rs6000: build constant via li;rotldi

If a constant is possible to be rotated to/from a positive or negative
value which "li" can generated, then "li;rotldi" can be used to build
the constant.

gcc/ChangeLog:

	* config/rs6000/rs6000.cc (can_be_built_by_li_and_rotldi): New function.
	(rs6000_emit_set_long_const): Call can_be_built_by_li_and_rotldi.

gcc/testsuite/ChangeLog:

	* gcc.target/powerpc/const-build.c: New test.

diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index cc9253bb0406a510d9e75812abce82692e52a738..a4c461c0a05b024bd70a6b1569e90fc472339ae9 100644 (file)
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -10299,6 +10299,31 @@ rs6000_emit_set_const (rtx dest, rtx source)
   return true;
 }
 
+/* Check if value C can be built by 2 instructions: one is 'li', another is
+   'rotldi'.
+
+   If so, *SHIFT is set to the shift operand of rotldi(rldicl), and *MASK
+   is set to the mask operand of rotldi(rldicl), and return true.
+   Return false otherwise.  */
+
+static bool
+can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
+                                  HOST_WIDE_INT *mask)
+{
+  /* If C or ~C contains at least 49 successive zeros, then C can be rotated
+     to/from a positive or negative value that 'li' is able to load.  */
+  int n;
+  if (can_be_rotated_to_lowbits (c, 15, &n)
+      || can_be_rotated_to_lowbits (~c, 15, &n))
+    {
+      *mask = HOST_WIDE_INT_M1;
+      *shift = HOST_BITS_PER_WIDE_INT - n;
+      return true;
+    }
+
+  return false;
+}
+
 /* Subroutine of rs6000_emit_set_const, handling PowerPC64 DImode.
    Output insns to set DEST equal to the constant C as a series of
    lis, ori and shl instructions.  */
@@ -10307,15 +10332,14 @@ static void
 rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
 {
   rtx temp;
+  int shift;
+  HOST_WIDE_INT mask;
   HOST_WIDE_INT ud1, ud2, ud3, ud4;
 
   ud1 = c & 0xffff;
-  c = c >> 16;
-  ud2 = c & 0xffff;
-  c = c >> 16;
-  ud3 = c & 0xffff;
-  c = c >> 16;
-  ud4 = c & 0xffff;
+  ud2 = (c >> 16) & 0xffff;
+  ud3 = (c >> 32) & 0xffff;
+  ud4 = (c >> 48) & 0xffff;
 
   if ((ud4 == 0xffff && ud3 == 0xffff && ud2 == 0xffff && (ud1 & 0x8000))
       || (ud4 == 0 && ud3 == 0 && ud2 == 0 && ! (ud1 & 0x8000)))
@@ -10346,6 +10370,17 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
       emit_move_insn (dest, gen_rtx_XOR (DImode, temp,
                                         GEN_INT ((ud2 ^ 0xffff) << 16)));
     }
+  else if (can_be_built_by_li_and_rotldi (c, &shift, &mask))
+    {
+      temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
+      unsigned HOST_WIDE_INT imm = (c | ~mask);
+      imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
+
+      emit_move_insn (temp, GEN_INT (imm));
+      if (shift != 0)
+       temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
+      emit_move_insn (dest, temp);
+    }
   else if (ud3 == 0 && ud4 == 0)
     {
       temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);

diff --git a/gcc/testsuite/gcc.target/powerpc/const-build.c b/gcc/testsuite/gcc.target/powerpc/const-build.c
new file mode 100644 (file)
index 0000000..9534ce5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
@@ -0,0 +1,57 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-require-effective-target has_arch_ppc64 } */
+
+/* Verify that two instructions are successfully used to build constants.
+   One insn is li, another is rotate: rldicl.  */
+
+#define NOIPA __attribute__ ((noipa))
+
+struct fun
+{
+  long long (*f) (void);
+  long long val;
+};
+
+long long NOIPA
+li_rotldi_1 (void)
+{
+  return 0x7531000000000LL;
+}
+
+long long NOIPA
+li_rotldi_2 (void)
+{
+  return 0x2100000000000064LL;
+}
+
+long long NOIPA
+li_rotldi_3 (void)
+{
+  return 0xffff8531ffffffffLL;
+}
+
+long long NOIPA
+li_rotldi_4 (void)
+{
+  return 0x21ffffffffffff94LL;
+}
+
+struct fun arr[] = {
+  {li_rotldi_1, 0x7531000000000LL},
+  {li_rotldi_2, 0x2100000000000064LL},
+  {li_rotldi_3, 0xffff8531ffffffffLL},
+  {li_rotldi_4, 0x21ffffffffffff94LL},
+};
+
+/* { dg-final { scan-assembler-times {\mrotldi\M} 4 } } */
+
+int
+main ()
+{
+  for (int i = 0; i < sizeof (arr) / sizeof (arr[0]); i++)
+    if ((*arr[i].f) () != arr[i].val)
+      __builtin_abort ();
+
+  return 0;
+}