Rework 128-bit complex multiply and divide.

This patch reworks how the complex multiply and divide built-in functions are
done.  Previously GCC created built-in declarations for doing long double complex
multiply and divide when long double is IEEE 128-bit.  However, it did not
support __ibm128 complex multiply and divide if long double is IEEE 128-bit.

This code does not create the built-in declaration with the changed name.
Instead, it uses the TARGET_MANGLE_DECL_ASSEMBLER_NAME hook to change the name
before it is written out to the assembler file like it now does for all of the
other long double built-in functions.

2023-03-20   Michael Meissner  <meissner@linux.ibm.com>

gcc/

	PR target/109067
	* config/rs6000/rs6000.cc (create_complex_muldiv): Delete.
	(init_float128_ieee): Delete code to switch complex multiply and divide
	for long double.
	(complex_multiply_builtin_code): New helper function.
	(complex_divide_builtin_code): Likewise.
	(rs6000_mangle_decl_assembler_name): Add support for mangling the name
	of complex 128-bit multiply and divide built-in functions.

gcc/testsuite/

	PR target/109067
	* gcc.target/powerpc/divic3-1.c: New test.
	* gcc.target/powerpc/divic3-2.c: Likewise.
	* gcc.target/powerpc/mulic3-1.c: Likewise.
	* gcc.target/powerpc/mulic3-2.c: Likewise.

gcc/config/rs6000/rs6000.cc

@@ -11154,26 +11154,6 @@ init_float128_ibm (machine_mode mode)
     }
 }
 
-/* Create a decl for either complex long double multiply or complex long double
-   divide when long double is IEEE 128-bit floating point.  We can't use
-   __multc3 and __divtc3 because the original long double using IBM extended
-   double used those names.  The complex multiply/divide functions are encoded
-   as builtin functions with a complex result and 4 scalar inputs.  */
-
-static void
-create_complex_muldiv (const char *name, built_in_function fncode, tree fntype)
-{
-  tree fndecl = add_builtin_function (name, fntype, fncode, BUILT_IN_NORMAL,
-				      name, NULL_TREE);
-
-  set_builtin_decl (fncode, fndecl, true);
-
-  if (TARGET_DEBUG_BUILTIN)
-    fprintf (stderr, "create complex %s, fncode: %d\n", name, (int) fncode);
-
-  return;
-}
-
 /* Set up IEEE 128-bit floating point routines.  Use different names if the
    arguments can be passed in a vector register.  The historical PowerPC
    implementation of IEEE 128-bit floating point used _q_<op> for the names, so
@@ -11185,32 +11165,6 @@ init_float128_ieee (machine_mode mode)
 {
   if (FLOAT128_VECTOR_P (mode))
     {
-      static bool complex_muldiv_init_p = false;
-
-      /* Set up to call __mulkc3 and __divkc3 under -mabi=ieeelongdouble.  If
-	 we have clone or target attributes, this will be called a second
-	 time.  We want to create the built-in function only once.  */
-     if (mode == TFmode && TARGET_IEEEQUAD && !complex_muldiv_init_p)
-       {
-	 complex_muldiv_init_p = true;
-	 built_in_function fncode_mul =
-	   (built_in_function) (BUILT_IN_COMPLEX_MUL_MIN + TCmode
-				- MIN_MODE_COMPLEX_FLOAT);
-	 built_in_function fncode_div =
-	   (built_in_function) (BUILT_IN_COMPLEX_DIV_MIN + TCmode
-				- MIN_MODE_COMPLEX_FLOAT);
-
-	 tree fntype = build_function_type_list (complex_long_double_type_node,
-						 long_double_type_node,
-						 long_double_type_node,
-						 long_double_type_node,
-						 long_double_type_node,
-						 NULL_TREE);
-
-	 create_complex_muldiv ("__mulkc3", fncode_mul, fntype);
-	 create_complex_muldiv ("__divkc3", fncode_div, fntype);
-       }
-
       set_optab_libfunc (add_optab, mode, "__addkf3");
       set_optab_libfunc (sub_optab, mode, "__subkf3");
       set_optab_libfunc (neg_optab, mode, "__negkf2");
@@ -28228,6 +28182,27 @@ rs6000_starting_frame_offset (void)
   return RS6000_STARTING_FRAME_OFFSET;
 }
 
+/* Internal function to return the built-in function id for the complex
+   multiply operation for a given mode.  */
+
+static inline built_in_function
+complex_multiply_builtin_code (machine_mode mode)
+{
+  gcc_assert (IN_RANGE (mode, MIN_MODE_COMPLEX_FLOAT, MAX_MODE_COMPLEX_FLOAT));
+  int func = BUILT_IN_COMPLEX_MUL_MIN + mode - MIN_MODE_COMPLEX_FLOAT;
+  return (built_in_function) func;
+}
+
+/* Internal function to return the built-in function id for the complex divide
+   operation for a given mode.  */
+
+static inline built_in_function
+complex_divide_builtin_code (machine_mode mode)
+{
+  gcc_assert (IN_RANGE (mode, MIN_MODE_COMPLEX_FLOAT, MAX_MODE_COMPLEX_FLOAT));
+  int func = BUILT_IN_COMPLEX_DIV_MIN + mode - MIN_MODE_COMPLEX_FLOAT;
+  return (built_in_function) func;
+}
 
 /* On 64-bit Linux and Freebsd systems, possibly switch the long double library
    function names from <foo>l to <foo>f128 if the default long double type is
@@ -28246,11 +28221,53 @@ rs6000_starting_frame_offset (void)
    only do this transformation if the __float128 type is enabled.  This
    prevents us from doing the transformation on older 32-bit ports that might
    have enabled using IEEE 128-bit floating point as the default long double
-   type.  */
+   type.
+
+   We also use the TARGET_MANGLE_DECL_ASSEMBLER_NAME hook to change the
+   function names used for complex multiply and divide to the appropriate
+   names.  */
 
 static tree
 rs6000_mangle_decl_assembler_name (tree decl, tree id)
 {
+  /* Handle complex multiply/divide.  For IEEE 128-bit, use __mulkc3 or
+     __divkc3 and for IBM 128-bit use __multc3 and __divtc3.  */
+  if (TARGET_FLOAT128_TYPE
+      && TREE_CODE (decl) == FUNCTION_DECL
+      && DECL_IS_UNDECLARED_BUILTIN (decl)
+      && DECL_BUILT_IN_CLASS (decl) == BUILT_IN_NORMAL)
+    {
+      built_in_function id = DECL_FUNCTION_CODE (decl);
+      const char *newname = NULL;
+
+      if (id == complex_multiply_builtin_code (KCmode))
+	newname = "__mulkc3";
+
+      else if (id == complex_multiply_builtin_code (ICmode))
+	newname = "__multc3";
+
+      else if (id == complex_multiply_builtin_code (TCmode))
+	newname = (TARGET_IEEEQUAD) ? "__mulkc3" : "__multc3";
+
+      else if (id == complex_divide_builtin_code (KCmode))
+	newname = "__divkc3";
+
+      else if (id == complex_divide_builtin_code (ICmode))
+	newname = "__divtc3";
+
+      else if (id == complex_divide_builtin_code (TCmode))
+	newname = (TARGET_IEEEQUAD) ? "__divkc3" : "__divtc3";
+
+      if (newname)
+	{
+	  if (TARGET_DEBUG_BUILTIN)
+	    fprintf (stderr, "Map complex mul/div => %s\n", newname);
+
+	  return get_identifier (newname);
+	}
+    }
+
+  /* Map long double built-in functions if long double is IEEE 128-bit.  */
   if (TARGET_FLOAT128_TYPE && TARGET_IEEEQUAD && TARGET_LONG_DOUBLE_128
       && TREE_CODE (decl) == FUNCTION_DECL
       && DECL_IS_UNDECLARED_BUILTIN (decl)

gcc/testsuite/gcc.target/powerpc/divic3-1.c

@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ppc_float128_sw } */
+/* { dg-options "-O2 -mabi=ieeelongdouble -Wno-psabi" } */
+
+/* When GCC is configured with an older library that does not support IEEE
+   128-bit, it issues a warning if you change the long double type. We use
+   -Wno-psabi to silence this warning.  Since this is a code generation test,
+   it does not matter if the library has full IEEE 128-bit support.  */
+
+/* Check that complex divide generates the right call for __ibm128 when long
+   double is IEEE 128-bit floating point.  */
+
+typedef _Complex long double c_ibm128_t __attribute__((mode(__IC__)));
+
+void
+divide (c_ibm128_t *p, c_ibm128_t *q, c_ibm128_t *r)
+{
+  *p = *q / *r;
+}
+
+/* { dg-final { scan-assembler {\mbl .*__divtc3\M} } } */

gcc/testsuite/gcc.target/powerpc/divic3-2.c

@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ppc_float128_sw } */
+/* { dg-require-effective-target longdouble128 } */
+/* { dg-options "-O2 -mabi=ibmlongdouble -Wno-psabi" } */
+
+/* When GCC is configured with an older library that does not support IEEE
+   128-bit, it issues a warning if you change the long double type. We use
+   -Wno-psabi to silence this warning.  Since this is a code generation test,
+   it does not matter if the library has full IEEE 128-bit support.
+
+   We also need to require that the default long double is 128-bits, otherwise
+   the TC/TF modes might not be available.  */
+
+/* Check that complex divide generates the right call for __ibm128 when long
+   double is IBM 128-bit floating point.  */
+
+typedef _Complex long double c_ibm128_t __attribute__((mode(__TC__)));
+
+void
+divide (c_ibm128_t *p, c_ibm128_t *q, c_ibm128_t *r)
+{
+  *p = *q / *r;
+}
+
+/* { dg-final { scan-assembler {\mbl .*__divtc3\M} } } */

gcc/testsuite/gcc.target/powerpc/mulic3-1.c

@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ppc_float128_sw } */
+/* { dg-options "-O2 -mabi=ieeelongdouble -Wno-psabi" } */
+
+/* When GCC is configured with an older library that does not support IEEE
+   128-bit, it issues a warning if you change the long double type. We use
+   -Wno-psabi to silence this warning.  Since this is a code generation test,
+   it does not matter if the library has full IEEE 128-bit support.  */
+
+/* Check that complex multiply generates the right call for __ibm128 when long
+   double is IEEE 128-bit floating point.  */
+
+typedef _Complex long double c_ibm128_t __attribute__((mode(__IC__)));
+
+void
+multiply (c_ibm128_t *p, c_ibm128_t *q, c_ibm128_t *r)
+{
+  *p = *q * *r;
+}
+
+/* { dg-final { scan-assembler {\mbl .*__multc3\M} } } */

gcc/testsuite/gcc.target/powerpc/mulic3-2.c

@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ppc_float128_sw } */
+/* { dg-require-effective-target longdouble128 } */
+/* { dg-options "-O2 -mabi=ibmlongdouble -Wno-psabi" } */
+
+/* When GCC is configured with an older library that does not support IEEE
+   128-bit, it issues a warning if you change the long double type. We use
+   -Wno-psabi to silence this warning.  Since this is a code generation test,
+   it does not matter if the library has full IEEE 128-bit support.
+
+   We also need to require that the default long double is 128-bits, otherwise
+   the TC/TF modes might not be available.  */
+
+/* Check that complex multiply generates the right call for __ibm128 when long
+   double is IBM 128-bit floating point.  */
+
+typedef _Complex long double c_ibm128_t __attribute__((mode(__TC__)));
+
+void
+multiply (c_ibm128_t *p, c_ibm128_t *q, c_ibm128_t *r)
+{
+  *p = *q * *r;
+}
+
+/* { dg-final { scan-assembler {\mbl .*__multc3\M} } } */