Simplify vec_merge of vec_duplicate with const_vector

I'm trying to improve some of the RTL-level handling of vector lane operations on aarch64 and that
involves dealing with a lot of vec_merge operations. One simplification that I noticed missing
from simplify-rtx are combinations of vec_merge with vec_duplicate.
In this particular case:
(vec_merge (vec_duplicate (X)) (const_vector [A, B]) (const_int N))

which can be replaced with

(vec_concat (X) (B)) if N == 1 (0b01) or
(vec_concat (A) (X)) if N == 2 (0b10).

For the aarch64 testcase in this patch this simplifications allows us to try to combine:
(set (reg:V2DI 77 [ x ])
    (vec_concat:V2DI (mem:DI (reg:DI 0 x0 [ y ]) [1 *y_3(D)+0 S8 A64])
        (const_int 0 [0])))

instead of the more complex:
(set (reg:V2DI 77 [ x ])
    (vec_merge:V2DI (vec_duplicate:V2DI (mem:DI (reg:DI 0 x0 [ y ]) [1 *y_3(D)+0 S8 A64]))
        (const_vector:V2DI [
                (const_int 0 [0])
                (const_int 0 [0])
            ])
        (const_int 1 [0x1])))


For the simplified form above we already have an aarch64 pattern: *aarch64_combinez<mode> which
is missing a DI/DFmode version due to an oversight, so this patch extends that pattern as well to
use the VDC mode iterator that includes DI and DFmode (as well as V2HF which VD_BHSI was missing).
The aarch64 hunk is needed to see the benefit of the simplify-rtx.c hunk, so I didn't split them
into separate patches.

Before this for the testcase we'd generate:
construct_lanedi:
        movi    v0.4s, 0
        ldr     x0, [x0]
        ins     v0.d[0], x0
        ret

construct_lanedf:
        movi    v0.2d, 0
        ldr     d1, [x0]
        ins     v0.d[0], v1.d[0]
        ret

but now we can generate:
construct_lanedi:
        ldr     d0, [x0]
        ret

construct_lanedf:
        ldr     d0, [x0]
        ret

Bootstrapped and tested on aarch64-none-linux-gnu.


	* simplify-rtx.c (simplify_ternary_operation, VEC_MERGE):
	Simplify vec_merge of vec_duplicate and const_vector.
	* config/aarch64/predicates.md (aarch64_simd_or_scalar_imm_zero):
	New predicate.
	* config/aarch64/aarch64-simd.md (*aarch64_combinez<mode>): Use VDC
	mode iterator.  Update predicate on operand 1 to
	handle non-const_vec constants.  Delete constraints.
	(*aarch64_combinez_be<mode>): Likewise for operand 2.

	* gcc.target/aarch64/construct_lane_zero_1.c: New test.

From-SVN: r254548

gcc/ChangeLog

+2017-11-08  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+	* simplify-rtx.c (simplify_ternary_operation, VEC_MERGE):
+	Simplify vec_merge of vec_duplicate and const_vector.
+	* config/aarch64/predicates.md (aarch64_simd_or_scalar_imm_zero):
+	New predicate.
+	* config/aarch64/aarch64-simd.md (*aarch64_combinez<mode>): Use VDC
+	mode iterator.  Update predicate on operand 1 to
+	handle non-const_vec constants.  Delete constraints.
+	(*aarch64_combinez_be<mode>): Likewise for operand 2.
+
 2017-11-08  Jakub Jelinek  <jakub@redhat.com>
 
 	PR tree-optimization/78821

gcc/config/aarch64/aarch64-simd.md

@@ -2940,9 +2940,9 @@
 
 (define_insn "*aarch64_combinez<mode>"
   [(set (match_operand:<VDBL> 0 "register_operand" "=w,w,w")
-        (vec_concat:<VDBL>
-	   (match_operand:VD_BHSI 1 "general_operand" "w,?r,m")
-	   (match_operand:VD_BHSI 2 "aarch64_simd_imm_zero" "Dz,Dz,Dz")))]
+	(vec_concat:<VDBL>
+	  (match_operand:VDC 1 "general_operand" "w,?r,m")
+	  (match_operand:VDC 2 "aarch64_simd_or_scalar_imm_zero")))]
   "TARGET_SIMD && !BYTES_BIG_ENDIAN"
   "@
    mov\\t%0.8b, %1.8b
@@ -2956,8 +2956,8 @@
 (define_insn "*aarch64_combinez_be<mode>"
   [(set (match_operand:<VDBL> 0 "register_operand" "=w,w,w")
         (vec_concat:<VDBL>
-	   (match_operand:VD_BHSI 2 "aarch64_simd_imm_zero" "Dz,Dz,Dz")
-	   (match_operand:VD_BHSI 1 "general_operand" "w,?r,m")))]
+	  (match_operand:VDC 2 "aarch64_simd_or_scalar_imm_zero")
+	  (match_operand:VDC 1 "general_operand" "w,?r,m")))]
   "TARGET_SIMD && BYTES_BIG_ENDIAN"
   "@
    mov\\t%0.8b, %1.8b

gcc/config/aarch64/predicates.md

@@ -364,6 +364,9 @@
   return aarch64_simd_imm_zero_p (op, mode);
 })
 
+(define_special_predicate "aarch64_simd_or_scalar_imm_zero"
+  (match_test "aarch64_simd_imm_zero_p (op, mode)"))
+
 (define_special_predicate "aarch64_simd_imm_minus_one"
   (match_code "const_vector")
 {

gcc/simplify-rtx.c

@@ -5749,6 +5749,22 @@ simplify_ternary_operation (enum rtx_code code, machine_mode mode,
 		    return op1;
 		}
 	    }
+	  /* Replace (vec_merge (vec_duplicate (X)) (const_vector [A, B])
+	     (const_int N))
+	     with (vec_concat (X) (B)) if N == 1 or
+	     (vec_concat (A) (X)) if N == 2.  */
+	  if (GET_CODE (op0) == VEC_DUPLICATE
+	      && GET_CODE (op1) == CONST_VECTOR
+	      && CONST_VECTOR_NUNITS (op1) == 2
+	      && GET_MODE_NUNITS (GET_MODE (op0)) == 2
+	      && IN_RANGE (sel, 1, 2))
+	    {
+	      rtx newop0 = XEXP (op0, 0);
+	      rtx newop1 = CONST_VECTOR_ELT (op1, 2 - sel);
+	      if (sel == 2)
+		std::swap (newop0, newop1);
+	      return simplify_gen_binary (VEC_CONCAT, mode, newop0, newop1);
+	    }
 	}
 
       if (rtx_equal_p (op0, op1)

gcc/testsuite/ChangeLog

+2017-11-08  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+	* gcc.target/aarch64/construct_lane_zero_1.c: New test.
+
 2017-11-08  Ed Schonberg  <schonberg@adacore.com>
 
 	* gnat.dg/delta_aggr.adb: New testcase.

gcc/testsuite/gcc.target/aarch64/construct_lane_zero_1.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+typedef long long v2di __attribute__ ((vector_size (16)));
+typedef double v2df __attribute__ ((vector_size (16)));
+
+v2di
+construct_lanedi (long long *y)
+{
+  v2di x =
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+  { 0, y[0] }
+#else
+  { y[0], 0 }
+#endif
+  ;
+  return x;
+}
+
+v2df
+construct_lanedf (double *y)
+{
+  v2df x =
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+  { 0.0, y[0] }
+#else
+  { y[0], 0.0 }
+#endif
+  ;
+  return x;
+}
+
+/* Check that creating V2DI and V2DF vectors from a lane with a zero
+   makes use of the D-reg LDR rather than doing explicit lane inserts.  */
+
+/* { dg-final { scan-assembler-times "ldr\td\[0-9\]+" 2 } } */
+/* { dg-final { scan-assembler-not "ins\t" } } */