static bool
propagate_rtx_1 (rtx *px, rtx old_rtx, rtx new_rtx, int flags)
{
rtx x = *px, tem = NULL_RTX, op0, op1, op2;
enum rtx_code code = GET_CODE (x);
machine_mode mode = GET_MODE (x);
machine_mode op_mode;
bool can_appear = (flags & PR_CAN_APPEAR) != 0;
bool valid_ops = true;
if (!(flags & PR_HANDLE_MEM) && MEM_P (x) && !MEM_READONLY_P (x))
{
/* If unsafe, change MEMs to CLOBBERs or SCRATCHes (to preserve whether
they have side effects or not). */
*px = (side_effects_p (x)
? gen_rtx_CLOBBER (GET_MODE (x), const0_rtx)
: gen_rtx_SCRATCH (GET_MODE (x)));
return false;
}
/* If X is OLD_RTX, return NEW_RTX. But not if replacing only within an
address, and we are *not* inside one. */
if (x == old_rtx)
{
*px = new_rtx;
return can_appear;
}
/* If this is an expression, try recursive substitution. */
switch (GET_RTX_CLASS (code))
{
case RTX_UNARY:
op0 = XEXP (x, 0);
op_mode = GET_MODE (op0);
valid_ops &= propagate_rtx_1 (&op0, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0))
return true;
tem = simplify_gen_unary (code, mode, op0, op_mode);
break;
case RTX_BIN_ARITH:
case RTX_COMM_ARITH:
op0 = XEXP (x, 0);
op1 = XEXP (x, 1);
valid_ops &= propagate_rtx_1 (&op0, old_rtx, new_rtx, flags);
valid_ops &= propagate_rtx_1 (&op1, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0) && op1 == XEXP (x, 1))
return true;
tem = simplify_gen_binary (code, mode, op0, op1);
break;
case RTX_COMPARE:
case RTX_COMM_COMPARE:
op0 = XEXP (x, 0);
op1 = XEXP (x, 1);
op_mode = GET_MODE (op0) != VOIDmode ? GET_MODE (op0) : GET_MODE (op1);
valid_ops &= propagate_rtx_1 (&op0, old_rtx, new_rtx, flags);
valid_ops &= propagate_rtx_1 (&op1, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0) && op1 == XEXP (x, 1))
return true;
tem = simplify_gen_relational (code, mode, op_mode, op0, op1);
break;
case RTX_TERNARY:
case RTX_BITFIELD_OPS:
op0 = XEXP (x, 0);
op1 = XEXP (x, 1);
op2 = XEXP (x, 2);
op_mode = GET_MODE (op0);
valid_ops &= propagate_rtx_1 (&op0, old_rtx, new_rtx, flags);
valid_ops &= propagate_rtx_1 (&op1, old_rtx, new_rtx, flags);
valid_ops &= propagate_rtx_1 (&op2, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0) && op1 == XEXP (x, 1) && op2 == XEXP (x, 2))
return true;
if (op_mode == VOIDmode)
op_mode = GET_MODE (op0);
tem = simplify_gen_ternary (code, mode, op_mode, op0, op1, op2);
break;
case RTX_EXTRA:
/* The only case we try to handle is a SUBREG. */
if (code == SUBREG)
{
op0 = XEXP (x, 0);
valid_ops &= propagate_rtx_1 (&op0, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0))
return true;
tem = simplify_gen_subreg (mode, op0, GET_MODE (SUBREG_REG (x)),
SUBREG_BYTE (x));
}
break;
case RTX_OBJ:
if (code == MEM && x != new_rtx)
{
rtx new_op0;
op0 = XEXP (x, 0);
/* There are some addresses that we cannot work on. */
if (!can_simplify_addr (op0))
return true;
op0 = new_op0 = targetm.delegitimize_address (op0);
valid_ops &= propagate_rtx_1 (&new_op0, old_rtx, new_rtx,
flags | PR_CAN_APPEAR);
/* Dismiss transformation that we do not want to carry on. */
if (!valid_ops
|| new_op0 == op0
|| !(GET_MODE (new_op0) == GET_MODE (op0)
|| GET_MODE (new_op0) == VOIDmode))
return true;
canonicalize_address (new_op0);
/* Copy propagations are always ok. Otherwise check the costs. */
if (!(REG_P (old_rtx) && REG_P (new_rtx))
&& !should_replace_address (op0, new_op0, GET_MODE (x),
MEM_ADDR_SPACE (x),
flags & PR_OPTIMIZE_FOR_SPEED))
return true;
tem = replace_equiv_address_nv (x, new_op0);
}
else if (code == LO_SUM)
{
op0 = XEXP (x, 0);
op1 = XEXP (x, 1);
/* The only simplification we do attempts to remove references to op0
or make it constant -- in both cases, op0's invalidity will not
make the result invalid. */
propagate_rtx_1 (&op0, old_rtx, new_rtx, flags | PR_CAN_APPEAR);
valid_ops &= propagate_rtx_1 (&op1, old_rtx, new_rtx, flags);
if (op0 == XEXP (x, 0) && op1 == XEXP (x, 1))
return true;
/* (lo_sum (high x) x) -> x */
if (GET_CODE (op0) == HIGH && rtx_equal_p (XEXP (op0, 0), op1))
tem = op1;
else
tem = gen_rtx_LO_SUM (mode, op0, op1);
/* OP1 is likely not a legitimate address, otherwise there would have
been no LO_SUM. We want it to disappear if it is invalid, return
false in that case. */
return memory_address_p (mode, tem);
}
else if (code == REG)
{
if (rtx_equal_p (x, old_rtx))
{
*px = new_rtx;
return can_appear;
}
}
break;
default:
break;
}
/* No change, no trouble. */
if (tem == NULL_RTX)
return true;
*px = tem;
/* Allow replacements that simplify operations on a vector or complex
value to a component. The most prominent case is
(subreg ([vec_]concat ...)). */
if (REG_P (tem) && !HARD_REGISTER_P (tem)
&& (VECTOR_MODE_P (GET_MODE (new_rtx))
|| COMPLEX_MODE_P (GET_MODE (new_rtx)))
&& GET_MODE (tem) == GET_MODE_INNER (GET_MODE (new_rtx)))
return true;
/* The replacement we made so far is valid, if all of the recursive
replacements were valid, or we could simplify everything to
a constant. */
return valid_ops || can_appear || CONSTANT_P (tem);
}
static bool
doloop_optimize (struct loop *loop)
{
enum machine_mode mode;
rtx doloop_seq, doloop_pat, doloop_reg;
rtx iterations, count;
rtx iterations_max;
rtx start_label;
rtx condition;
unsigned level, est_niter;
struct niter_desc *desc;
unsigned word_mode_size;
unsigned HOST_WIDE_INT word_mode_max;
if (dump_file)
fprintf (dump_file, "Doloop: Processing loop %d.\n", loop->num);
/* APPLE LOCAL begin lno */
/* Ignore large loops. */
if (loop->ninsns > (unsigned) PARAM_VALUE (PARAM_MAX_DOLOOP_INSNS))
{
if (dump_file)
fprintf (dump_file,
"Doloop: The loop is too large.\n");
return false;
}
/* APPLE LOCAL end lno */
iv_analysis_loop_init (loop);
/* Find the simple exit of a LOOP. */
desc = get_simple_loop_desc (loop);
/* Check that loop is a candidate for a low-overhead looping insn. */
if (!doloop_valid_p (loop, desc))
{
if (dump_file)
fprintf (dump_file,
"Doloop: The loop is not suitable.\n");
return false;
}
mode = desc->mode;
est_niter = 3;
if (desc->const_iter)
est_niter = desc->niter;
/* If the estimate on number of iterations is reliable (comes from profile
feedback), use it. Do not use it normally, since the expected number
of iterations of an unrolled loop is 2. */
if (loop->header->count)
est_niter = expected_loop_iterations (loop);
if (est_niter < 3)
{
if (dump_file)
fprintf (dump_file,
"Doloop: Too few iterations (%u) to be profitable.\n",
est_niter);
return false;
}
count = copy_rtx (desc->niter_expr);
iterations = desc->const_iter ? desc->niter_expr : const0_rtx;
iterations_max = GEN_INT (desc->niter_max);
level = get_loop_level (loop) + 1;
/* Generate looping insn. If the pattern FAILs then give up trying
to modify the loop since there is some aspect the back-end does
not like. */
start_label = block_label (desc->in_edge->dest);
doloop_reg = gen_reg_rtx (mode);
doloop_seq = gen_doloop_end (doloop_reg, iterations, iterations_max,
GEN_INT (level), start_label);
word_mode_size = GET_MODE_BITSIZE (word_mode);
word_mode_max
= ((unsigned HOST_WIDE_INT) 1 << (word_mode_size - 1) << 1) - 1;
if (! doloop_seq
&& mode != word_mode
/* Before trying mode different from the one in that # of iterations is
computed, we must be sure that the number of iterations fits into
the new mode. */
&& (word_mode_size >= GET_MODE_BITSIZE (mode)
|| desc->niter_max <= word_mode_max))
{
if (word_mode_size > GET_MODE_BITSIZE (mode))
{
count = simplify_gen_unary (ZERO_EXTEND, word_mode,
count, mode);
iterations = simplify_gen_unary (ZERO_EXTEND, word_mode,
iterations, mode);
iterations_max = simplify_gen_unary (ZERO_EXTEND, word_mode,
iterations_max, mode);
}
else
{
count = lowpart_subreg (word_mode, count, mode);
iterations = lowpart_subreg (word_mode, iterations, mode);
iterations_max = lowpart_subreg (word_mode, iterations_max, mode);
}
PUT_MODE (doloop_reg, word_mode);
doloop_seq = gen_doloop_end (doloop_reg, iterations, iterations_max,
GEN_INT (level), start_label);
}
if (! doloop_seq)
{
if (dump_file)
fprintf (dump_file,
"Doloop: Target unwilling to use doloop pattern!\n");
return false;
}
/* If multiple instructions were created, the last must be the
jump instruction. Also, a raw define_insn may yield a plain
pattern. */
doloop_pat = doloop_seq;
if (INSN_P (doloop_pat))
{
while (NEXT_INSN (doloop_pat) != NULL_RTX)
doloop_pat = NEXT_INSN (doloop_pat);
if (JUMP_P (doloop_pat))
doloop_pat = PATTERN (doloop_pat);
else
doloop_pat = NULL_RTX;
}
if (! doloop_pat
|| ! (condition = doloop_condition_get (doloop_pat)))
{
if (dump_file)
fprintf (dump_file, "Doloop: Unrecognizable doloop pattern!\n");
return false;
}
doloop_modify (loop, desc, doloop_seq, condition, count);
return true;
}