rs6000.c (gimple-ssa.h): New #include.

[gcc]

2016-11-04  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* config/rs6000/rs6000.c (gimple-ssa.h): New #include.
	(TARGET_GIMPLE_FOLD_BUILTIN): Define as
	rs6000_gimple_fold_builtin.
	(rs6000_gimple_fold_builtin): New function.  Add handling for
	early expansion of vector addition builtins.


[gcc/testsuite]

2016-11-04  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* gcc.target/powerpc/fold-vec-add-1.c: New.
	* gcc.target/powerpc/fold-vec-add-2.c: New.
	* gcc.target/powerpc/fold-vec-add-3.c: New.
	* gcc.target/powerpc/fold-vec-add-4.c: New.
	* gcc.target/powerpc/fold-vec-add-5.c: New.
	* gcc.target/powerpc/fold-vec-add-6.c: New.
	* gcc.target/powerpc/fold-vec-add-7.c: New.

From-SVN: r241857

gcc/ChangeLog

+2016-11-04  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* config/rs6000/rs6000.c (gimple-ssa.h): New #include.
+	(TARGET_GIMPLE_FOLD_BUILTIN): Define as
+	rs6000_gimple_fold_builtin.
+	(rs6000_gimple_fold_builtin): New function.  Add handling for
+	early expansion of vector addition builtins.
+
 2016-11-04  Eric Botcazou  <ebotcazou@adacore.com>
 
 	* expr.h (copy_blkmode_from_reg): Delete.

gcc/config/rs6000/rs6000.c

@@ -56,6 +56,7 @@
 #include "sched-int.h"
 #include "gimplify.h"
 #include "gimple-iterator.h"
+#include "gimple-ssa.h"
 #include "gimple-walk.h"
 #include "intl.h"
 #include "params.h"
@@ -1632,6 +1633,8 @@ static const struct attribute_spec rs6000_attribute_table[] =
 
 #undef TARGET_FOLD_BUILTIN
 #define TARGET_FOLD_BUILTIN rs6000_fold_builtin
+#undef TARGET_GIMPLE_FOLD_BUILTIN
+#define TARGET_GIMPLE_FOLD_BUILTIN rs6000_gimple_fold_builtin
 
 #undef TARGET_EXPAND_BUILTIN
 #define TARGET_EXPAND_BUILTIN rs6000_expand_builtin
@@ -16391,6 +16394,46 @@ rs6000_fold_builtin (tree fndecl, int n_args ATTRIBUTE_UNUSED,
 #endif
 }
 
+/* Fold a machine-dependent built-in in GIMPLE.  (For folding into
+   a constant, use rs6000_fold_builtin.)  */
+
+bool
+rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
+{
+  gimple *stmt = gsi_stmt (*gsi);
+  tree fndecl = gimple_call_fndecl (stmt);
+  gcc_checking_assert (fndecl && DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD);
+  enum rs6000_builtins fn_code
+    = (enum rs6000_builtins) DECL_FUNCTION_CODE (fndecl);
+  tree arg0, arg1, lhs;
+
+  switch (fn_code)
+    {
+    /* Flavors of vec_add.  We deliberately don't expand
+       P8V_BUILTIN_VADDUQM as it gets lowered from V1TImode to
+       TImode, resulting in much poorer code generation.  */
+    case ALTIVEC_BUILTIN_VADDUBM:
+    case ALTIVEC_BUILTIN_VADDUHM:
+    case ALTIVEC_BUILTIN_VADDUWM:
+    case P8V_BUILTIN_VADDUDM:
+    case ALTIVEC_BUILTIN_VADDFP:
+    case VSX_BUILTIN_XVADDDP:
+      {
+	arg0 = gimple_call_arg (stmt, 0);
+	arg1 = gimple_call_arg (stmt, 1);
+	lhs = gimple_call_lhs (stmt);
+	gimple *g = gimple_build_assign (lhs, PLUS_EXPR, arg0, arg1);
+	gimple_set_location (g, gimple_location (stmt));
+	gsi_replace (gsi, g, true);
+	return true;
+      }
+    default:
+      break;
+    }
+
+  return false;
+}
+
 /* Expand an expression EXP that calls a built-in function,
    with result going to TARGET if that's convenient
    (and in mode MODE if that's convenient).

gcc/testsuite/ChangeLog

+2016-11-04  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/fold-vec-add-1.c: New.
+	* gcc.target/powerpc/fold-vec-add-2.c: New.
+	* gcc.target/powerpc/fold-vec-add-3.c: New.
+	* gcc.target/powerpc/fold-vec-add-4.c: New.
+	* gcc.target/powerpc/fold-vec-add-5.c: New.
+	* gcc.target/powerpc/fold-vec-add-6.c: New.
+	* gcc.target/powerpc/fold-vec-add-7.c: New.
+
 2016-11-04  Toma Tabacu  <toma.tabacu@imgtec.com>
 
 	* gcc.target/mips/mips.exp (mips-dg-options): Downgrade to R5

gcc/testsuite/gcc.target/powerpc/fold-vec-add-1.c

+/* Verify that overloaded built-ins for vec_add with char
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+#include <altivec.h>
+
+vector signed char
+test1 (vector bool char x, vector signed char y)
+{
+  return vec_add (x, y);
+}
+
+vector signed char
+test2 (vector signed char x, vector bool char y)
+{
+  return vec_add (x, y);
+}
+
+vector signed char
+test3 (vector signed char x, vector signed char y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned char
+test4 (vector bool char x, vector unsigned char y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned char
+test5 (vector unsigned char x, vector bool char y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned char
+test6 (vector unsigned char x, vector unsigned char y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vaddubm" 6 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-2.c

+/* Verify that overloaded built-ins for vec_add with short
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+#include <altivec.h>
+
+vector signed short
+test1 (vector bool short x, vector signed short y)
+{
+  return vec_add (x, y);
+}
+
+vector signed short
+test2 (vector signed short x, vector bool short y)
+{
+  return vec_add (x, y);
+}
+
+vector signed short
+test3 (vector signed short x, vector signed short y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned short
+test4 (vector bool short x, vector unsigned short y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned short
+test5 (vector unsigned short x, vector bool short y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned short
+test6 (vector unsigned short x, vector unsigned short y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vadduhm" 6 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-3.c

+/* Verify that overloaded built-ins for vec_add with int
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+#include <altivec.h>
+
+vector signed int
+test1 (vector bool int x, vector signed int y)
+{
+  return vec_add (x, y);
+}
+
+vector signed int
+test2 (vector signed int x, vector bool int y)
+{
+  return vec_add (x, y);
+}
+
+vector signed int
+test3 (vector signed int x, vector signed int y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned int
+test4 (vector bool int x, vector unsigned int y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned int
+test5 (vector unsigned int x, vector bool int y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned int
+test6 (vector unsigned int x, vector unsigned int y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vadduwm" 6 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-4.c

+/* Verify that overloaded built-ins for vec_add with long long
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+
+#include <altivec.h>
+
+vector signed long long
+test1 (vector bool long long x, vector signed long long y)
+{
+  return vec_add (x, y);
+}
+
+vector signed long long
+test2 (vector signed long long x, vector bool long long y)
+{
+  return vec_add (x, y);
+}
+
+vector signed long long
+test3 (vector signed long long x, vector signed long long y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned long long
+test4 (vector bool long long x, vector unsigned long long y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned long long
+test5 (vector unsigned long long x, vector bool long long y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned long long
+test6 (vector unsigned long long x, vector unsigned long long y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vaddudm" 6 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-5.c

+/* Verify that overloaded built-ins for vec_add with float
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-additional-options "-mno-vsx" } */
+
+#include <altivec.h>
+
+vector float
+test1 (vector float x, vector float y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vaddfp" 1 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-6.c

+/* Verify that overloaded built-ins for vec_add with float and
+   double inputs for VSX produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+
+#include <altivec.h>
+
+vector float
+test1 (vector float x, vector float y)
+{
+  return vec_add (x, y);
+}
+
+vector double
+test2 (vector double x, vector double y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "xvaddsp" 1 } } */
+/* { dg-final { scan-assembler-times "xvadddp" 1 } } */

gcc/testsuite/gcc.target/powerpc/fold-vec-add-7.c

+/* Verify that overloaded built-ins for vec_add with __int128
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+
+#include "altivec.h"
+
+vector signed __int128
+test1 (vector signed __int128 x, vector signed __int128 y)
+{
+  return vec_add (x, y);
+}
+
+vector unsigned __int128
+test2 (vector unsigned __int128 x, vector unsigned __int128 y)
+{
+  return vec_add (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vadduqm" 2 } } */