uint16_t prev_copy;
uint16_t next_copy;
tcg_target_ulong val;
+ tcg_target_ulong mask;
};
static struct tcg_temp_info temps[TCG_MAX_TEMPS];
}
}
temps[temp].state = TCG_TEMP_UNDEF;
+ temps[temp].mask = -1;
+}
+
+/* Reset all temporaries, given that there are NB_TEMPS of them. */
+static void reset_all_temps(int nb_temps)
+{
+ int i;
+ for (i = 0; i < nb_temps; i++) {
+ temps[i].state = TCG_TEMP_UNDEF;
+ temps[i].mask = -1;
+ }
}
static int op_bits(TCGOpcode op)
static void tcg_opt_gen_mov(TCGContext *s, TCGArg *gen_args,
TCGArg dst, TCGArg src)
{
- reset_temp(dst);
- assert(temps[src].state != TCG_TEMP_CONST);
-
- if (s->temps[src].type == s->temps[dst].type) {
- if (temps[src].state != TCG_TEMP_COPY) {
- temps[src].state = TCG_TEMP_COPY;
- temps[src].next_copy = src;
- temps[src].prev_copy = src;
- }
- temps[dst].state = TCG_TEMP_COPY;
- temps[dst].next_copy = temps[src].next_copy;
- temps[dst].prev_copy = src;
- temps[temps[dst].next_copy].prev_copy = dst;
- temps[src].next_copy = dst;
+ reset_temp(dst);
+ temps[dst].mask = temps[src].mask;
+ assert(temps[src].state != TCG_TEMP_CONST);
+
+ if (s->temps[src].type == s->temps[dst].type) {
+ if (temps[src].state != TCG_TEMP_COPY) {
+ temps[src].state = TCG_TEMP_COPY;
+ temps[src].next_copy = src;
+ temps[src].prev_copy = src;
}
+ temps[dst].state = TCG_TEMP_COPY;
+ temps[dst].next_copy = temps[src].next_copy;
+ temps[dst].prev_copy = src;
+ temps[temps[dst].next_copy].prev_copy = dst;
+ temps[src].next_copy = dst;
+ }
- gen_args[0] = dst;
- gen_args[1] = src;
+ gen_args[0] = dst;
+ gen_args[1] = src;
}
static void tcg_opt_gen_movi(TCGArg *gen_args, TCGArg dst, TCGArg val)
{
- reset_temp(dst);
- temps[dst].state = TCG_TEMP_CONST;
- temps[dst].val = val;
- gen_args[0] = dst;
- gen_args[1] = val;
+ reset_temp(dst);
+ temps[dst].state = TCG_TEMP_CONST;
+ temps[dst].val = val;
+ temps[dst].mask = val;
+ gen_args[0] = dst;
+ gen_args[1] = val;
}
static TCGOpcode op_to_mov(TCGOpcode op)
TCGArg *args, TCGOpDef *tcg_op_defs)
{
int i, nb_ops, op_index, nb_temps, nb_globals, nb_call_args;
+ tcg_target_ulong mask, affected;
TCGOpcode op;
const TCGOpDef *def;
TCGArg *gen_args;
nb_temps = s->nb_temps;
nb_globals = s->nb_globals;
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ reset_all_temps(nb_temps);
- nb_ops = tcg_opc_ptr - gen_opc_buf;
+ nb_ops = tcg_opc_ptr - s->gen_opc_buf;
gen_args = args;
for (op_index = 0; op_index < nb_ops; op_index++) {
- op = gen_opc_buf[op_index];
+ op = s->gen_opc_buf[op_index];
def = &tcg_op_defs[op];
/* Do copy propagation */
if (op == INDEX_op_call) {
args[5] = tcg_invert_cond(args[5]);
}
break;
- case INDEX_op_add2_i32:
+ CASE_OP_32_64(add2):
swap_commutative(args[0], &args[2], &args[4]);
swap_commutative(args[1], &args[3], &args[5]);
break;
- case INDEX_op_mulu2_i32:
+ CASE_OP_32_64(mulu2):
+ CASE_OP_32_64(muls2):
swap_commutative(args[0], &args[2], &args[3]);
break;
case INDEX_op_brcond2_i32:
break;
}
- /* Simplify expressions for "shift/rot r, 0, a => movi r, 0" */
+ /* Simplify expressions for "shift/rot r, 0, a => movi r, 0",
+ and "sub r, 0, a => neg r, a" case. */
switch (op) {
CASE_OP_32_64(shl):
CASE_OP_32_64(shr):
CASE_OP_32_64(rotr):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[1]].val == 0) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], 0);
args += 3;
gen_args += 2;
continue;
}
break;
+ CASE_OP_32_64(sub):
+ {
+ TCGOpcode neg_op;
+ bool have_neg;
+
+ if (temps[args[2]].state == TCG_TEMP_CONST) {
+ /* Proceed with possible constant folding. */
+ break;
+ }
+ if (op == INDEX_op_sub_i32) {
+ neg_op = INDEX_op_neg_i32;
+ have_neg = TCG_TARGET_HAS_neg_i32;
+ } else {
+ neg_op = INDEX_op_neg_i64;
+ have_neg = TCG_TARGET_HAS_neg_i64;
+ }
+ if (!have_neg) {
+ break;
+ }
+ if (temps[args[1]].state == TCG_TEMP_CONST
+ && temps[args[1]].val == 0) {
+ s->gen_opc_buf[op_index] = neg_op;
+ reset_temp(args[0]);
+ gen_args[0] = args[0];
+ gen_args[1] = args[2];
+ args += 3;
+ gen_args += 2;
+ continue;
+ }
+ }
+ break;
default:
break;
}
if (temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0) {
if (temps_are_copies(args[0], args[1])) {
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
} else {
- gen_opc_buf[op_index] = op_to_mov(op);
+ s->gen_opc_buf[op_index] = op_to_mov(op);
tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
gen_args += 2;
}
break;
}
+ /* Simplify using known-zero bits */
+ mask = -1;
+ affected = -1;
+ switch (op) {
+ CASE_OP_32_64(ext8s):
+ if ((temps[args[1]].mask & 0x80) != 0) {
+ break;
+ }
+ CASE_OP_32_64(ext8u):
+ mask = 0xff;
+ goto and_const;
+ CASE_OP_32_64(ext16s):
+ if ((temps[args[1]].mask & 0x8000) != 0) {
+ break;
+ }
+ CASE_OP_32_64(ext16u):
+ mask = 0xffff;
+ goto and_const;
+ case INDEX_op_ext32s_i64:
+ if ((temps[args[1]].mask & 0x80000000) != 0) {
+ break;
+ }
+ case INDEX_op_ext32u_i64:
+ mask = 0xffffffffU;
+ goto and_const;
+
+ CASE_OP_32_64(and):
+ mask = temps[args[2]].mask;
+ if (temps[args[2]].state == TCG_TEMP_CONST) {
+ and_const:
+ affected = temps[args[1]].mask & ~mask;
+ }
+ mask = temps[args[1]].mask & mask;
+ break;
+
+ CASE_OP_32_64(sar):
+ if (temps[args[2]].state == TCG_TEMP_CONST) {
+ mask = ((tcg_target_long)temps[args[1]].mask
+ >> temps[args[2]].val);
+ }
+ break;
+
+ CASE_OP_32_64(shr):
+ if (temps[args[2]].state == TCG_TEMP_CONST) {
+ mask = temps[args[1]].mask >> temps[args[2]].val;
+ }
+ break;
+
+ CASE_OP_32_64(shl):
+ if (temps[args[2]].state == TCG_TEMP_CONST) {
+ mask = temps[args[1]].mask << temps[args[2]].val;
+ }
+ break;
+
+ CASE_OP_32_64(neg):
+ /* Set to 1 all bits to the left of the rightmost. */
+ mask = -(temps[args[1]].mask & -temps[args[1]].mask);
+ break;
+
+ CASE_OP_32_64(deposit):
+ tmp = ((1ull << args[4]) - 1);
+ mask = ((temps[args[1]].mask & ~(tmp << args[3]))
+ | ((temps[args[2]].mask & tmp) << args[3]));
+ break;
+
+ CASE_OP_32_64(or):
+ CASE_OP_32_64(xor):
+ mask = temps[args[1]].mask | temps[args[2]].mask;
+ break;
+
+ CASE_OP_32_64(setcond):
+ mask = 1;
+ break;
+
+ CASE_OP_32_64(movcond):
+ mask = temps[args[3]].mask | temps[args[4]].mask;
+ break;
+
+ default:
+ break;
+ }
+
+ if (mask == 0) {
+ assert(def->nb_oargs == 1);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
+ tcg_opt_gen_movi(gen_args, args[0], 0);
+ args += def->nb_oargs + def->nb_iargs + def->nb_cargs;
+ gen_args += 2;
+ continue;
+ }
+ if (affected == 0) {
+ assert(def->nb_oargs == 1);
+ if (temps_are_copies(args[0], args[1])) {
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
+ } else if (temps[args[1]].state != TCG_TEMP_CONST) {
+ s->gen_opc_buf[op_index] = op_to_mov(op);
+ tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
+ gen_args += 2;
+ } else {
+ s->gen_opc_buf[op_index] = op_to_movi(op);
+ tcg_opt_gen_movi(gen_args, args[0], temps[args[1]].val);
+ gen_args += 2;
+ }
+ args += def->nb_iargs + 1;
+ continue;
+ }
+
/* Simplify expression for "op r, a, 0 => movi r, 0" cases */
switch (op) {
CASE_OP_32_64(and):
CASE_OP_32_64(mul):
if ((temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0)) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], 0);
args += 3;
gen_args += 2;
CASE_OP_32_64(and):
if (temps_are_copies(args[1], args[2])) {
if (temps_are_copies(args[0], args[1])) {
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
} else {
- gen_opc_buf[op_index] = op_to_mov(op);
+ s->gen_opc_buf[op_index] = op_to_mov(op);
tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
gen_args += 2;
}
CASE_OP_32_64(sub):
CASE_OP_32_64(xor):
if (temps_are_copies(args[1], args[2])) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], 0);
gen_args += 2;
args += 3;
CASE_OP_32_64(mov):
if (temps_are_copies(args[0], args[1])) {
args += 2;
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
break;
}
if (temps[args[1]].state != TCG_TEMP_CONST) {
/* Source argument is constant. Rewrite the operation and
let movi case handle it. */
op = op_to_movi(op);
- gen_opc_buf[op_index] = op;
+ s->gen_opc_buf[op_index] = op;
args[1] = temps[args[1]].val;
/* fallthrough */
CASE_OP_32_64(movi):
case INDEX_op_ext32s_i64:
case INDEX_op_ext32u_i64:
if (temps[args[1]].state == TCG_TEMP_CONST) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val, 0);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
CASE_OP_32_64(nor):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[2]].state == TCG_TEMP_CONST) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val,
temps[args[2]].val);
tcg_opt_gen_movi(gen_args, args[0], tmp);
CASE_OP_32_64(deposit):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[2]].state == TCG_TEMP_CONST) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tmp = ((1ull << args[4]) - 1);
tmp = (temps[args[1]].val & ~(tmp << args[3]))
| ((temps[args[2]].val & tmp) << args[3]);
CASE_OP_32_64(setcond):
tmp = do_constant_folding_cond(op, args[1], args[2], args[3]);
if (tmp != 2) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
args += 4;
tmp = do_constant_folding_cond(op, args[0], args[1], args[2]);
if (tmp != 2) {
if (tmp) {
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- gen_opc_buf[op_index] = INDEX_op_br;
+ reset_all_temps(nb_temps);
+ s->gen_opc_buf[op_index] = INDEX_op_br;
gen_args[0] = args[3];
gen_args += 1;
} else {
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
}
args += 4;
break;
tmp = do_constant_folding_cond(op, args[1], args[2], args[5]);
if (tmp != 2) {
if (temps_are_copies(args[0], args[4-tmp])) {
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
} else if (temps[args[4-tmp]].state == TCG_TEMP_CONST) {
- gen_opc_buf[op_index] = op_to_movi(op);
+ s->gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], temps[args[4-tmp]].val);
gen_args += 2;
} else {
- gen_opc_buf[op_index] = op_to_mov(op);
+ s->gen_opc_buf[op_index] = op_to_mov(op);
tcg_opt_gen_mov(s, gen_args, args[0], args[4-tmp]);
gen_args += 2;
}
}
/* We emit the extra nop when we emit the add2/sub2. */
- assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+ assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
rl = args[0];
rh = args[1];
- gen_opc_buf[op_index] = INDEX_op_movi_i32;
- gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+ s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ s->gen_opc_buf[++op_index] = INDEX_op_movi_i32;
tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)a);
tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(a >> 32));
gen_args += 4;
TCGArg rl, rh;
/* We emit the extra nop when we emit the mulu2. */
- assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+ assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
rl = args[0];
rh = args[1];
- gen_opc_buf[op_index] = INDEX_op_movi_i32;
- gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+ s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ s->gen_opc_buf[++op_index] = INDEX_op_movi_i32;
tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)r);
tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(r >> 32));
gen_args += 4;
tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
if (tmp != 2) {
if (tmp) {
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- gen_opc_buf[op_index] = INDEX_op_br;
+ reset_all_temps(nb_temps);
+ s->gen_opc_buf[op_index] = INDEX_op_br;
gen_args[0] = args[5];
gen_args += 1;
} else {
- gen_opc_buf[op_index] = INDEX_op_nop;
+ s->gen_opc_buf[op_index] = INDEX_op_nop;
}
} else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
&& temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[3]].val == 0) {
/* Simplify LT/GE comparisons vs zero to a single compare
vs the high word of the input. */
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- gen_opc_buf[op_index] = INDEX_op_brcond_i32;
+ reset_all_temps(nb_temps);
+ s->gen_opc_buf[op_index] = INDEX_op_brcond_i32;
gen_args[0] = args[1];
gen_args[1] = args[3];
gen_args[2] = args[4];
case INDEX_op_setcond2_i32:
tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
if (tmp != 2) {
- gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
} else if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE)
&& temps[args[4]].val == 0) {
/* Simplify LT/GE comparisons vs zero to a single compare
vs the high word of the input. */
- gen_opc_buf[op_index] = INDEX_op_setcond_i32;
+ s->gen_opc_buf[op_index] = INDEX_op_setcond_i32;
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[2];
gen_args[2] = args[4];
/* Default case: we know nothing about operation (or were unable
to compute the operation result) so no propagation is done.
We trash everything if the operation is the end of a basic
- block, otherwise we only trash the output args. */
+ block, otherwise we only trash the output args. "mask" is
+ the non-zero bits mask for the first output arg. */
if (def->flags & TCG_OPF_BB_END) {
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ reset_all_temps(nb_temps);
} else {
for (i = 0; i < def->nb_oargs; i++) {
reset_temp(args[i]);
projects / qemu.git / blobdiff