[AArch64] Implement copysign[ds]f3

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 88ba72e..925c6b1 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -4412,6 +4412,52 @@ 
   [(set_attr "type" "f_minmax<s>")]
 )
 
+;; For copysign (x, y), we want to generate:
+;;
+;;   LDR d2, #(1 << 63)
+;;   BSL v2.8b, [y], [x]
+;;
+;; or another, equivalent, sequence using one of BSL/BIT/BIF.
+;; aarch64_simd_bsldf will select the best suited of these instructions
+;; to generate based on register allocation, and knows how to partially
+;; constant fold based on the values of X and Y, so expand through that.
+
+(define_expand "copysigndf3"
+  [(match_operand:DF 0 "register_operand")
+   (match_operand:DF 1 "register_operand")
+   (match_operand:DF 2 "register_operand")]
+  "TARGET_FLOAT && TARGET_SIMD"
+{
+  rtx mask = gen_reg_rtx (DImode);
+  emit_move_insn (mask, GEN_INT (HOST_WIDE_INT_1U << 63));
+  emit_insn (gen_aarch64_simd_bsldf (operands[0], mask,
+				     operands[2], operands[1]));
+  DONE;
+}
+)
+
+;; As above, but we must first get to a 64-bit value if we wish to use
+;; aarch64_simd_bslv2sf.
+
+(define_expand "copysignsf3"
+  [(match_operand:SF 0 "register_operand")
+   (match_operand:SF 1 "register_operand")
+   (match_operand:SF 2 "register_operand")]
+  "TARGET_FLOAT && TARGET_SIMD"
+{
+  rtx mask = gen_reg_rtx (DImode);
+
+  /* Juggle modes to get us in to a vector mode for BSL.  */
+  rtx op1 = lowpart_subreg (V2SFmode, operands[1], SFmode);
+  rtx op2 = lowpart_subreg (V2SFmode, operands[2], SFmode);
+  rtx tmp = gen_reg_rtx (V2SFmode);
+  emit_move_insn (mask, GEN_INT (HOST_WIDE_INT_1U << 31));
+  emit_insn (gen_aarch64_simd_bslv2sf (tmp, mask, op2, op1));
+  emit_move_insn (operands[0], lowpart_subreg (SFmode, tmp, V2SFmode));
+  DONE;
+}
+)
+
 ;; -------------------------------------------------------------------
 ;; Reload support
 ;; -------------------------------------------------------------------
diff --git a/gcc/testsuite/gcc.target/aarch64/copysign_1.c b/gcc/testsuite/gcc.target/aarch64/copysign_1.c
new file mode 100644
index 0000000..27fb9ca
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/copysign_1.c
@@ -0,0 +1,81 @@ 
+/* { dg-do run } */
+/* { dg-options "-O2 --save-temps" } */
+
+double fabs (double);
+
+double
+check (double x, double y)
+{
+  return __builtin_copysign (x, y);
+}
+
+double
+check1 (double x)
+{
+  return __builtin_copysign (x, 1.0);
+}
+
+double
+check2 (double x)
+{
+  return __builtin_copysign (1.0, x);
+}
+
+double
+check3 (double x)
+{
+  return -__builtin_copysign (x, 1.0);
+}
+
+double
+check4 (double x, double y)
+{
+  return x * __builtin_copysign (x, y);
+}
+
+double
+check5 (double x, double y)
+{
+  return __builtin_copysign (-x, -y);
+}
+
+int
+main (int argc, char** argv)
+{
+  double x = 2.0;
+  double y = -5.0;
+  double epsilon = 0.00001;
+
+  double expected = -2.0;
+
+  if (fabs (check (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 2.0;
+
+  if (fabs (check1 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 1.0;
+
+  if (fabs (check2 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = -2.0;
+
+  if (fabs (check3 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = -4.0;
+
+  if (fabs (check4 (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 2.0;
+
+  if (fabs (check5 (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+}
+
+/* { dg-final { scan-assembler-not "copysign\tw" } } */
+
diff --git a/gcc/testsuite/gcc.target/aarch64/copysign_2.c b/gcc/testsuite/gcc.target/aarch64/copysign_2.c
new file mode 100644
index 0000000..6eaa704
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/copysign_2.c
@@ -0,0 +1,81 @@ 
+/* { dg-do run } */
+/* { dg-options "-O2 --save-temps" } */
+
+float fabsf (float);
+
+float
+check (float x, float y)
+{
+  return __builtin_copysignf (x, y);
+}
+
+float
+check1 (float x)
+{
+  return __builtin_copysignf (x, 1.0);
+}
+
+float
+check2 (float x)
+{
+  return __builtin_copysignf (1.0, x);
+}
+
+float
+check3 (float x)
+{
+  return -__builtin_copysignf (x, 1.0);
+}
+
+float
+check4 (float x, float y)
+{
+  return x * __builtin_copysignf (x, y);
+}
+
+float
+check5 (float x, float y)
+{
+  return __builtin_copysignf (-x, -y);
+}
+
+int
+main (int argc, char** argv)
+{
+  float x = 2.0f;
+  float y = -5.0f;
+  float epsilon = 0.00001f;
+
+  float expected = -2.0f;
+
+  if (fabsf (check (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 2.0f;
+
+  if (fabsf (check1 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 1.0f;
+
+  if (fabsf (check2 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = -2.0f;
+
+  if (fabsf (check3 (x) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = -4.0f;
+
+  if (fabsf (check4 (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+
+  expected = 2.0f;
+
+  if (fabsf (check5 (x, y) - expected) >= epsilon)
+    __builtin_abort ();
+}
+
+/* { dg-final { scan-assembler-not "copysign\tw" } } */
+