Enable const permutations for V64QImode.

gcc/
	* config/i386/i386.c (expand_vec_perm_broadcast_1): Handle v64qi.
	(expand_vec_perm_vpermi2_vpshub2): New.
	(ix86_expand_vec_perm_const_1): Use it.
	(ix86_vectorize_vec_perm_const_ok): Handle v64qi.
	* config/i386/sse.md (VEC_PERM_CONST): Add v64qi.

From-SVN: r218482

3 files changed, 90 insertions, 1 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6f9096b..15f5f26 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2014-12-08  Ilya Tocar  <ilya.tocar@intel.com>
+
+	* config/i386/i386.c (expand_vec_perm_broadcast_1): Handle v64qi.
+	(expand_vec_perm_vpermi2_vpshub2): New.
+	(ix86_expand_vec_perm_const_1): Use it.
+	(ix86_vectorize_vec_perm_const_ok): Handle v64qi.
+	* config/i386/sse.md (VEC_PERM_CONST): Add v64qi.
+
 2014-12-08  Ilya Enkovich  <ilya.enkovich@intel.com>
 
 	* tree-chkp.c (chkp_build_returned_bound): Don't predict
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index aaf0b38..88dd9f4 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -48882,6 +48882,7 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d)
 	emit_move_insn (d->target, gen_lowpart (d->vmode, dest));
       return true;
 
+    case V64QImode:
     case V32QImode:
     case V16HImode:
     case V8SImode:
@@ -48915,6 +48916,78 @@ expand_vec_perm_broadcast (struct expand_vec_perm_d *d)
   return expand_vec_perm_broadcast_1 (d);
 }
 
+/* Implement arbitrary permutations of two V64QImode operands
+   will 2 vpermi2w, 2 vpshufb and one vpor instruction.  */
+static bool
+expand_vec_perm_vpermi2_vpshub2 (struct expand_vec_perm_d *d)
+{
+  if (!TARGET_AVX512BW || !(d->vmode == V64QImode))
+    return false;
+
+  if (d->testing_p)
+    return true;
+
+  struct expand_vec_perm_d ds[2];
+  rtx rperm[128], vperm, target0, target1;
+  unsigned int i, nelt;
+  machine_mode vmode;
+
+  nelt = d->nelt;
+  vmode = V64QImode;
+
+  for (i = 0; i < 2; i++)
+    {
+      ds[i] = *d;
+      ds[i].vmode = V32HImode;
+      ds[i].nelt = 32;
+      ds[i].target = gen_reg_rtx (V32HImode);
+      ds[i].op0 = gen_lowpart (V32HImode, d->op0);
+      ds[i].op1 = gen_lowpart (V32HImode, d->op1);
+    }
+
+  /* Prepare permutations such that the first one takes care of
+     putting the even bytes into the right positions or one higher
+     positions (ds[0]) and the second one takes care of
+     putting the odd bytes into the right positions or one below
+     (ds[1]).  */
+
+  for (i = 0; i < nelt; i++)
+    {
+      ds[i & 1].perm[i / 2] = d->perm[i] / 2;
+      if (i & 1)
+	{
+	  rperm[i] = constm1_rtx;
+	  rperm[i + 64] = GEN_INT ((i & 14) + (d->perm[i] & 1));
+	}
+      else
+	{
+	  rperm[i] = GEN_INT ((i & 14) + (d->perm[i] & 1));
+	  rperm[i + 64] = constm1_rtx;
+	}
+    }
+
+  bool ok = expand_vec_perm_1 (&ds[0]);
+  gcc_assert (ok);
+  ds[0].target = gen_lowpart (V64QImode, ds[0].target);
+
+  ok = expand_vec_perm_1 (&ds[1]);
+  gcc_assert (ok);
+  ds[1].target = gen_lowpart (V64QImode, ds[1].target);
+
+  vperm = gen_rtx_CONST_VECTOR (V64QImode, gen_rtvec_v (64, rperm));
+  vperm = force_reg (vmode, vperm);
+  target0 = gen_reg_rtx (V64QImode);
+  emit_insn (gen_avx512bw_pshufbv64qi3 (target0, ds[0].target, vperm));
+
+  vperm = gen_rtx_CONST_VECTOR (V64QImode, gen_rtvec_v (64, rperm + 64));
+  vperm = force_reg (vmode, vperm);
+  target1 = gen_reg_rtx (V64QImode);
+  emit_insn (gen_avx512bw_pshufbv64qi3 (target1, ds[1].target, vperm));
+
+  emit_insn (gen_iorv64qi3 (d->target, target0, target1));
+  return true;
+}
+
 /* Implement arbitrary permutation of two V32QImode and V16QImode operands
    with 4 vpshufb insns, 2 vpermq and 3 vpor.  We should have already failed
    all the shorter instruction sequences.  */
@@ -49089,6 +49162,9 @@ ix86_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
   if (expand_vec_perm_vpshufb2_vpermq_even_odd (d))
     return true;
 
+  if (expand_vec_perm_vpermi2_vpshub2 (d))
+    return true;
+
   /* ??? Look for narrow permutations whose element orderings would
      allow the promotion to a wider mode.  */
 
@@ -49233,6 +49309,11 @@ ix86_vectorize_vec_perm_const_ok (machine_mode vmode,
 	/* All implementable with a single vpermi2 insn.  */
 	return true;
       break;
+    case V64QImode:
+      if (TARGET_AVX512BW)
+	/* Implementable with 2 vpermi2, 2 vpshufb and 1 or insn.  */
+	return true;
+      break;
     case V8SImode:
     case V8SFmode:
     case V4DFmode:
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index c3aaea3..734e6b4 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -10713,7 +10713,7 @@
    (V32QI "TARGET_AVX2") (V16HI "TARGET_AVX2")
    (V16SI "TARGET_AVX512F") (V8DI "TARGET_AVX512F")
    (V16SF "TARGET_AVX512F") (V8DF "TARGET_AVX512F")
-   (V32HI "TARGET_AVX512BW")])
+   (V32HI "TARGET_AVX512BW") (V64QI "TARGET_AVX512BW")])
 
 (define_expand "vec_perm_const<mode>"
   [(match_operand:VEC_PERM_CONST 0 "register_operand")