i386: Improve single operand AVX512F permutations [PR80355]

On the following testcase we emit
	vmovdqa32	.LC0(%rip), %zmm1
	vpermd	%zmm0, %zmm1, %zmm0
and
	vmovdqa64	.LC1(%rip), %zmm1
	vpermq	%zmm0, %zmm1, %zmm0
instead of
	vshufi32x4	$78, %zmm0, %zmm0, %zmm0
and
	vshufi64x2	$78, %zmm0, %zmm0, %zmm0
we can emit with the patch.  We have patterns that match two argument
permutations for vshuf[if]*, but for one argument it doesn't trigger.
Either we can add two patterns for that, or we would need to add another
routine to i386-expand.c that would transform under certain condition
these cases to the two argument vshuf*, doing it in sse.md looked simpler.
We don't need this for 32-byte vectors, we already emit single insn
permutation that doesn't need memory op there.

2021-08-10  Jakub Jelinek  <jakub@redhat.com>

	PR target/80355
	* config/i386/sse.md (*avx512f_shuf_<shuffletype>64x2_1<mask_name>_1,
	*avx512f_shuf_<shuffletype>32x4_1<mask_name>_1): New define_insn
	patterns.

	* gcc.target/i386/avx512f-pr80355-1.c: New test.

2 files changed, 107 insertions, 0 deletions

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 2b0d10e..3957c86 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -15336,6 +15336,42 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_insn "*avx512f_shuf_<shuffletype>64x2_1<mask_name>_1"
+  [(set (match_operand:V8FI 0 "register_operand" "=v")
+	(vec_select:V8FI
+	  (match_operand:V8FI 1 "register_operand" "v")
+	  (parallel [(match_operand 2 "const_0_to_7_operand")
+		     (match_operand 3 "const_0_to_7_operand")
+		     (match_operand 4 "const_0_to_7_operand")
+		     (match_operand 5 "const_0_to_7_operand")
+		     (match_operand 6 "const_0_to_7_operand")
+		     (match_operand 7 "const_0_to_7_operand")
+		     (match_operand 8 "const_0_to_7_operand")
+		     (match_operand 9 "const_0_to_7_operand")])))]
+  "TARGET_AVX512F
+   && (INTVAL (operands[2]) & 1) == 0
+   && INTVAL (operands[2]) == INTVAL (operands[3]) - 1
+   && (INTVAL (operands[4]) & 1) == 0
+   && INTVAL (operands[4]) == INTVAL (operands[5]) - 1
+   && (INTVAL (operands[6]) & 1) == 0
+   && INTVAL (operands[6]) == INTVAL (operands[7]) - 1
+   && (INTVAL (operands[8]) & 1) == 0
+   && INTVAL (operands[8]) == INTVAL (operands[9]) - 1"
+{
+  int mask;
+  mask = INTVAL (operands[2]) / 2;
+  mask |= INTVAL (operands[4]) / 2 << 2;
+  mask |= INTVAL (operands[6]) / 2 << 4;
+  mask |= INTVAL (operands[8]) / 2 << 6;
+  operands[2] = GEN_INT (mask);
+
+  return "vshuf<shuffletype>64x2\t{%2, %1, %1, %0<mask_operand10>|%0<mask_operand10>, %1, %1, %2}";
+}
+  [(set_attr "type" "sselog")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
 (define_expand "avx512vl_shuf_<shuffletype>32x4_mask"
   [(match_operand:VI4F_256 0 "register_operand")
    (match_operand:VI4F_256 1 "register_operand")
@@ -15482,6 +15518,58 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_insn "*avx512f_shuf_<shuffletype>32x4_1<mask_name>_1"
+  [(set (match_operand:V16FI 0 "register_operand" "=v")
+	(vec_select:V16FI
+	  (match_operand:V16FI 1 "register_operand" "v")
+	  (parallel [(match_operand 2 "const_0_to_15_operand")
+		     (match_operand 3 "const_0_to_15_operand")
+		     (match_operand 4 "const_0_to_15_operand")
+		     (match_operand 5 "const_0_to_15_operand")
+		     (match_operand 6 "const_0_to_15_operand")
+		     (match_operand 7 "const_0_to_15_operand")
+		     (match_operand 8 "const_0_to_15_operand")
+		     (match_operand 9 "const_0_to_15_operand")
+		     (match_operand 10 "const_0_to_15_operand")
+		     (match_operand 11 "const_0_to_15_operand")
+		     (match_operand 12 "const_0_to_15_operand")
+		     (match_operand 13 "const_0_to_15_operand")
+		     (match_operand 14 "const_0_to_15_operand")
+		     (match_operand 15 "const_0_to_15_operand")
+		     (match_operand 16 "const_0_to_15_operand")
+		     (match_operand 17 "const_0_to_15_operand")])))]
+  "TARGET_AVX512F
+   && (INTVAL (operands[2]) & 3) == 0
+   && INTVAL (operands[2]) == INTVAL (operands[3]) - 1
+   && INTVAL (operands[2]) == INTVAL (operands[4]) - 2
+   && INTVAL (operands[2]) == INTVAL (operands[5]) - 3
+   && (INTVAL (operands[6]) & 3) == 0
+   && INTVAL (operands[6]) == INTVAL (operands[7]) - 1
+   && INTVAL (operands[6]) == INTVAL (operands[8]) - 2
+   && INTVAL (operands[6]) == INTVAL (operands[9]) - 3
+   && (INTVAL (operands[10]) & 3) == 0
+   && INTVAL (operands[10]) == INTVAL (operands[11]) - 1
+   && INTVAL (operands[10]) == INTVAL (operands[12]) - 2
+   && INTVAL (operands[10]) == INTVAL (operands[13]) - 3
+   && (INTVAL (operands[14]) & 3) == 0
+   && INTVAL (operands[14]) == INTVAL (operands[15]) - 1
+   && INTVAL (operands[14]) == INTVAL (operands[16]) - 2
+   && INTVAL (operands[14]) == INTVAL (operands[17]) - 3"
+{
+  int mask;
+  mask = INTVAL (operands[2]) / 4;
+  mask |= INTVAL (operands[6]) / 4 << 2;
+  mask |= INTVAL (operands[10]) / 4 << 4;
+  mask |= INTVAL (operands[14]) / 4 << 6;
+  operands[2] = GEN_INT (mask);
+
+  return "vshuf<shuffletype>32x4\t{%2, %1, %1, %0<mask_operand18>|%0<mask_operand18>, %1, %1, %2}";
+}
+  [(set_attr "type" "sselog")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
 (define_expand "avx512f_pshufdv3_mask"
   [(match_operand:V16SI 0 "register_operand")
    (match_operand:V16SI 1 "nonimmediate_operand")
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-pr80355-1.c b/gcc/testsuite/gcc.target/i386/avx512f-pr80355-1.c
new file mode 100644
index 0000000..b1ff010
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-pr80355-1.c
@@ -0,0 +1,19 @@
+/* PR target/80355 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mno-avx512vl -mno-avx512dq" } */
+/* { dg-final { scan-assembler "\tvshufi32x4\t" } } */
+/* { dg-final { scan-assembler "\tvshufi64x2\t" } } */
+
+typedef long long V __attribute__((vector_size (64)));
+typedef int W __attribute__((vector_size (64)));
+
+W
+f0 (W x)
+{
+  return __builtin_shuffle (x, (W) { 8, 9, 10, 11, 12, 13, 14, 15, 0, 1, 2, 3, 4, 5, 6, 7 });
+}
+V
+f1 (V x)
+{
+  return __builtin_shuffle (x, (V) { 4, 5, 6, 7, 0, 1, 2, 3 });
+}