i386: Implement V2SI and V4HI shuffles

2020-05-26  Uroš Bizjak  <ubizjak@gmail.com>

gcc/ChangeLog:
	* config/i386/mmx.md (*mmx_pshufd_1): New insn pattern.
	* config/i386/i386-expand.c (ix86_vectorize_vec_perm_const):
	Handle E_V2SImode and E_V4HImode.
	(expand_vec_perm_even_odd_1): Handle E_V4HImode.
	Assert that E_V2SImode is already handled.
	(expand_vec_perm_broadcast_1): Assert that E_V2SImode
	is already handled by standard shuffle patterns.

gcc/testsuite/ChangeLog:
	* gcc.target/i386/vperm-v2si.c: New test.
	* gcc.target/i386/vperm-v4hi.c: Ditto.

1 files changed, 25 insertions, 1 deletions

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 79f827fd653..338b4f7cf4f 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -18634,10 +18634,26 @@ expand_vec_perm_even_odd_1 (struct expand_vec_perm_d *d, unsigned odd)
     case E_V2DFmode:
     case E_V4SFmode:
     case E_V2DImode:
+    case E_V2SImode:
     case E_V4SImode:
       /* These are always directly implementable by expand_vec_perm_1.  */
       gcc_unreachable ();
 
+    case E_V4HImode:
+      if (d->testing_p)
+	break;
+      /* We need 2*log2(N)-1 operations to achieve odd/even
+	 with interleave. */
+      t1 = gen_reg_rtx (V4HImode);
+      emit_insn (gen_mmx_punpckhwd (t1, d->op0, d->op1));
+      emit_insn (gen_mmx_punpcklwd (d->target, d->op0, d->op1));
+      if (odd)
+	t2 = gen_mmx_punpckhwd (d->target, d->target, t1);
+      else
+	t2 = gen_mmx_punpcklwd (d->target, d->target, t1);
+      emit_insn (t2);
+      break;
+
     case E_V8HImode:
       if (TARGET_SSE4_1)
 	return expand_vec_perm_even_odd_pack (d);
@@ -18820,6 +18836,7 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d)
     case E_V2DFmode:
     case E_V2DImode:
     case E_V4SFmode:
+    case E_V2SImode:
     case E_V4SImode:
       /* These are always implementable using standard shuffle patterns.  */
       gcc_unreachable ();
@@ -19312,6 +19329,11 @@ ix86_vectorize_vec_perm_const (machine_mode vmode, rtx target, rtx op0,
       if (d.testing_p && TARGET_SSSE3)
 	return true;
       break;
+    case E_V2SImode:
+    case E_V4HImode:
+      if (!TARGET_MMX_WITH_SSE)
+	return false;
+      break;
     case E_V2DImode:
     case E_V2DFmode:
       if (!TARGET_SSE)
@@ -19344,7 +19366,9 @@ ix86_vectorize_vec_perm_const (machine_mode vmode, rtx target, rtx op0,
       d.one_operand_p = (which != 3);
 
       /* Implementable with shufps or pshufd.  */
-      if (d.one_operand_p && (d.vmode == V4SFmode || d.vmode == V4SImode))
+      if (d.one_operand_p
+	  && (d.vmode == V4SFmode
+	      || d.vmode == V4SImode || d.vmode == V2SImode))
 	return true;
 
       /* Otherwise we have to go through the motions and see if we can