gh-131798: Remove bounds check when indexing into tuples with a constant index (#137607)

* Remove bounds check when indexing into tuples with a constant index

* Add news entry

* fixup after rebase
This commit is contained in:
Tomas R. 2025-12-28 22:06:06 +01:00 committed by GitHub
parent c3febba73b
commit 713684de53
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 1232 additions and 940 deletions

View file

@ -968,9 +968,16 @@ dummy_func(
}
macro(BINARY_OP_SUBSCR_TUPLE_INT) =
_GUARD_TOS_INT + _GUARD_NOS_TUPLE + unused/5 + _BINARY_OP_SUBSCR_TUPLE_INT + _POP_TOP_INT + POP_TOP;
_GUARD_TOS_INT +
_GUARD_NOS_TUPLE +
_GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS +
unused/5 +
_BINARY_OP_SUBSCR_TUPLE_INT +
_POP_TOP_INT +
POP_TOP;
op(_BINARY_OP_SUBSCR_TUPLE_INT, (tuple_st, sub_st -- res, ts, ss)) {
// A guard that checks that the tuple subscript is within bounds
op(_GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS, (tuple_st, sub_st -- tuple_st, sub_st)) {
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
@ -981,7 +988,17 @@ dummy_func(
DEOPT_IF(!_PyLong_IsNonNegativeCompact((PyLongObject *)sub));
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
DEOPT_IF(index >= PyTuple_GET_SIZE(tuple));
}
op(_BINARY_OP_SUBSCR_TUPLE_INT, (tuple_st, sub_st -- res, ts, ss)) {
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
STAT_INC(BINARY_OP, hit);
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
PyObject *res_o = PyTuple_GET_ITEM(tuple, index);
assert(res_o != NULL);
res = PyStackRef_FromPyObjectNew(res_o);

View file

@ -4891,14 +4891,76 @@
break;
}
case _BINARY_OP_SUBSCR_TUPLE_INT_r23: {
case _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS_r02: {
CHECK_CURRENT_CACHED_VALUES(0);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
sub_st = stack_pointer[-1];
tuple_st = stack_pointer[-2];
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
if (!_PyLong_IsNonNegativeCompact((PyLongObject *)sub)) {
UOP_STAT_INC(uopcode, miss);
SET_CURRENT_CACHED_VALUES(0);
JUMP_TO_JUMP_TARGET();
}
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
if (index >= PyTuple_GET_SIZE(tuple)) {
UOP_STAT_INC(uopcode, miss);
SET_CURRENT_CACHED_VALUES(0);
JUMP_TO_JUMP_TARGET();
}
_tos_cache1 = sub_st;
_tos_cache0 = tuple_st;
SET_CURRENT_CACHED_VALUES(2);
stack_pointer += -2;
ASSERT_WITHIN_STACK_BOUNDS(__FILE__, __LINE__);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS_r12: {
CHECK_CURRENT_CACHED_VALUES(1);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef _stack_item_0 = _tos_cache0;
sub_st = _stack_item_0;
tuple_st = stack_pointer[-1];
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
if (!_PyLong_IsNonNegativeCompact((PyLongObject *)sub)) {
UOP_STAT_INC(uopcode, miss);
_tos_cache0 = sub_st;
SET_CURRENT_CACHED_VALUES(1);
JUMP_TO_JUMP_TARGET();
}
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
if (index >= PyTuple_GET_SIZE(tuple)) {
UOP_STAT_INC(uopcode, miss);
_tos_cache0 = sub_st;
SET_CURRENT_CACHED_VALUES(1);
JUMP_TO_JUMP_TARGET();
}
_tos_cache1 = sub_st;
_tos_cache0 = tuple_st;
SET_CURRENT_CACHED_VALUES(2);
stack_pointer += -1;
ASSERT_WITHIN_STACK_BOUNDS(__FILE__, __LINE__);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS_r22: {
CHECK_CURRENT_CACHED_VALUES(2);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef res;
_PyStackRef ts;
_PyStackRef ss;
_PyStackRef _stack_item_0 = _tos_cache0;
_PyStackRef _stack_item_1 = _tos_cache1;
sub_st = _stack_item_1;
@ -4922,7 +4984,133 @@
SET_CURRENT_CACHED_VALUES(2);
JUMP_TO_JUMP_TARGET();
}
_tos_cache1 = sub_st;
_tos_cache0 = tuple_st;
SET_CURRENT_CACHED_VALUES(2);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS_r33: {
CHECK_CURRENT_CACHED_VALUES(3);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef _stack_item_0 = _tos_cache0;
_PyStackRef _stack_item_1 = _tos_cache1;
_PyStackRef _stack_item_2 = _tos_cache2;
sub_st = _stack_item_2;
tuple_st = _stack_item_1;
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
if (!_PyLong_IsNonNegativeCompact((PyLongObject *)sub)) {
UOP_STAT_INC(uopcode, miss);
_tos_cache2 = sub_st;
_tos_cache1 = tuple_st;
_tos_cache0 = _stack_item_0;
SET_CURRENT_CACHED_VALUES(3);
JUMP_TO_JUMP_TARGET();
}
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
if (index >= PyTuple_GET_SIZE(tuple)) {
UOP_STAT_INC(uopcode, miss);
_tos_cache2 = sub_st;
_tos_cache1 = tuple_st;
_tos_cache0 = _stack_item_0;
SET_CURRENT_CACHED_VALUES(3);
JUMP_TO_JUMP_TARGET();
}
_tos_cache2 = sub_st;
_tos_cache1 = tuple_st;
_tos_cache0 = _stack_item_0;
SET_CURRENT_CACHED_VALUES(3);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _BINARY_OP_SUBSCR_TUPLE_INT_r03: {
CHECK_CURRENT_CACHED_VALUES(0);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef res;
_PyStackRef ts;
_PyStackRef ss;
sub_st = stack_pointer[-1];
tuple_st = stack_pointer[-2];
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
STAT_INC(BINARY_OP, hit);
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
PyObject *res_o = PyTuple_GET_ITEM(tuple, index);
assert(res_o != NULL);
res = PyStackRef_FromPyObjectNew(res_o);
ts = tuple_st;
ss = sub_st;
_tos_cache2 = ss;
_tos_cache1 = ts;
_tos_cache0 = res;
SET_CURRENT_CACHED_VALUES(3);
stack_pointer += -2;
ASSERT_WITHIN_STACK_BOUNDS(__FILE__, __LINE__);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _BINARY_OP_SUBSCR_TUPLE_INT_r13: {
CHECK_CURRENT_CACHED_VALUES(1);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef res;
_PyStackRef ts;
_PyStackRef ss;
_PyStackRef _stack_item_0 = _tos_cache0;
sub_st = _stack_item_0;
tuple_st = stack_pointer[-1];
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
STAT_INC(BINARY_OP, hit);
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
PyObject *res_o = PyTuple_GET_ITEM(tuple, index);
assert(res_o != NULL);
res = PyStackRef_FromPyObjectNew(res_o);
ts = tuple_st;
ss = sub_st;
_tos_cache2 = ss;
_tos_cache1 = ts;
_tos_cache0 = res;
SET_CURRENT_CACHED_VALUES(3);
stack_pointer += -1;
ASSERT_WITHIN_STACK_BOUNDS(__FILE__, __LINE__);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
break;
}
case _BINARY_OP_SUBSCR_TUPLE_INT_r23: {
CHECK_CURRENT_CACHED_VALUES(2);
assert(WITHIN_STACK_BOUNDS_IGNORING_CACHE());
_PyStackRef sub_st;
_PyStackRef tuple_st;
_PyStackRef res;
_PyStackRef ts;
_PyStackRef ss;
_PyStackRef _stack_item_0 = _tos_cache0;
_PyStackRef _stack_item_1 = _tos_cache1;
sub_st = _stack_item_1;
tuple_st = _stack_item_0;
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
STAT_INC(BINARY_OP, hit);
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
PyObject *res_o = PyTuple_GET_ITEM(tuple, index);
assert(res_o != NULL);
res = PyStackRef_FromPyObjectNew(res_o);

View file

@ -1042,8 +1042,7 @@
JUMP_TO_PREDICTED(BINARY_OP);
}
}
/* Skip 5 cache entries */
// _BINARY_OP_SUBSCR_TUPLE_INT
// _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS
{
sub_st = value;
tuple_st = nos;
@ -1062,7 +1061,16 @@
assert(_PyOpcode_Deopt[opcode] == (BINARY_OP));
JUMP_TO_PREDICTED(BINARY_OP);
}
}
/* Skip 5 cache entries */
// _BINARY_OP_SUBSCR_TUPLE_INT
{
PyObject *sub = PyStackRef_AsPyObjectBorrow(sub_st);
PyObject *tuple = PyStackRef_AsPyObjectBorrow(tuple_st);
assert(PyLong_CheckExact(sub));
assert(PyTuple_CheckExact(tuple));
STAT_INC(BINARY_OP, hit);
Py_ssize_t index = ((PyLongObject*)sub)->long_value.ob_digit[0];
PyObject *res_o = PyTuple_GET_ITEM(tuple, index);
assert(res_o != NULL);
res = PyStackRef_FromPyObjectNew(res_o);

View file

@ -332,6 +332,19 @@ dummy_func(void) {
i = sub_st;
}
op(_GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS, (tuple_st, sub_st -- tuple_st, sub_st)) {
assert(sym_matches_type(tuple_st, &PyTuple_Type));
if (sym_is_const(ctx, sub_st)) {
assert(PyLong_CheckExact(sym_get_const(ctx, sub_st)));
long index = PyLong_AsLong(sym_get_const(ctx, sub_st));
assert(index >= 0);
int tuple_length = sym_tuple_length(tuple_st);
if (tuple_length != -1 && index < tuple_length) {
REPLACE_OP(this_instr, _NOP, 0, 0);
}
}
}
op(_BINARY_OP_SUBSCR_TUPLE_INT, (tuple_st, sub_st -- res, ts, ss)) {
assert(sym_matches_type(tuple_st, &PyTuple_Type));
if (sym_is_const(ctx, sub_st)) {

View file

@ -799,6 +799,24 @@
break;
}
case _GUARD_BINARY_OP_SUBSCR_TUPLE_INT_BOUNDS: {
JitOptRef sub_st;
JitOptRef tuple_st;
sub_st = stack_pointer[-1];
tuple_st = stack_pointer[-2];
assert(sym_matches_type(tuple_st, &PyTuple_Type));
if (sym_is_const(ctx, sub_st)) {
assert(PyLong_CheckExact(sym_get_const(ctx, sub_st)));
long index = PyLong_AsLong(sym_get_const(ctx, sub_st));
assert(index >= 0);
int tuple_length = sym_tuple_length(tuple_st);
if (tuple_length != -1 && index < tuple_length) {
REPLACE_OP(this_instr, _NOP, 0, 0);
}
}
break;
}
case _BINARY_OP_SUBSCR_TUPLE_INT: {
JitOptRef sub_st;
JitOptRef tuple_st;