internal-fn: Avoid dropping the lhs of some calls [PR94941]

create_output_operand coerces an output operand to the insn's
predicates, using a suggested rtx location if convenient.
But if that rtx location is actually required rather than
optional, the builder of the insn has to emit a move afterwards.

(We could instead add a new interface that does this automatically,
but that's future work.)

This PR shows that we were failing to emit the move for some of the
vector load internal functions.  I think there are other routines in
internal-fn.c that potentially have the same problem, but this patch is
supposed to be a conservative subset suitable for backporting to GCC 10.

2020-05-04  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	PR middle-end/94941
	* internal-fn.c (expand_load_lanes_optab_fn): Emit a move if the
	chosen lhs is different from the gcall lhs.
	(expand_mask_load_optab_fn): Likewise.
	(expand_gather_load_optab_fn): Likewise.

gcc/testsuite/
	PR middle-end/94941
	* gcc.target/aarch64/sve/acle/general/unoptimized_1.c: New test.

gcc/ChangeLog

+2020-05-04  Richard Sandiford  <richard.sandiford@arm.com>
+
+	PR middle-end/94941
+	* internal-fn.c (expand_load_lanes_optab_fn): Emit a move if the
+	chosen lhs is different from the gcall lhs.
+	(expand_mask_load_optab_fn): Likewise.
+	(expand_gather_load_optab_fn): Likewise.
+
 2020-05-04  Marek Polacek  <polacek@redhat.com>
 
 	Revert:

gcc/internal-fn.c

@@ -167,6 +167,8 @@ expand_load_lanes_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
   create_output_operand (&ops[0], target, TYPE_MODE (type));
   create_fixed_operand (&ops[1], mem);
   expand_insn (get_multi_vector_move (type, optab), 2, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* Expand STORE_LANES call STMT using optab OPTAB.  */
@@ -2507,6 +2509,8 @@ expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
   create_fixed_operand (&ops[1], mem);
   create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
   expand_insn (icode, 3, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 #define expand_mask_load_lanes_optab_fn expand_mask_load_optab_fn
@@ -2827,6 +2831,8 @@ expand_gather_load_optab_fn (internal_fn, gcall *stmt, direct_optab optab)
   insn_code icode = convert_optab_handler (optab, TYPE_MODE (TREE_TYPE (lhs)),
 					   TYPE_MODE (TREE_TYPE (offset)));
   expand_insn (icode, i, ops);
+  if (!rtx_equal_p (lhs_rtx, ops[0].value))
+    emit_move_insn (lhs_rtx, ops[0].value);
 }
 
 /* Expand DIVMOD() using:

gcc/testsuite/ChangeLog

+2020-05-04  Richard Sandiford  <richard.sandiford@arm.com>
+
+	PR middle-end/94941
+	* gcc.target/aarch64/sve/acle/general/unoptimized_1.c: New test.
+
 2020-04-30  Martin Jambor  <mjambor@suse.cz>
 
 	PR ipa/94856

gcc/testsuite/gcc.target/aarch64/sve/acle/general/unoptimized_1.c

+/* { dg-do run { target aarch64_sve_hw } } */
+
+#include <arm_sve.h>
+
+svfloat32_t
+foo (float *ptr)
+{
+  svbool_t pg = svptrue_pat_b32 (SV_VL1);
+  svfloat32_t res = svld1 (pg, ptr);
+  return res;
+}
+
+int
+main (void)
+{
+  svbool_t pg = svptrue_pat_b32 (SV_VL1);
+  float x[1] = { 1 };
+  if (svptest_any (pg, svcmpne (pg, foo (x), 1.0)))
+    __builtin_abort ();
+  return 0;
+}