i386: Split V2HImode *punpckwd to SSE instruction [PR101058]

V2HImode *punpckwd should not be split to the insn that depends on
TARGET_MMX_WITH_SSE, since the later is disabled on 32bit targets.

Also return true early from ix86_vectorize_vec_perm_const when testing
with V2HI mode.  *punpckwd can be used to implement all permutations.

2021-06-14  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/101058
	* config/i386/i386-expand.c (ix86_vectorize_vec_perm_const):
	Return true early when testing with V2HImode.
	* config/i386/mmx.md (*punpckwd): Split to sse2_pshuflw_1.

gcc/testsuite/

	PR target/101058
	* gcc.target/i386/pr101058.c: New test.

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 6e33f6f81962af015bc537ba7e165d1c08509328..dee3df2e3a012676ed97f29e829e7c2f954cb9ab 100644 (file)
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -20446,9 +20446,12 @@ ix86_vectorize_vec_perm_const (machine_mode vmode, rtx target, rtx op0,
        return false;
       break;
     case E_V2HImode:
-       if (!TARGET_SSE2)
-         return false;
-       break;
+      if (!TARGET_SSE2)
+       return false;
+      /* All implementable with *punpckwd.  */
+      if (d.testing_p)
+       return true;
+      break;
     case E_V2DImode:
     case E_V2DFmode:
       if (!TARGET_SSE)

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index f9e7d2786c6c2e1340d8d4a597379ba9d8eef168..1a9e7b024dd91c6ff61459e426db3a0c70c5c0d1 100644 (file)
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -3368,16 +3368,18 @@
          (vec_concat:V4HI
            (match_operand:V2HI 1 "register_operand" "0,Yw")
            (match_operand:V2HI 2 "register_operand" "x,Yw"))
-          (parallel [(match_operand 3 "const_0_to_3_operand")
-                     (match_operand 4 "const_0_to_3_operand")])))]
+         (parallel [(match_operand 3 "const_0_to_3_operand")
+                    (match_operand 4 "const_0_to_3_operand")])))]
   "TARGET_SSE2"
   "#"
   "&& reload_completed"
   [(set (match_dup 5)
-        (vec_select:V4HI
+       (vec_select:V8HI
          (match_dup 5)
           (parallel [(match_dup 3) (match_dup 4)
-                     (const_int 0) (const_int 0)])))]
+                     (const_int 2) (const_int 3)
+                     (const_int 4) (const_int 5)
+                     (const_int 6) (const_int 7)])))]
 {
   rtx dest = lowpart_subreg (V8HImode, operands[0], V2HImode);
   rtx op1 = lowpart_subreg (V8HImode, operands[1], V2HImode);
@@ -3395,8 +3397,7 @@
 
   operands[3] = GEN_INT (sel0);
   operands[4] = GEN_INT (sel1);
-
-  operands[5] = lowpart_subreg (V4HImode, dest, V8HImode);
+  operands[5] = dest;
 }
   [(set_attr "isa" "noavx,avx")
    (set_attr "type" "sselog")

diff --git a/gcc/testsuite/gcc.target/i386/pr101058.c b/gcc/testsuite/gcc.target/i386/pr101058.c
new file mode 100644 (file)
index 0000000..a2b251c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr101058.c
@@ -0,0 +1,12 @@
+/* PR target/101058 */
+/* { dg-do compile } */
+/* { dg-options "-O3 -msse2 -mno-mmx" } */
+
+short add90Hybrid_a_1;
+short *add90Hybrid_b, *add90Hybrid_c, *add90Hybrid_d;
+void add90Hybrid() {
+  for (int i; i < 200; i += 2) {
+    add90Hybrid_c[i] = add90Hybrid_b[i];
+    add90Hybrid_d[i] = add90Hybrid_a_1 - add90Hybrid_b[i + 1];
+  }
+}