===================================================================
@@ -1882,7 +1882,7 @@ rs6000_hard_regno_nregs_internal (int re
128-bit floating point that can go in vector registers, which has VSX
memory addressing. */
if (FP_REGNO_P (regno))
- reg_size = (VECTOR_MEM_VSX_P (mode)
+ reg_size = (VECTOR_MEM_VSX_P (mode) || FLOAT128_VECTOR_P (mode)
? UNITS_PER_VSX_WORD
: UNITS_PER_FP_WORD);
@@ -1914,6 +1914,9 @@ rs6000_hard_regno_mode_ok (int regno, ma
{
int last_regno = regno + rs6000_hard_regno_nregs[mode][regno] - 1;
+ if (COMPLEX_MODE_P (mode))
+ mode = GET_MODE_INNER (mode);
+
/* PTImode can only go in GPRs. Quad word memory operations require even/odd
register combinations, and use PTImode where we need to deal with quad
word memory operations. Don't allow quad words in the argument or frame
@@ -2716,8 +2719,17 @@ rs6000_setup_reg_addr_masks (void)
for (m = 0; m < NUM_MACHINE_MODES; ++m)
{
- machine_mode m2 = (machine_mode)m;
- unsigned short msize = GET_MODE_SIZE (m2);
+ machine_mode m2 = (machine_mode) m;
+ bool complex_p = false;
+ size_t msize;
+
+ if (COMPLEX_MODE_P (m2))
+ {
+ complex_p = true;
+ m2 = GET_MODE_INNER (m2);
+ }
+
+ msize = GET_MODE_SIZE (m2);
/* SDmode is special in that we want to access it only via REG+REG
addressing on power7 and above, since we want to use the LFIWZX and
@@ -2739,7 +2751,7 @@ rs6000_setup_reg_addr_masks (void)
/* Indicate if the mode takes more than 1 physical register. If
it takes a single register, indicate it can do REG+REG
addressing. */
- if (nregs > 1 || m == BLKmode)
+ if (nregs > 1 || m == BLKmode || complex_p)
addr_mask |= RELOAD_REG_MULTIPLE;
else
addr_mask |= RELOAD_REG_INDEXED;
@@ -2755,7 +2767,7 @@ rs6000_setup_reg_addr_masks (void)
&& msize <= 8
&& !VECTOR_MODE_P (m2)
&& !FLOAT128_VECTOR_P (m2)
- && !COMPLEX_MODE_P (m2)
+ && !complex_p
&& (m2 != DFmode || !TARGET_UPPER_REGS_DF)
&& (m2 != SFmode || !TARGET_UPPER_REGS_SF)
&& !(TARGET_E500_DOUBLE && msize == 8))
@@ -10447,6 +10459,35 @@ rs6000_must_pass_in_stack (machine_mode
return must_pass_in_stack_var_size_or_pad (mode, type);
}
+static inline bool
+is_complex_IBM_long_double (machine_mode mode)
+{
+ return mode == ICmode || (!TARGET_IEEEQUAD && mode == TCmode);
+}
+
+/* Whether ABI_V4 passes MODE args to a function in floating point
+ registers. */
+
+static bool
+abi_v4_pass_in_fpr (machine_mode mode)
+{
+ if (!TARGET_FPRS || !TARGET_HARD_FLOAT)
+ return false;
+ if (TARGET_SINGLE_FLOAT && mode == SFmode)
+ return true;
+ if (TARGET_DOUBLE_FLOAT && mode == DFmode)
+ return true;
+ /* ABI_V4 passes complex IBM long double in 8 gprs.
+ Stupid, but we can't change the ABI now. */
+ if (is_complex_IBM_long_double (mode))
+ return false;
+ if (FLOAT128_2REG_P (mode))
+ return true;
+ if (DECIMAL_FLOAT_MODE_P (mode))
+ return true;
+ return false;
+}
+
/* If defined, a C expression which determines whether, and in which
direction, to pad out an argument with extra space. The value
should be of type `enum direction': either `upward' to pad above
@@ -10531,6 +10572,7 @@ rs6000_function_arg_boundary (machine_mo
&& (GET_MODE_SIZE (mode) == 8
|| (TARGET_HARD_FLOAT
&& TARGET_FPRS
+ && !is_complex_IBM_long_double (mode)
&& FLOAT128_2REG_P (mode))))
return 64;
else if (FLOAT128_VECTOR_P (mode))
@@ -10910,11 +10952,7 @@ rs6000_function_arg_advance_1 (CUMULATIV
}
else if (DEFAULT_ABI == ABI_V4)
{
- if (TARGET_HARD_FLOAT && TARGET_FPRS
- && ((TARGET_SINGLE_FLOAT && mode == SFmode)
- || (TARGET_DOUBLE_FLOAT && mode == DFmode)
- || FLOAT128_2REG_P (mode)
- || DECIMAL_FLOAT_MODE_P (mode)))
+ if (abi_v4_pass_in_fpr (mode))
{
/* _Decimal128 must use an even/odd register pair. This assumes
that the register number is odd when fregno is odd. */
@@ -11571,11 +11609,7 @@ rs6000_function_arg (cumulative_args_t c
else if (abi == ABI_V4)
{
- if (TARGET_HARD_FLOAT && TARGET_FPRS
- && ((TARGET_SINGLE_FLOAT && mode == SFmode)
- || (TARGET_DOUBLE_FLOAT && mode == DFmode)
- || FLOAT128_2REG_P (mode)
- || DECIMAL_FLOAT_MODE_P (mode)))
+ if (abi_v4_pass_in_fpr (mode))
{
/* _Decimal128 must use an even/odd register pair. This assumes
that the register number is odd when fregno is odd. */
@@ -12496,19 +12530,15 @@ rs6000_gimplify_va_arg (tree valist, tre
rsize = (size + 3) / 4;
align = 1;
- if (TARGET_HARD_FLOAT && TARGET_FPRS
- && ((TARGET_SINGLE_FLOAT && TYPE_MODE (type) == SFmode)
- || (TARGET_DOUBLE_FLOAT
- && (TYPE_MODE (type) == DFmode
- || FLOAT128_2REG_P (TYPE_MODE (type))
- || DECIMAL_FLOAT_MODE_P (TYPE_MODE (type))))))
+ machine_mode mode = TYPE_MODE (type);
+ if (abi_v4_pass_in_fpr (mode))
{
/* FP args go in FP registers, if present. */
reg = fpr;
n_reg = (size + 7) / 8;
sav_ofs = ((TARGET_HARD_FLOAT && TARGET_DOUBLE_FLOAT) ? 8 : 4) * 4;
sav_scale = ((TARGET_HARD_FLOAT && TARGET_DOUBLE_FLOAT) ? 8 : 4);
- if (TYPE_MODE (type) != SFmode && TYPE_MODE (type) != SDmode)
+ if (mode != SFmode && mode != SDmode)
align = 8;
}
else
@@ -12528,7 +12558,7 @@ rs6000_gimplify_va_arg (tree valist, tre
addr = create_tmp_var (ptr_type_node, "addr");
/* AltiVec vectors never go in registers when -mabi=altivec. */
- if (TARGET_ALTIVEC_ABI && ALTIVEC_VECTOR_MODE (TYPE_MODE (type)))
+ if (TARGET_ALTIVEC_ABI && ALTIVEC_VECTOR_MODE (mode))
align = 16;
else
{
@@ -12549,7 +12579,7 @@ rs6000_gimplify_va_arg (tree valist, tre
}
/* _Decimal128 is passed in even/odd fpr pairs; the stored
reg number is 0 for f1, so we want to make it odd. */
- else if (reg == fpr && TYPE_MODE (type) == TDmode)
+ else if (reg == fpr && mode == TDmode)
{
t = build2 (BIT_IOR_EXPR, TREE_TYPE (reg), unshare_expr (reg),
build_int_cst (TREE_TYPE (reg), 1));
@@ -12576,7 +12606,7 @@ rs6000_gimplify_va_arg (tree valist, tre
FP register for 32-bit binaries. */
if (TARGET_32BIT
&& TARGET_HARD_FLOAT && TARGET_FPRS
- && TYPE_MODE (type) == SDmode)
+ && mode == SDmode)
t = fold_build_pointer_plus_hwi (t, size);
gimplify_assign (addr, t, pre_p);
@@ -18645,25 +18675,33 @@ rs6000_secondary_reload_memory (rtx addr
addr_mask = (reg_addr[mode].addr_mask[RELOAD_REG_VMX]
& ~RELOAD_REG_AND_M16);
- else
+ /* If the register allocator hasn't made up its mind yet on the register
+ class to use, settle on defaults to use. */
+ else if (rclass == NO_REGS)
{
- if (TARGET_DEBUG_ADDR)
- fprintf (stderr,
- "rs6000_secondary_reload_memory: mode = %s, class = %s, "
- "class is not GPR, FPR, VMX\n",
- GET_MODE_NAME (mode), reg_class_names[rclass]);
+ addr_mask = (reg_addr[mode].addr_mask[RELOAD_REG_ANY]
+ & ~RELOAD_REG_AND_M16);
- return -1;
+ if ((addr_mask & RELOAD_REG_MULTIPLE) != 0)
+ addr_mask &= ~(RELOAD_REG_INDEXED
+ | RELOAD_REG_PRE_INCDEC
+ | RELOAD_REG_PRE_MODIFY);
}
+ else
+ addr_mask = 0;
+
/* If the register isn't valid in this register class, just return now. */
if ((addr_mask & RELOAD_REG_VALID) == 0)
{
if (TARGET_DEBUG_ADDR)
- fprintf (stderr,
- "rs6000_secondary_reload_memory: mode = %s, class = %s, "
- "not valid in class\n",
- GET_MODE_NAME (mode), reg_class_names[rclass]);
+ {
+ fprintf (stderr,
+ "rs6000_secondary_reload_memory: mode = %s, class = %s, "
+ "not valid in class\n",
+ GET_MODE_NAME (mode), reg_class_names[rclass]);
+ debug_rtx (addr);
+ }
return -1;
}
@@ -19324,6 +19362,9 @@ rs6000_secondary_reload (bool in_p,
fprintf (stderr, ", reload func = %s, extra cost = %d",
insn_data[sri->icode].name, sri->extra_cost);
+ else if (sri->extra_cost > 0)
+ fprintf (stderr, ", extra cost = %d", sri->extra_cost);
+
fputs ("\n", stderr);
debug_rtx (x);
}
@@ -19734,6 +19775,16 @@ rs6000_preferred_reload_class (rtx x, en
machine_mode mode = GET_MODE (x);
bool is_constant = CONSTANT_P (x);
+ /* If a mode can't go in FPR/ALTIVEC/VSX registers, don't return a preferred
+ reload class for it. */
+ if ((rclass == ALTIVEC_REGS || rclass == VSX_REGS)
+ && (reg_addr[mode].addr_mask[RELOAD_REG_VMX] & RELOAD_REG_VALID) == 0)
+ return NO_REGS;
+
+ if ((rclass == FLOAT_REGS || rclass == VSX_REGS)
+ && (reg_addr[mode].addr_mask[RELOAD_REG_FPR] & RELOAD_REG_VALID) == 0)
+ return NO_REGS;
+
/* For VSX, see if we should prefer FLOAT_REGS or ALTIVEC_REGS. Do not allow
the reloading of address expressions using PLUS into floating point
registers. */
@@ -19784,6 +19835,25 @@ rs6000_preferred_reload_class (rtx x, en
return NO_REGS;
}
+ /* If we haven't picked a register class, and the type is a vector or
+ floating point type, prefer to use the VSX, FPR, or Altivec register
+ classes. */
+ if (rclass == NO_REGS)
+ {
+ if (TARGET_VSX && VECTOR_MEM_VSX_OR_P8_VECTOR_P (mode))
+ return VSX_REGS;
+
+ if (TARGET_ALTIVEC && VECTOR_MEM_ALTIVEC_P (mode))
+ return ALTIVEC_REGS;
+
+ if (DECIMAL_FLOAT_MODE_P (mode))
+ return TARGET_DFP ? FLOAT_REGS : NO_REGS;
+
+ if (TARGET_FPRS && TARGET_HARD_FLOAT && FLOAT_MODE_P (mode)
+ && (reg_addr[mode].addr_mask[RELOAD_REG_FPR] & RELOAD_REG_VALID) == 0)
+ return FLOAT_REGS;
+ }
+
if (GET_MODE_CLASS (mode) == MODE_INT && rclass == NON_SPECIAL_REGS)
return GENERAL_REGS;
@@ -34728,8 +34798,14 @@ rs6000_complex_function_value (machine_m
machine_mode inner = GET_MODE_INNER (mode);
unsigned int inner_bytes = GET_MODE_UNIT_SIZE (mode);
- if (FLOAT_MODE_P (mode) && TARGET_HARD_FLOAT && TARGET_FPRS)
+ if (TARGET_FLOAT128
+ && (mode == KCmode
+ || (mode == TCmode && TARGET_IEEEQUAD)))
+ regno = ALTIVEC_ARG_RETURN;
+
+ else if (FLOAT_MODE_P (mode) && TARGET_HARD_FLOAT && TARGET_FPRS)
regno = FP_ARG_RETURN;
+
else
{
regno = GP_ARG_RETURN;
===================================================================
@@ -418,12 +418,12 @@ extern const char *host_detect_local_cpu
Similarly IFmode is the IBM long double format even if the default is IEEE
128-bit. */
#define FLOAT128_IEEE_P(MODE) \
- (((MODE) == TFmode && TARGET_IEEEQUAD) \
- || ((MODE) == KFmode))
+ ((TARGET_IEEEQUAD && ((MODE) == TFmode || (MODE) == TCmode)) \
+ || ((MODE) == KFmode) || ((MODE) == KCmode))
#define FLOAT128_IBM_P(MODE) \
- (((MODE) == TFmode && !TARGET_IEEEQUAD) \
- || ((MODE) == IFmode))
+ ((!TARGET_IEEEQUAD && ((MODE) == TFmode || (MODE) == TCmode)) \
+ || ((MODE) == IFmode) || ((MODE) == ICmode))
/* Helper macros to say whether a 128-bit floating point type can go in a
single vector register, or whether it needs paired scalar values. */
@@ -1789,7 +1789,9 @@ extern enum reg_class rs6000_constraints
#define ALTIVEC_ARG_RETURN (FIRST_ALTIVEC_REGNO + 2)
#define FP_ARG_MAX_RETURN (DEFAULT_ABI != ABI_ELFv2 ? FP_ARG_RETURN \
: (FP_ARG_RETURN + AGGR_ARG_NUM_REG - 1))
-#define ALTIVEC_ARG_MAX_RETURN (DEFAULT_ABI != ABI_ELFv2 ? ALTIVEC_ARG_RETURN \
+#define ALTIVEC_ARG_MAX_RETURN (DEFAULT_ABI != ABI_ELFv2 \
+ ? (ALTIVEC_ARG_RETURN \
+ + (TARGET_FLOAT128 ? 1 : 0)) \
: (ALTIVEC_ARG_RETURN + AGGR_ARG_NUM_REG - 1))
/* Flags for the call/call_value rtl operations set up by function_arg */
===================================================================
@@ -962,8 +962,13 @@ complex @code{__float128} type. When th
would use the following syntax to declare @code{_Complex128} to be a
complex @code{__float128} type:
+On the PowerPC Linux VSX targets, you can declare complex types using
+the corresponding internal complex type, @code{KCmode} for
+@code{__float128} type and @code{ICmode} for @code{__ibm128} type:
+
@smallexample
-typedef _Complex float __attribute__((mode(KC))) _Complex128;
+typedef _Complex float __attribute__((mode(KC))) _Complex_float128;
+typedef _Complex float __attribute__((mode(IC))) _Complex_ibm128;
@end smallexample
Not all targets support additional floating-point types.
===================================================================
@@ -66,6 +66,7 @@ struct mode_data
this mode as a component. */
struct mode_data *next_cont; /* Next mode in that list. */
+ struct mode_data *complex; /* complex type with mode as component. */
const char *file; /* file and line of definition, */
unsigned int line; /* for error reporting */
unsigned int counter; /* Rank ordering of modes */
@@ -83,7 +84,7 @@ static struct mode_data *void_mode;
static const struct mode_data blank_mode = {
0, "<unknown>", MAX_MODE_CLASS,
-1U, -1U, -1U, -1U,
- 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0,
"<unknown>", 0, 0, 0, 0, false, 0
};
@@ -472,6 +473,7 @@ make_complex_modes (enum mode_class cl,
c = new_mode (cclass, buf, file, line);
c->component = m;
+ m->complex = c;
}
}
@@ -1381,6 +1383,22 @@ emit_mode_wider (void)
}
static void
+emit_mode_complex (void)
+{
+ int c;
+ struct mode_data *m;
+
+ print_decl ("unsigned char", "mode_complex", "NUM_MACHINE_MODES");
+
+ for_all_modes (c, m)
+ tagged_printf ("%smode",
+ m->complex ? m->complex->name : void_mode->name,
+ m->name);
+
+ print_closer ();
+}
+
+static void
emit_mode_mask (void)
{
int c;
@@ -1745,6 +1763,7 @@ emit_insn_modes_c (void)
emit_mode_size ();
emit_mode_nunits ();
emit_mode_wider ();
+ emit_mode_complex ();
emit_mode_mask ();
emit_mode_inner ();
emit_mode_unit_size ();
===================================================================
@@ -269,6 +269,10 @@ extern const unsigned char mode_wider[NU
extern const unsigned char mode_2xwider[NUM_MACHINE_MODES];
#define GET_MODE_2XWIDER_MODE(MODE) ((machine_mode) mode_2xwider[MODE])
+/* Get the complex mode from the component mode. */
+extern const unsigned char mode_complex[NUM_MACHINE_MODES];
+#define GET_MODE_COMPLEX_MODE(MODE) ((machine_mode) mode_complex[MODE])
+
/* Return the mode for data of a given size SIZE and mode class CLASS.
If LIMIT is nonzero, then don't use modes bigger than MAX_FIXED_MODE_SIZE.
The value is BLKmode if no other mode is found. */
===================================================================
@@ -2147,10 +2147,8 @@ layout_type (tree type)
case COMPLEX_TYPE:
TYPE_UNSIGNED (type) = TYPE_UNSIGNED (TREE_TYPE (type));
SET_TYPE_MODE (type,
- mode_for_size (2 * TYPE_PRECISION (TREE_TYPE (type)),
- (TREE_CODE (TREE_TYPE (type)) == REAL_TYPE
- ? MODE_COMPLEX_FLOAT : MODE_COMPLEX_INT),
- 0));
+ GET_MODE_COMPLEX_MODE (TYPE_MODE (TREE_TYPE (type))));
+
TYPE_SIZE (type) = bitsize_int (GET_MODE_BITSIZE (TYPE_MODE (type)));
TYPE_SIZE_UNIT (type) = size_int (GET_MODE_SIZE (TYPE_MODE (type)));
break;
===================================================================
@@ -0,0 +1,157 @@
+/* { dg-do compile { target { powerpc*-*-linux* } } } */
+/* { dg-require-effective-target powerpc_float128_sw_ok } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power7" } } */
+/* { dg-options "-O2 -mcpu=power7 -mfloat128" } */
+
+#ifndef NO_FLOAT
+typedef _Complex float float_complex;
+extern float_complex cfloat1 (void);
+extern float_complex cfloat2 (void);
+
+#define FLOAT_ARG(NAME, OP) ARG_OP(float, float_complex, NAME, OP)
+#define FLOAT_PTR(NAME, OP) PTR_OP(float, float_complex, NAME, OP)
+#define FLOAT_CALL() CALL_OP(float, float_complex, cfloat1, cfloat2)
+
+#else
+#define FLOAT_ARG(NAME, OP)
+#define FLOAT_PTR(NAME, OP)
+#define FLOAT_CALL()
+#endif
+
+#ifndef NO_DOUBLE
+typedef _Complex double double_complex;
+extern double_complex cdouble1 (void);
+extern double_complex cdouble2 (void);
+
+#define DOUBLE_ARG(NAME, OP) ARG_OP(double, double_complex, NAME, OP)
+#define DOUBLE_PTR(NAME, OP) PTR_OP(double, double_complex, NAME, OP)
+#define DOUBLE_CALL() CALL_OP(double, double_complex, cdouble1, cdouble2)
+
+#else
+#define DOUBLE_ARG(NAME, OP)
+#define DOUBLE_PTR(NAME, OP)
+#define DOUBLE_CALL()
+#endif
+
+#ifndef NO_FLOAT128
+#ifdef __VSX__
+typedef _Complex float __attribute__((mode(KC))) float128_complex;
+#else
+typedef _Complex float __attribute__((mode(TC))) float128_complex;
+#endif
+
+extern float128_complex cfloat128_1 (void);
+extern float128_complex cfloat128_2 (void);
+
+#define FLOAT128_ARG(NAME, OP) ARG_OP(float128, float128_complex, NAME, OP)
+#define FLOAT128_PTR(NAME, OP) PTR_OP(float128, float128_complex, NAME, OP)
+#define FLOAT128_CALL() CALL_OP(float128, float128_complex, cfloat128_1, cfloat128_2)
+
+#else
+#define FLOAT128_ARG(NAME, OP)
+#define FLOAT128_PTR(NAME, OP)
+#define FLOAT128_CALL()
+#endif
+
+#ifndef NO_LDOUBLE
+typedef _Complex long double ldouble_complex;
+extern ldouble_complex cldouble1 (void);
+extern ldouble_complex cldouble2 (void);
+
+#define LDOUBLE_ARG(NAME, OP) ARG_OP(ldouble, ldouble_complex, NAME, OP)
+#define LDOUBLE_PTR(NAME, OP) PTR_OP(ldouble, ldouble_complex, NAME, OP)
+#define LDOUBLE_CALL() CALL_OP(ldouble, ldouble_complex, cldouble1, cldouble2)
+
+#else
+#define LDOUBLE_ARG(NAME, OP)
+#define LDOUBLE_PTR(NAME, OP)
+#define LDOUBLE_CALL()
+#endif
+
+
+#define ARG_OP(SUFFIX, TYPE, NAME, OP) \
+TYPE arg_ ## NAME ## _ ## SUFFIX (TYPE a, TYPE b) \
+{ \
+ return a OP b; \
+}
+
+#define PTR_OP(SUFFIX, TYPE, NAME, OP) \
+void ptr_ ## NAME ## _ ## SUFFIX (TYPE *p, TYPE *a, TYPE *b) \
+{ \
+ *p = *a OP *b; \
+}
+
+#define CALL_OP(SUFFIX, TYPE, FUNC1, FUNC2) \
+TYPE call_ ## SUFFIX (void) \
+{ \
+ TYPE value1 = FUNC1 (); \
+ TYPE value2 = FUNC2 (); \
+ return value1 + value2; \
+}
+
+#ifndef NO_ARG
+#ifndef NO_ADD
+FLOAT_ARG (add, +)
+DOUBLE_ARG (add, +)
+FLOAT128_ARG (add, +)
+LDOUBLE_ARG (add, +)
+#endif
+
+#ifndef NO_SUB
+FLOAT_ARG (sub, -)
+DOUBLE_ARG (sub, -)
+FLOAT128_ARG (sub, -)
+LDOUBLE_ARG (sub, -)
+#endif
+
+#ifndef NO_MUL
+FLOAT_ARG (mul, *)
+DOUBLE_ARG (mul, *)
+FLOAT128_ARG (mul, *)
+LDOUBLE_ARG (mul, *)
+#endif
+
+#ifndef NO_DIV
+FLOAT_ARG (div, /)
+DOUBLE_ARG (div, /)
+FLOAT128_ARG (div, /)
+LDOUBLE_ARG (div, /)
+#endif
+#endif
+
+#ifndef NO_PTR
+#ifndef NO_ADD
+FLOAT_PTR (add, +)
+DOUBLE_PTR (add, +)
+FLOAT128_PTR (add, +)
+LDOUBLE_PTR (add, +)
+#endif
+
+#ifndef NO_SUB
+FLOAT_PTR (sub, -)
+DOUBLE_PTR (sub, -)
+FLOAT128_PTR (sub, -)
+LDOUBLE_PTR (sub, -)
+#endif
+
+#ifndef NO_MUL
+FLOAT_PTR (mul, *)
+DOUBLE_PTR (mul, *)
+FLOAT128_PTR (mul, *)
+LDOUBLE_PTR (mul, *)
+#endif
+
+#ifndef NO_DIV
+FLOAT_PTR (div, /)
+DOUBLE_PTR (div, /)
+FLOAT128_PTR (div, /)
+LDOUBLE_PTR (div, /)
+#endif
+#endif
+
+#ifndef NO_CALL
+FLOAT_CALL ()
+DOUBLE_CALL ()
+FLOAT128_CALL ()
+LDOUBLE_CALL ()
+#endif
===================================================================
@@ -0,0 +1,160 @@
+/* { dg-do compile { target { powerpc*-*-linux* } } } */
+/* { dg-require-effective-target powerpc_float128_hw_ok } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-options "-O2 -mcpu=power9 -mfloat128 -mfloat128-hardware" } */
+
+#ifndef NO_FLOAT
+typedef _Complex float float_complex;
+extern float_complex cfloat1 (void);
+extern float_complex cfloat2 (void);
+
+#define FLOAT_ARG(NAME, OP) ARG_OP(float, float_complex, NAME, OP)
+#define FLOAT_PTR(NAME, OP) PTR_OP(float, float_complex, NAME, OP)
+#define FLOAT_CALL() CALL_OP(float, float_complex, cfloat1, cfloat2)
+
+#else
+#define FLOAT_ARG(NAME, OP)
+#define FLOAT_PTR(NAME, OP)
+#define FLOAT_CALL()
+#endif
+
+#ifndef NO_DOUBLE
+typedef _Complex double double_complex;
+extern double_complex cdouble1 (void);
+extern double_complex cdouble2 (void);
+
+#define DOUBLE_ARG(NAME, OP) ARG_OP(double, double_complex, NAME, OP)
+#define DOUBLE_PTR(NAME, OP) PTR_OP(double, double_complex, NAME, OP)
+#define DOUBLE_CALL() CALL_OP(double, double_complex, cdouble1, cdouble2)
+
+#else
+#define DOUBLE_ARG(NAME, OP)
+#define DOUBLE_PTR(NAME, OP)
+#define DOUBLE_CALL()
+#endif
+
+#ifndef NO_FLOAT128
+#ifdef __VSX__
+typedef _Complex float __attribute__((mode(KC))) float128_complex;
+#else
+typedef _Complex float __attribute__((mode(TC))) float128_complex;
+#endif
+
+extern float128_complex cfloat128_1 (void);
+extern float128_complex cfloat128_2 (void);
+
+#define FLOAT128_ARG(NAME, OP) ARG_OP(float128, float128_complex, NAME, OP)
+#define FLOAT128_PTR(NAME, OP) PTR_OP(float128, float128_complex, NAME, OP)
+#define FLOAT128_CALL() CALL_OP(float128, float128_complex, cfloat128_1, cfloat128_2)
+
+#else
+#define FLOAT128_ARG(NAME, OP)
+#define FLOAT128_PTR(NAME, OP)
+#define FLOAT128_CALL()
+#endif
+
+#ifndef NO_LDOUBLE
+typedef _Complex long double ldouble_complex;
+extern ldouble_complex cldouble1 (void);
+extern ldouble_complex cldouble2 (void);
+
+#define LDOUBLE_ARG(NAME, OP) ARG_OP(ldouble, ldouble_complex, NAME, OP)
+#define LDOUBLE_PTR(NAME, OP) PTR_OP(ldouble, ldouble_complex, NAME, OP)
+#define LDOUBLE_CALL() CALL_OP(ldouble, ldouble_complex, cldouble1, cldouble2)
+
+#else
+#define LDOUBLE_ARG(NAME, OP)
+#define LDOUBLE_PTR(NAME, OP)
+#define LDOUBLE_CALL()
+#endif
+
+
+#define ARG_OP(SUFFIX, TYPE, NAME, OP) \
+TYPE arg_ ## NAME ## _ ## SUFFIX (TYPE a, TYPE b) \
+{ \
+ return a OP b; \
+}
+
+#define PTR_OP(SUFFIX, TYPE, NAME, OP) \
+void ptr_ ## NAME ## _ ## SUFFIX (TYPE *p, TYPE *a, TYPE *b) \
+{ \
+ *p = *a OP *b; \
+}
+
+#define CALL_OP(SUFFIX, TYPE, FUNC1, FUNC2) \
+TYPE call_ ## SUFFIX (void) \
+{ \
+ TYPE value1 = FUNC1 (); \
+ TYPE value2 = FUNC2 (); \
+ return value1 + value2; \
+}
+
+#ifndef NO_ARG
+#ifndef NO_ADD
+FLOAT_ARG (add, +)
+DOUBLE_ARG (add, +)
+FLOAT128_ARG (add, +)
+LDOUBLE_ARG (add, +)
+#endif
+
+#ifndef NO_SUB
+FLOAT_ARG (sub, -)
+DOUBLE_ARG (sub, -)
+FLOAT128_ARG (sub, -)
+LDOUBLE_ARG (sub, -)
+#endif
+
+#ifndef NO_MUL
+FLOAT_ARG (mul, *)
+DOUBLE_ARG (mul, *)
+FLOAT128_ARG (mul, *)
+LDOUBLE_ARG (mul, *)
+#endif
+
+#ifndef NO_DIV
+FLOAT_ARG (div, /)
+DOUBLE_ARG (div, /)
+FLOAT128_ARG (div, /)
+LDOUBLE_ARG (div, /)
+#endif
+#endif
+
+#ifndef NO_PTR
+#ifndef NO_ADD
+FLOAT_PTR (add, +)
+DOUBLE_PTR (add, +)
+FLOAT128_PTR (add, +)
+LDOUBLE_PTR (add, +)
+#endif
+
+#ifndef NO_SUB
+FLOAT_PTR (sub, -)
+DOUBLE_PTR (sub, -)
+FLOAT128_PTR (sub, -)
+LDOUBLE_PTR (sub, -)
+#endif
+
+#ifndef NO_MUL
+FLOAT_PTR (mul, *)
+DOUBLE_PTR (mul, *)
+FLOAT128_PTR (mul, *)
+LDOUBLE_PTR (mul, *)
+#endif
+
+#ifndef NO_DIV
+FLOAT_PTR (div, /)
+DOUBLE_PTR (div, /)
+FLOAT128_PTR (div, /)
+LDOUBLE_PTR (div, /)
+#endif
+#endif
+
+#ifndef NO_CALL
+FLOAT_CALL ()
+DOUBLE_CALL ()
+FLOAT128_CALL ()
+LDOUBLE_CALL ()
+#endif
+
+/* { dg-final { scan-assembler "xsaddqp" } } */
+/* { dg-final { scan-assembler "xssubqp" } } */