[rs6000] Fold vector subtract built-ins in GIMPLE

diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index f0c1354..0ab8de3 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -16492,6 +16492,24 @@  rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
 	gsi_replace (gsi, g, true);
 	return true;
       }
+    /* Flavors of vec_sub.  We deliberately don't expand
+       P8V_BUILTIN_VSUBUQM. */
+    case ALTIVEC_BUILTIN_VSUBUBM:
+    case ALTIVEC_BUILTIN_VSUBUHM:
+    case ALTIVEC_BUILTIN_VSUBUWM:
+    case P8V_BUILTIN_VSUBUDM:
+    case ALTIVEC_BUILTIN_VSUBFP:
+    case VSX_BUILTIN_XVSUBDP:
+      {
+	arg0 = gimple_call_arg (stmt, 0);
+	arg1 = gimple_call_arg (stmt, 1);
+	lhs = gimple_call_lhs (stmt);
+	gimple *g = gimple_build_assign (lhs, MINUS_EXPR, arg0, arg1);
+	gimple_set_location (g, gimple_location (stmt));
+	gsi_replace (gsi, g, true);
+	return true;
+      }
+
     default:
       break;
     }
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-char.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-char.c
new file mode 100644
index 0000000..5063bd8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-char.c
@@ -0,0 +1,46 @@ 
+/* Verify that overloaded built-ins for vec_sub with char
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-options "-maltivec" } */
+
+#include <altivec.h>
+
+vector signed char
+test1 (vector bool char x, vector signed char y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed char
+test2 (vector signed char x, vector bool char y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed char
+test3 (vector signed char x, vector signed char y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned char
+test4 (vector bool char x, vector unsigned char y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned char
+test5 (vector unsigned char x, vector bool char y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned char
+test6 (vector unsigned char x, vector unsigned char y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsububm" 6 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-float.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-float.c
new file mode 100644
index 0000000..8a29def
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-float.c
@@ -0,0 +1,17 @@ 
+/* Verify that overloaded built-ins for vec_sub with float
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-options "-maltivec -mno-vsx" } */
+
+#include <altivec.h>
+
+vector float
+test1 (vector float x, vector float y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsubfp" 1 } } */
+
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-floatdouble.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-floatdouble.c
new file mode 100644
index 0000000..c29acc9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-floatdouble.c
@@ -0,0 +1,23 @@ 
+/* Verify that overloaded built-ins for vec_sub with float and
+   double inputs for VSX produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-maltivec -mvsx" } */
+
+#include <altivec.h>
+
+vector float
+test1 (vector float x, vector float y)
+{
+  return vec_sub (x, y);
+}
+
+vector double
+test2 (vector double x, vector double y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "xvsubsp" 1 } } */
+/* { dg-final { scan-assembler-times "xvsubdp" 1 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int.c
new file mode 100644
index 0000000..1fac1dc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int.c
@@ -0,0 +1,47 @@ 
+/* Verify that overloaded built-ins for vec_sub with int
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-options "-maltivec" } */
+
+#include <altivec.h>
+
+vector signed int
+test1 (vector bool int x, vector signed int y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed int
+test2 (vector signed int x, vector bool int y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed int
+test3 (vector signed int x, vector signed int y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned int
+test4 (vector bool int x, vector unsigned int y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned int
+test5 (vector unsigned int x, vector bool int y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned int
+test6 (vector unsigned int x, vector unsigned int y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsubuwm" 6 } } */
+
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int128.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int128.c
new file mode 100644
index 0000000..13caa9e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-int128.c
@@ -0,0 +1,24 @@ 
+/* Verify that overloaded built-ins for vec_sub with __int128
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-require-effective-target int128 } */
+/* { dg-options "-maltivec -mvsx -mpower8-vector" } */
+/* { dg-additional-options "-maix64" { target powerpc-ibm-aix* } } */
+
+#include "altivec.h"
+
+vector signed __int128
+test1 (vector signed __int128 x, vector signed __int128 y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned __int128
+test2 (vector unsigned __int128 x, vector unsigned __int128 y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsubuqm" 2 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-longlong.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-longlong.c
new file mode 100644
index 0000000..889fba4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-longlong.c
@@ -0,0 +1,47 @@ 
+/* Verify that overloaded built-ins for vec_sub with long long
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-maltivec -mvsx -mpower8-vector" } */
+
+#include <altivec.h>
+
+vector signed long long
+test1 (vector bool long long x, vector signed long long y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed long long
+test2 (vector signed long long x, vector bool long long y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed long long
+test3 (vector signed long long x, vector signed long long y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned long long
+test4 (vector bool long long x, vector unsigned long long y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned long long
+test5 (vector unsigned long long x, vector bool long long y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned long long
+test6 (vector unsigned long long x, vector unsigned long long y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsubudm" 6 } } */
+
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-short.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-short.c
new file mode 100644
index 0000000..67052a2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-sub-short.c
@@ -0,0 +1,47 @@ 
+/* Verify that overloaded built-ins for vec_sub with short
+   inputs produce the right results.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-options "-maltivec" } */
+
+#include <altivec.h>
+
+vector signed short
+test1 (vector bool short x, vector signed short y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed short
+test2 (vector signed short x, vector bool short y)
+{
+  return vec_sub (x, y);
+}
+
+vector signed short
+test3 (vector signed short x, vector signed short y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned short
+test4 (vector bool short x, vector unsigned short y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned short
+test5 (vector unsigned short x, vector bool short y)
+{
+  return vec_sub (x, y);
+}
+
+vector unsigned short
+test6 (vector unsigned short x, vector unsigned short y)
+{
+  return vec_sub (x, y);
+}
+
+/* { dg-final { scan-assembler-times "vsubuhm" 6 } } */
+