;
+
+int
+main ()
+{
+  v = 0;
+  count = 0;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_RELAXED) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_ACQUIRE) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_RELEASE) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_ACQ_REL) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_SEQ_CST) != count)
+    abort ();
+  count++;
+
+  /* Now test the generic version.  */
+
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_RELAXED);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_ACQUIRE);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_RELEASE);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_ACQ_REL);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_SEQ_CST);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c
new file mode 100644
index 00000000000..edc212df04e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c
@@ -0,0 +1,69 @@
+/* Test __atomic routines for existence and proper execution on 2 byte
+   values with each valid memory model.  */
+/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-exchange-2.c */
+/* { dg-do run } */
+/* { dg-options "-minline-atomics" } */
+
+/* Test the execution of the __atomic_X builtin for a short.  */
+
+extern void abort(void);
+
+short v, count, ret;
+
+int
+main ()
+{
+  v = 0;
+  count = 0;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_RELAXED) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_ACQUIRE) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_RELEASE) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_ACQ_REL) != count)
+    abort ();
+  count++;
+
+  if (__atomic_exchange_n (&v, count + 1, __ATOMIC_SEQ_CST) != count)
+    abort ();
+  count++;
+
+  /* Now test the generic version.  */
+
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_RELAXED);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_ACQUIRE);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_RELEASE);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_ACQ_REL);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  __atomic_exchange (&v, &count, &ret, __ATOMIC_SEQ_CST);
+  if (ret != count - 1 || v != count)
+    abort ();
+  count++;
+
+  return 0;
+}
diff --git a/libgcc/config/riscv/atomic.c b/libgcc/config/riscv/atomic.c
index 69f53623509..573d163ea04 100644
--- a/libgcc/config/riscv/atomic.c
+++ b/libgcc/config/riscv/atomic.c
@@ -30,6 +30,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #define INVERT		"not %[tmp1], %[tmp1]\n\t"
 #define DONT_INVERT	""
 
+/* Logic duplicated in gcc/gcc/config/riscv/sync.md for use when inlining is enabled */
+
 #define GENERATE_FETCH_AND_OP(type, size, opname, insn, invert, cop)	\
   type __sync_fetch_and_ ## opname ## _ ## size (type *p, type v)	\
   {									\
-- 
2.25.1