toolchain/gcc/patches-12.x/700-RISCV-Inline-subword-atomic-ops.patch

From f797260adaf52bee0ec0e16190bbefbe1bfc3692 Mon Sep 17 00:00:00 2001
From: Patrick O'Neill <patrick@rivosinc.com>
Date: Tue, 18 Apr 2023 14:33:13 -0700
Subject: [PATCH] RISCV: Inline subword atomic ops

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>

gcc/ChangeLog:
	PR target/104338
	* config/riscv/riscv-protos.h: Add helper function stubs.
	* config/riscv/riscv.cc: Add helper functions for subword masking.
	* config/riscv/riscv.opt: Add command-line flag.
	* config/riscv/sync.md: Add masking logic and inline asm for fetch_and_op,
	fetch_and_nand, CAS, and exchange ops.
	* doc/invoke.texi: Add blurb regarding command-line flag.

libgcc/ChangeLog:
	PR target/104338
	* config/riscv/atomic.c: Add reference to duplicate logic.

gcc/testsuite/ChangeLog:
	PR target/104338
	* gcc.target/riscv/inline-atomics-1.c: New test.
	* gcc.target/riscv/inline-atomics-2.c: New test.
	* gcc.target/riscv/inline-atomics-3.c: New test.
	* gcc.target/riscv/inline-atomics-4.c: New test.
	* gcc.target/riscv/inline-atomics-5.c: New test.
	* gcc.target/riscv/inline-atomics-6.c: New test.
	* gcc.target/riscv/inline-atomics-7.c: New test.
	* gcc.target/riscv/inline-atomics-8.c: New test.

Signed-off-by: Patrick O'Neill <patrick@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 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

--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -74,6 +74,8 @@ extern bool riscv_expand_block_move (rtx
 extern bool riscv_store_data_bypass_p (rtx_insn *, rtx_insn *);
 extern rtx riscv_gen_gpr_save_insn (struct riscv_frame_info *);
 extern bool riscv_gpr_save_operation_p (rtx);
+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 *);
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -5605,6 +5605,55 @@ riscv_asan_shadow_offset (void)
   return TARGET_64BIT ? (HOST_WIDE_INT_1 << 29) : 0;
 }
 
+/* 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"
--- a/gcc/config/riscv/riscv.opt
+++ b/gcc/config/riscv/riscv.opt
@@ -209,6 +209,10 @@ int riscv_vector_elen_flags
 TargetVariable
 int riscv_zvl_flags
 
+minline-atomics
+Target Var(TARGET_INLINE_SUBWORD_ATOMIC) Init(1)
+Always inline subword atomic operations.
+
 Enum
 Name(isa_spec_class) Type(enum riscv_isa_spec_class)
 Supported ISA specs (for use with the -misa-spec= option):
--- 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
 ])
@@ -92,6 +95,135 @@
   "%F3amo<insn>.<amo>%A3 %0,%z2,%1"
   [(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 @@
   "%F3amoswap.<amo>%A3 %0,%z2,%1"
   [(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"))
@@ -152,6 +334,125 @@
   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
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -753,7 +753,8 @@ Objective-C and Objective-C++ Dialects}.
 -moverride=@var{string}  -mverbose-cost-dump @gol
 -mstack-protector-guard=@var{guard} -mstack-protector-guard-reg=@var{sysreg} @gol
 -mstack-protector-guard-offset=@var{offset} -mtrack-speculation @gol
--moutline-atomics }
+-moutline-atomics
+-minline-atomics  -mno-inline-atomics}
 
 @emph{Adapteva Epiphany Options}
 @gccoptlist{-mhalf-reg-file  -mprefer-short-insn-regs @gol
@@ -28035,6 +28036,13 @@ Do or don't use smaller but slower prolo
 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.
+
 @item -mshorten-memrefs
 @itemx -mno-shorten-memrefs
 @opindex mshorten-memrefs
--- /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);
+}
--- /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
--- /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;
+}
--- /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;
+}
--- /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;
+}
--- /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;
+}
--- /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;
+}
--- /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;
+}
--- a/libgcc/config/riscv/atomic.c
+++ b/libgcc/config/riscv/atomic.c
@@ -30,6 +30,8 @@ see the files COPYING3 and COPYING.RUNTI
 #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)	\
   {									\