This patch adds support for the missing versions of the vec_mul altivec...

This patch adds support for the missing versions of the vec_mul altivec
builtins from the Power Architecture 64-Bit ELF V2 ABI OpenPOWER ABI for
Linux Supplement (16 July 2015 Version 1.1). There are many of the builtins
that are missing and this is part of a series of patches to add them.

There aren't instructions for the {un}signed char, {un}signed short, and
{un}signed int versions of vec_mul so the output code is built from other
built-ins and operations that do have instructions.

The new test case is an executable test which verifies that the generated
code produces expected values. C macros were used so that the same
test case could be used for all the various supported types.

Bootstrapped and tested on powerpc64le-unknown-linux-gnu and
powerpc64-unknown-linux-gnu with no regressions. Is this ok for trunk?

[gcc]

2016-06-07  Bill Seurer  <seurer@linux.vnet.ibm.com>

	* config/rs6000/altivec.h: Add __builtin_vec_mul.
	* config/rs6000/rs6000-builtin.def (vec_mul): Change vec_mul to a
	special case Altivec builtin.
	* config/rs6000/rs6000-c.c (altivec_overloaded_builtins): Remove
	VSX_BUILTIN_VEC_MUL (replaced with special case code).
	* config/rs6000/rs6000-c.c (altivec_resolve_overloaded_builtin): Add
	code for ALTIVEC_BUILTIN_VEC_MUL.
	* config/rs6000/rs6000.c (altivec_init_builtins): Add definition
	for __builtin_vec_mul.

[gcc/testsuite]

2016-06-07  Bill Seurer  <seurer@linux.vnet.ibm.com>

	* gcc.target/powerpc/vec-mul.c: New test.

From-SVN: r237183

gcc/ChangeLog

+2016-06-07  Bill Seurer  <seurer@linux.vnet.ibm.com>
+
+	* config/rs6000/altivec.h: Add __builtin_vec_mul.
+	* config/rs6000/rs6000-builtin.def (vec_mul): Change vec_mul to a
+	special case Altivec builtin.
+	* config/rs6000/rs6000-c.c (altivec_overloaded_builtins): Remove
+	VSX_BUILTIN_VEC_MUL (replaced with special case code).
+	* config/rs6000/rs6000-c.c (altivec_resolve_overloaded_builtin): Add
+	code for ALTIVEC_BUILTIN_VEC_MUL.
+	* config/rs6000/rs6000.c (altivec_init_builtins): Add definition
+	for __builtin_vec_mul.
+
 2016-06-07  Peter Bergner  <bergner@vnet.ibm.com>
 
 	* doc/invoke.texi (RS/6000 and PowerPC Options): Document -mhtm and

gcc/config/rs6000/altivec.h

@@ -229,6 +229,7 @@
 #define vec_mladd __builtin_vec_mladd
 #define vec_msum __builtin_vec_msum
 #define vec_msums __builtin_vec_msums
+#define vec_mul __builtin_vec_mul
 #define vec_mule __builtin_vec_mule
 #define vec_mulo __builtin_vec_mulo
 #define vec_nor __builtin_vec_nor

gcc/config/rs6000/rs6000-builtin.def

@@ -1300,6 +1300,7 @@ BU_ALTIVEC_OVERLOAD_X (LVRX,	   "lvrx")
 BU_ALTIVEC_OVERLOAD_X (LVRXL,	   "lvrxl")
 BU_ALTIVEC_OVERLOAD_X (LVSL,	   "lvsl")
 BU_ALTIVEC_OVERLOAD_X (LVSR,	   "lvsr")
+BU_ALTIVEC_OVERLOAD_X (MUL,	   "mul")
 BU_ALTIVEC_OVERLOAD_X (PROMOTE,	   "promote")
 BU_ALTIVEC_OVERLOAD_X (SLD,	   "sld")
 BU_ALTIVEC_OVERLOAD_X (SPLAT,	   "splat")
@@ -1600,7 +1601,6 @@ BU_VSX_OVERLOAD_3V (XXPERMDI, "xxpermdi")
 BU_VSX_OVERLOAD_3V (XXSLDWI,  "xxsldwi")
 
 /* 2 argument VSX overloaded builtin functions.  */
-BU_VSX_OVERLOAD_2 (MUL,	     "mul")
 BU_VSX_OVERLOAD_2 (DIV,	     "div")
 BU_VSX_OVERLOAD_2 (XXMRGHW,  "xxmrghw")
 BU_VSX_OVERLOAD_2 (XXMRGLW,  "xxmrglw")

gcc/config/rs6000/rs6000-c.c

@@ -1941,14 +1941,6 @@ const struct altivec_builtin_types altivec_overloaded_builtins[] = {
     RS6000_BTI_unsigned_V16QI, RS6000_BTI_bool_V16QI, RS6000_BTI_unsigned_V16QI, 0 },
   { ALTIVEC_BUILTIN_VEC_VMINUB, ALTIVEC_BUILTIN_VMINUB,
     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI, RS6000_BTI_bool_V16QI, 0 },
-  { VSX_BUILTIN_VEC_MUL, VSX_BUILTIN_XVMULSP,
-    RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_V4SF, 0 },
-  { VSX_BUILTIN_VEC_MUL, VSX_BUILTIN_XVMULDP,
-    RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_V2DF, 0 },
-  { VSX_BUILTIN_VEC_MUL, VSX_BUILTIN_MUL_V2DI,
-    RS6000_BTI_V2DI, RS6000_BTI_V2DI, RS6000_BTI_V2DI, 0 },
-  { VSX_BUILTIN_VEC_MUL, VSX_BUILTIN_MUL_V2DI,
-    RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI, 0 },
   { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULEUB,
     RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI, 0 },
   { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESB,
@@ -4683,6 +4675,57 @@ assignment for unaligned loads and stores");
     warning (OPT_Wdeprecated, "vec_lvsr is deprecated for little endian; use \
 assignment for unaligned loads and stores");
 
+  if (fcode == ALTIVEC_BUILTIN_VEC_MUL)
+    {
+      /* vec_mul needs to be special cased because there are no instructions
+	 for it for the {un}signed char, {un}signed short, and {un}signed int
+	 types.  */
+      if (nargs != 2)
+	{
+	  error ("vec_mul only accepts 2 arguments");
+	  return error_mark_node;
+	}
+
+      tree arg0 = (*arglist)[0];
+      tree arg0_type = TREE_TYPE (arg0);
+      tree arg1 = (*arglist)[1];
+      tree arg1_type = TREE_TYPE (arg1);
+
+      /* Both arguments must be vectors and the types must match.  */
+      if (arg0_type != arg1_type)
+	goto bad;
+      if (TREE_CODE (arg0_type) != VECTOR_TYPE)
+	goto bad;
+
+      switch (TYPE_MODE (TREE_TYPE (arg0_type)))
+	{
+	  case QImode:
+	  case HImode:
+	  case SImode:
+	  case DImode:
+	  case TImode:
+	    {
+	      /* For scalar types just use a multiply expression.  */
+	      return fold_build2_loc (loc, MULT_EXPR, TREE_TYPE (arg0),
+					arg0, arg1);
+	    }
+	  case SFmode:
+	    {
+	      /* For floats use the xvmulsp instruction directly.  */
+	      tree call = rs6000_builtin_decls[VSX_BUILTIN_XVMULSP];
+	      return build_call_expr (call, 2, arg0, arg1);
+	    }
+	  case DFmode:
+	    {
+	      /* For doubles use the xvmuldp instruction directly.  */
+	      tree call = rs6000_builtin_decls[VSX_BUILTIN_XVMULDP];
+	      return build_call_expr (call, 2, arg0, arg1);
+	    }
+	  /* Other types are errors.  */
+	  default:
+	    goto bad;
+	}
+    }
 
   if (fcode == ALTIVEC_BUILTIN_VEC_CMPNE)
     {

gcc/config/rs6000/rs6000.c

@@ -16573,6 +16573,8 @@ altivec_init_builtins (void)
 		ALTIVEC_BUILTIN_VEC_ADDEC);
   def_builtin ("__builtin_vec_cmpne", opaque_ftype_opaque_opaque,
 		ALTIVEC_BUILTIN_VEC_CMPNE);
+  def_builtin ("__builtin_vec_mul", opaque_ftype_opaque_opaque,
+		ALTIVEC_BUILTIN_VEC_MUL);
 
   /* Cell builtins.  */
   def_builtin ("__builtin_altivec_lvlx",  v16qi_ftype_long_pcvoid, ALTIVEC_BUILTIN_LVLX);

gcc/testsuite/ChangeLog

+2016-06-07  Bill Seurer  <seurer@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/vec-mul.c: New test.
+
 2016-06-07  David Malcolm  <dmalcolm@redhat.com>
 
 	* gcc.dg/spellcheck-fields-2.c: New test case.

gcc/testsuite/gcc.target/powerpc/vec-mul.c

+/* { dg-do run { target { powerpc64*-*-* } } } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-mvsx -O3" } */
+
+/* Test that the vec_mul builtin works as expected.  */
+
+#include "altivec.h"
+
+#define N 4096
+
+void abort ();
+
+#define define_test_functions(STYPE, NAMESUFFIX) \
+\
+STYPE result_##NAMESUFFIX[N]; \
+STYPE operand1_##NAMESUFFIX[N]; \
+STYPE operand2_##NAMESUFFIX[N]; \
+STYPE expected_##NAMESUFFIX[N]; \
+\
+__attribute__((noinline)) void vector_tests_##NAMESUFFIX () \
+{ \
+  int i; \
+  vector STYPE v1, v2, tmp; \
+  for (i = 0; i < N; i+=16/sizeof (STYPE)) \
+    { \
+      /* result=operand1*operand2.  */ \
+      v1 = vec_vsx_ld (0, &operand1_##NAMESUFFIX[i]); \
+      v2 = vec_vsx_ld (0, &operand2_##NAMESUFFIX[i]); \
+\
+      tmp = vec_mul (v1, v2); \
+      vec_vsx_st (tmp, 0, &result_##NAMESUFFIX[i]); \
+    } \
+} \
+\
+__attribute__((noinline)) void init_##NAMESUFFIX () \
+{ \
+  int i; \
+  for (i = 0; i < N; ++i) \
+    { \
+      result_##NAMESUFFIX[i] = 0; \
+      operand1_##NAMESUFFIX[i] = (i+1) % 31; \
+      operand2_##NAMESUFFIX[i] = (i*2) % 15; \
+      expected_##NAMESUFFIX[i] = operand1_##NAMESUFFIX[i] * \
+				 operand2_##NAMESUFFIX[i]; \
+    } \
+} \
+\
+__attribute__((noinline)) void verify_results_##NAMESUFFIX () \
+{ \
+  int i; \
+  for (i = 0; i < N; ++i) \
+    { \
+      if (result_##NAMESUFFIX[i] != expected_##NAMESUFFIX[i]) \
+	abort (); \
+    } \
+}
+
+
+#define execute_test_functions(STYPE, NAMESUFFIX) \
+{ \
+  init_##NAMESUFFIX (); \
+  vector_tests_##NAMESUFFIX (); \
+  verify_results_##NAMESUFFIX (); \
+}
+
+
+define_test_functions (signed int, si);
+define_test_functions (unsigned int, ui);
+define_test_functions (signed short, ss);
+define_test_functions (unsigned short, us);
+define_test_functions (signed char, sc);
+define_test_functions (unsigned char, uc);
+define_test_functions (float, f);
+
+int main ()
+{
+  execute_test_functions (signed int, si);
+  execute_test_functions (unsigned int, ui);
+  execute_test_functions (signed short, ss);
+  execute_test_functions (unsigned short, us);
+  execute_test_functions (signed char, sc);
+  execute_test_functions (unsigned char, uc);
+  execute_test_functions (float, f);
+
+  return 0;
+}