Hi All,

Says what it does on the tin.  In case some operations form in RTL due to
a split, combine or any RTL pass then still try to recognize them.

Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.

Ok for master?

Thanks,
Tamar

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md: Add new peepholes.
	* config/aarch64/aarch64.cc (aarch_macro_fusion_pair_p): Schedule
	sequential PLUS operations next to each other to increase the chance of
	forming pairwise operations.

--- inline copy of patch -- 
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 93a2888f567460ad10ec050ea7d4f701df4729d1..20e9adbf7b9b484f9a19f0c62770930dc3941eb2 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -3425,6 +3425,22 @@ (define_insn "aarch64_faddp<mode>"
   [(set_attr "type" "neon_fp_reduc_add_<stype><q>")]
 )
 
+(define_peephole2
+  [(set (match_operand:<VEL> 0 "register_operand")
+	(vec_select:<VEL>
+	  (match_operand:VHSDF 1 "register_operand")
+	  (parallel [(match_operand 2 "const_int_operand")])))
+   (set (match_operand:<VEL> 3 "register_operand")
+	(plus:<VEL>
+	  (match_dup 0)
+	  (match_operand:<VEL> 5 "register_operand")))]
+  "TARGET_SIMD
+   && ENDIAN_LANE_N (<nunits>, INTVAL (operands[2])) == 1
+   && REGNO (operands[5]) == REGNO (operands[1])
+   && peep2_reg_dead_p (2, operands[0])"
+  [(set (match_dup 3) (unspec:<VEL> [(match_dup 1)] UNSPEC_FADDV))]
+)
+
 (define_insn "reduc_plus_scal_<mode>"
  [(set (match_operand:<VEL> 0 "register_operand" "=w")
        (unspec:<VEL> [(match_operand:VDQV 1 "register_operand" "w")]
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index f3bd71c9f10868f9e6ab50d8e36ed3ee3d48ac22..4023b1729d92bf37f5a2fc8fc8cd3a5194532079 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -25372,6 +25372,29 @@ aarch_macro_fusion_pair_p (rtx_insn *prev, rtx_insn *curr)
         }
     }
 
+  /* Try to schedule vec_select and add together so the peephole works.  */
+  if (simple_sets_p && REG_P (SET_DEST (prev_set)) && REG_P (SET_DEST (curr_set))
+      && GET_CODE (SET_SRC (prev_set)) == VEC_SELECT && GET_CODE (SET_SRC (curr_set)) == PLUS)
+  {
+    /* We're trying to match:
+       prev (vec_select) == (set (reg r0)
+				 (vec_select (reg r1) n)
+       curr (plus) == (set (reg r2)
+			   (plus (reg r0) (reg r1)))  */
+    rtx prev_src = SET_SRC (prev_set);
+    rtx curr_src = SET_SRC (curr_set);
+    rtx parallel = XEXP (prev_src, 1);
+    auto idx
+      = ENDIAN_LANE_N (GET_MODE_NUNITS (GET_MODE (XEXP (prev_src, 0))), 1);
+    if (GET_CODE (parallel) == PARALLEL
+	&& XVECLEN (parallel, 0) == 1
+	&& known_eq (INTVAL (XVECEXP (parallel, 0, 0)), idx)
+	&& GET_MODE (SET_DEST (prev_set)) == GET_MODE (curr_src)
+	&& GET_MODE_INNER (GET_MODE (XEXP (prev_src, 0)))
+	    == GET_MODE (XEXP (curr_src, 1)))
+      return true;
+  }
+
   /* Fuse compare (CMP/CMN/TST/BICS) and conditional branch.  */
   if (aarch64_fusion_enabled_p (AARCH64_FUSE_CMP_BRANCH)
       && prev_set && curr_set && any_condjump_p (curr)




--