static void
expand_one_stack_var_at (tree decl, HOST_WIDE_INT offset)
{
HOST_WIDE_INT align;
rtx x;
/* If this fails, we've overflowed the stack frame. Error nicely? */
gcc_assert (offset == trunc_int_for_mode (offset, Pmode));
x = plus_constant (virtual_stack_vars_rtx, offset);
x = gen_rtx_MEM (DECL_MODE (decl), x);
/* Set alignment we actually gave this decl. */
offset -= frame_phase;
align = offset & -offset;
align *= BITS_PER_UNIT;
if (align > STACK_BOUNDARY || align == 0)
align = STACK_BOUNDARY;
DECL_ALIGN (decl) = align;
DECL_USER_ALIGN (decl) = 0;
set_mem_attributes (x, decl, true);
SET_DECL_RTL (decl, x);
}
void
expand_builtin_cilk_detach (tree exp)
{
rtx_insn *insn;
tree fptr = get_frame_arg (exp);
if (fptr == NULL_TREE)
return;
tree parent = cilk_dot (fptr, CILK_TI_FRAME_PARENT, 0);
tree worker = cilk_dot (fptr, CILK_TI_FRAME_WORKER, 0);
tree tail = cilk_arrow (worker, CILK_TI_WORKER_TAIL, 1);
rtx wreg = expand_expr (worker, NULL_RTX, Pmode, EXPAND_NORMAL);
if (GET_CODE (wreg) != REG)
wreg = copy_to_reg (wreg);
rtx preg = expand_expr (parent, NULL_RTX, Pmode, EXPAND_NORMAL);
/* TMP <- WORKER.TAIL
*TMP <- PARENT
TMP <- TMP + 1
WORKER.TAIL <- TMP */
HOST_WIDE_INT worker_tail_offset =
tree_to_shwi (DECL_FIELD_OFFSET (cilk_trees[CILK_TI_WORKER_TAIL])) +
tree_to_shwi (DECL_FIELD_BIT_OFFSET (cilk_trees[CILK_TI_WORKER_TAIL])) /
BITS_PER_UNIT;
rtx tmem0 = gen_rtx_MEM (Pmode,
plus_constant (Pmode, wreg, worker_tail_offset));
set_mem_attributes (tmem0, tail, 0);
MEM_NOTRAP_P (tmem0) = 1;
gcc_assert (MEM_VOLATILE_P (tmem0));
rtx treg = copy_to_mode_reg (Pmode, tmem0);
rtx tmem1 = gen_rtx_MEM (Pmode, treg);
set_mem_attributes (tmem1, TREE_TYPE (TREE_TYPE (tail)), 0);
MEM_NOTRAP_P (tmem1) = 1;
emit_move_insn (tmem1, preg);
emit_move_insn (treg, plus_constant (Pmode, treg, GET_MODE_SIZE (Pmode)));
/* There is a release barrier (st8.rel, membar #StoreStore,
sfence, lwsync, etc.) between the two stores. On x86
normal volatile stores have proper semantics; the sfence
would only be needed for nontemporal stores (which we
could generate using the storent optab, for no benefit
in this case).
The predicate may return false even for a REG if this is
the limited release operation that only stores 0. */
enum insn_code icode = direct_optab_handler (sync_lock_release_optab, Pmode);
if (icode != CODE_FOR_nothing
&& insn_data[icode].operand[1].predicate (treg, Pmode)
&& (insn = GEN_FCN (icode) (tmem0, treg)) != NULL_RTX)
emit_insn (insn);
else
emit_move_insn (tmem0, treg);
/* The memory barrier inserted above should not prevent
the load of flags from being moved before the stores,
but in practice it does because it is implemented with
unspec_volatile. In-order RISC machines should
explicitly load flags earlier. */
tree flags = cilk_dot (fptr, CILK_TI_FRAME_FLAGS, 0);
expand_expr (build2 (MODIFY_EXPR, void_type_node, flags,
build2 (BIT_IOR_EXPR, TREE_TYPE (flags), flags,
build_int_cst (TREE_TYPE (flags),
CILK_FRAME_DETACHED))),
const0_rtx, VOIDmode, EXPAND_NORMAL);
}
