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)
static TCGArg do_constant_folding_2(TCGOpcode op, TCGArg x, TCGArg y)
{
+ uint64_t l64, h64;
+
switch (op) {
CASE_OP_32_64(add):
return x + y;
return (int64_t)x >> (int64_t)y;
case INDEX_op_rotr_i32:
- x = ((uint32_t)x << (32 - y)) | ((uint32_t)x >> y);
- return x;
+ return ror32(x, y);
case INDEX_op_rotr_i64:
- x = ((uint64_t)x << (64 - y)) | ((uint64_t)x >> y);
- return x;
+ return ror64(x, y);
case INDEX_op_rotl_i32:
- x = ((uint32_t)x << y) | ((uint32_t)x >> (32 - y));
- return x;
+ return rol32(x, y);
case INDEX_op_rotl_i64:
- x = ((uint64_t)x << y) | ((uint64_t)x >> (64 - y));
- return x;
+ return rol64(x, y);
CASE_OP_32_64(not):
return ~x;
case INDEX_op_ext32u_i64:
return (uint32_t)x;
+ case INDEX_op_muluh_i32:
+ return ((uint64_t)(uint32_t)x * (uint32_t)y) >> 32;
+ case INDEX_op_mulsh_i32:
+ return ((int64_t)(int32_t)x * (int32_t)y) >> 32;
+
+ case INDEX_op_muluh_i64:
+ mulu64(&l64, &h64, x, y);
+ return h64;
+ case INDEX_op_mulsh_i64:
+ muls64(&l64, &h64, x, y);
+ return h64;
+
+ case INDEX_op_div_i32:
+ /* Avoid crashing on divide by zero, otherwise undefined. */
+ return (int32_t)x / ((int32_t)y ? : 1);
+ case INDEX_op_divu_i32:
+ return (uint32_t)x / ((uint32_t)y ? : 1);
+ case INDEX_op_div_i64:
+ return (int64_t)x / ((int64_t)y ? : 1);
+ case INDEX_op_divu_i64:
+ return (uint64_t)x / ((uint64_t)y ? : 1);
+
+ case INDEX_op_rem_i32:
+ return (int32_t)x % ((int32_t)y ? : 1);
+ case INDEX_op_remu_i32:
+ return (uint32_t)x % ((uint32_t)y ? : 1);
+ case INDEX_op_rem_i64:
+ return (int64_t)x % ((int64_t)y ? : 1);
+ case INDEX_op_remu_i64:
+ return (uint64_t)x % ((uint64_t)y ? : 1);
+
default:
fprintf(stderr,
"Unrecognized operation %d in do_constant_folding.\n", op);
return res;
}
+static bool do_constant_folding_cond_32(uint32_t x, uint32_t y, TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_EQ:
+ return x == y;
+ case TCG_COND_NE:
+ return x != y;
+ case TCG_COND_LT:
+ return (int32_t)x < (int32_t)y;
+ case TCG_COND_GE:
+ return (int32_t)x >= (int32_t)y;
+ case TCG_COND_LE:
+ return (int32_t)x <= (int32_t)y;
+ case TCG_COND_GT:
+ return (int32_t)x > (int32_t)y;
+ case TCG_COND_LTU:
+ return x < y;
+ case TCG_COND_GEU:
+ return x >= y;
+ case TCG_COND_LEU:
+ return x <= y;
+ case TCG_COND_GTU:
+ return x > y;
+ default:
+ tcg_abort();
+ }
+}
+
+static bool do_constant_folding_cond_64(uint64_t x, uint64_t y, TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_EQ:
+ return x == y;
+ case TCG_COND_NE:
+ return x != y;
+ case TCG_COND_LT:
+ return (int64_t)x < (int64_t)y;
+ case TCG_COND_GE:
+ return (int64_t)x >= (int64_t)y;
+ case TCG_COND_LE:
+ return (int64_t)x <= (int64_t)y;
+ case TCG_COND_GT:
+ return (int64_t)x > (int64_t)y;
+ case TCG_COND_LTU:
+ return x < y;
+ case TCG_COND_GEU:
+ return x >= y;
+ case TCG_COND_LEU:
+ return x <= y;
+ case TCG_COND_GTU:
+ return x > y;
+ default:
+ tcg_abort();
+ }
+}
+
+static bool do_constant_folding_cond_eq(TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_GT:
+ case TCG_COND_LTU:
+ case TCG_COND_LT:
+ case TCG_COND_GTU:
+ case TCG_COND_NE:
+ return 0;
+ case TCG_COND_GE:
+ case TCG_COND_GEU:
+ case TCG_COND_LE:
+ case TCG_COND_LEU:
+ case TCG_COND_EQ:
+ return 1;
+ default:
+ tcg_abort();
+ }
+}
+
/* Return 2 if the condition can't be simplified, and the result
of the condition (0 or 1) if it can */
static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) {
switch (op_bits(op)) {
case 32:
- switch (c) {
- case TCG_COND_EQ:
- return (uint32_t)temps[x].val == (uint32_t)temps[y].val;
- case TCG_COND_NE:
- return (uint32_t)temps[x].val != (uint32_t)temps[y].val;
- case TCG_COND_LT:
- return (int32_t)temps[x].val < (int32_t)temps[y].val;
- case TCG_COND_GE:
- return (int32_t)temps[x].val >= (int32_t)temps[y].val;
- case TCG_COND_LE:
- return (int32_t)temps[x].val <= (int32_t)temps[y].val;
- case TCG_COND_GT:
- return (int32_t)temps[x].val > (int32_t)temps[y].val;
- case TCG_COND_LTU:
- return (uint32_t)temps[x].val < (uint32_t)temps[y].val;
- case TCG_COND_GEU:
- return (uint32_t)temps[x].val >= (uint32_t)temps[y].val;
- case TCG_COND_LEU:
- return (uint32_t)temps[x].val <= (uint32_t)temps[y].val;
- case TCG_COND_GTU:
- return (uint32_t)temps[x].val > (uint32_t)temps[y].val;
- }
- break;
+ return do_constant_folding_cond_32(temps[x].val, temps[y].val, c);
case 64:
- switch (c) {
- case TCG_COND_EQ:
- return (uint64_t)temps[x].val == (uint64_t)temps[y].val;
- case TCG_COND_NE:
- return (uint64_t)temps[x].val != (uint64_t)temps[y].val;
- case TCG_COND_LT:
- return (int64_t)temps[x].val < (int64_t)temps[y].val;
- case TCG_COND_GE:
- return (int64_t)temps[x].val >= (int64_t)temps[y].val;
- case TCG_COND_LE:
- return (int64_t)temps[x].val <= (int64_t)temps[y].val;
- case TCG_COND_GT:
- return (int64_t)temps[x].val > (int64_t)temps[y].val;
- case TCG_COND_LTU:
- return (uint64_t)temps[x].val < (uint64_t)temps[y].val;
- case TCG_COND_GEU:
- return (uint64_t)temps[x].val >= (uint64_t)temps[y].val;
- case TCG_COND_LEU:
- return (uint64_t)temps[x].val <= (uint64_t)temps[y].val;
- case TCG_COND_GTU:
- return (uint64_t)temps[x].val > (uint64_t)temps[y].val;
- }
- break;
+ return do_constant_folding_cond_64(temps[x].val, temps[y].val, c);
+ default:
+ tcg_abort();
}
} else if (temps_are_copies(x, y)) {
- switch (c) {
- case TCG_COND_GT:
- case TCG_COND_LTU:
- case TCG_COND_LT:
- case TCG_COND_GTU:
- case TCG_COND_NE:
- return 0;
- case TCG_COND_GE:
- case TCG_COND_GEU:
- case TCG_COND_LE:
- case TCG_COND_LEU:
- case TCG_COND_EQ:
- return 1;
- }
+ return do_constant_folding_cond_eq(c);
} else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) {
switch (c) {
case TCG_COND_LTU:
} else {
return 2;
}
+}
+
+/* Return 2 if the condition can't be simplified, and the result
+ of the condition (0 or 1) if it can */
+static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c)
+{
+ TCGArg al = p1[0], ah = p1[1];
+ TCGArg bl = p2[0], bh = p2[1];
+
+ if (temps[bl].state == TCG_TEMP_CONST
+ && temps[bh].state == TCG_TEMP_CONST) {
+ uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val;
+
+ if (temps[al].state == TCG_TEMP_CONST
+ && temps[ah].state == TCG_TEMP_CONST) {
+ uint64_t a;
+ a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val;
+ return do_constant_folding_cond_64(a, b, c);
+ }
+ if (b == 0) {
+ switch (c) {
+ case TCG_COND_LTU:
+ return 0;
+ case TCG_COND_GEU:
+ return 1;
+ default:
+ break;
+ }
+ }
+ }
+ if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) {
+ return do_constant_folding_cond_eq(c);
+ }
+ return 2;
+}
+
+static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
+{
+ TCGArg a1 = *p1, a2 = *p2;
+ int sum = 0;
+ sum += temps[a1].state == TCG_TEMP_CONST;
+ sum -= temps[a2].state == TCG_TEMP_CONST;
+
+ /* Prefer the constant in second argument, and then the form
+ op a, a, b, which is better handled on non-RISC hosts. */
+ if (sum > 0 || (sum == 0 && dest == a2)) {
+ *p1 = a2;
+ *p2 = a1;
+ return true;
+ }
+ return false;
+}
- fprintf(stderr,
- "Unrecognized bitness %d or condition %d in "
- "do_constant_folding_cond.\n", op_bits(op), c);
- tcg_abort();
+static bool swap_commutative2(TCGArg *p1, TCGArg *p2)
+{
+ int sum = 0;
+ sum += temps[p1[0]].state == TCG_TEMP_CONST;
+ sum += temps[p1[1]].state == TCG_TEMP_CONST;
+ sum -= temps[p2[0]].state == TCG_TEMP_CONST;
+ sum -= temps[p2[1]].state == TCG_TEMP_CONST;
+ if (sum > 0) {
+ TCGArg t;
+ t = p1[0], p1[0] = p2[0], p2[0] = t;
+ t = p1[1], p1[1] = p2[1], p2[1] = t;
+ return true;
+ }
+ return false;
}
/* Propagate constants and copies, fold constant expressions. */
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;
TCGArg tmp;
- TCGCond cond;
/* Array VALS has an element for each temp.
If this temp holds a constant then its value is kept in VALS' element.
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) {
CASE_OP_32_64(eqv):
CASE_OP_32_64(nand):
CASE_OP_32_64(nor):
- /* Prefer the constant in second argument, and then the form
- op a, a, b, which is better handled on non-RISC hosts. */
- if (temps[args[1]].state == TCG_TEMP_CONST || (args[0] == args[2]
- && temps[args[2]].state != TCG_TEMP_CONST)) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
- }
+ CASE_OP_32_64(muluh):
+ CASE_OP_32_64(mulsh):
+ swap_commutative(args[0], &args[1], &args[2]);
break;
CASE_OP_32_64(brcond):
- if (temps[args[0]].state == TCG_TEMP_CONST
- && temps[args[1]].state != TCG_TEMP_CONST) {
- tmp = args[0];
- args[0] = args[1];
- args[1] = tmp;
+ if (swap_commutative(-1, &args[0], &args[1])) {
args[2] = tcg_swap_cond(args[2]);
}
break;
CASE_OP_32_64(setcond):
- if (temps[args[1]].state == TCG_TEMP_CONST
- && temps[args[2]].state != TCG_TEMP_CONST) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
+ if (swap_commutative(args[0], &args[1], &args[2])) {
args[3] = tcg_swap_cond(args[3]);
}
break;
CASE_OP_32_64(movcond):
- cond = args[5];
- if (temps[args[1]].state == TCG_TEMP_CONST
- && temps[args[2]].state != TCG_TEMP_CONST) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
- cond = tcg_swap_cond(cond);
+ if (swap_commutative(-1, &args[1], &args[2])) {
+ args[5] = tcg_swap_cond(args[5]);
}
/* For movcond, we canonicalize the "false" input reg to match
the destination reg so that the tcg backend can implement
a "move if true" operation. */
- if (args[0] == args[3]) {
- tmp = args[3];
- args[3] = args[4];
- args[4] = tmp;
- cond = tcg_invert_cond(cond);
+ if (swap_commutative(args[0], &args[4], &args[3])) {
+ args[5] = tcg_invert_cond(args[5]);
+ }
+ break;
+ CASE_OP_32_64(add2):
+ swap_commutative(args[0], &args[2], &args[4]);
+ swap_commutative(args[1], &args[3], &args[5]);
+ break;
+ CASE_OP_32_64(mulu2):
+ CASE_OP_32_64(muls2):
+ swap_commutative(args[0], &args[2], &args[3]);
+ break;
+ case INDEX_op_brcond2_i32:
+ if (swap_commutative2(&args[0], &args[2])) {
+ args[4] = tcg_swap_cond(args[4]);
+ }
+ break;
+ case INDEX_op_setcond2_i32:
+ if (swap_commutative2(&args[1], &args[3])) {
+ args[5] = tcg_swap_cond(args[5]);
}
- args[5] = cond;
+ break;
default:
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):
+ CASE_OP_32_64(muluh):
+ CASE_OP_32_64(mulsh):
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):
gen_args += 2;
args += 2;
break;
+
CASE_OP_32_64(not):
CASE_OP_32_64(neg):
CASE_OP_32_64(ext8s):
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);
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
+ gen_args += 2;
+ args += 2;
+ break;
}
- gen_args += 2;
- args += 2;
- break;
+ goto do_default;
+
CASE_OP_32_64(add):
CASE_OP_32_64(sub):
CASE_OP_32_64(mul):
CASE_OP_32_64(eqv):
CASE_OP_32_64(nand):
CASE_OP_32_64(nor):
+ CASE_OP_32_64(muluh):
+ CASE_OP_32_64(mulsh):
+ CASE_OP_32_64(div):
+ CASE_OP_32_64(divu):
+ CASE_OP_32_64(rem):
+ CASE_OP_32_64(remu):
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);
gen_args += 2;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args += 3;
+ args += 3;
+ break;
}
- args += 3;
- break;
+ goto do_default;
+
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]);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args[4] = args[4];
- gen_args += 5;
+ args += 5;
+ break;
}
- args += 5;
- break;
+ goto do_default;
+
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;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args += 4;
+ args += 4;
+ break;
}
- args += 4;
- break;
+ goto do_default;
+
CASE_OP_32_64(brcond):
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;
}
- } else {
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args += 4;
+ args += 4;
+ break;
}
- args += 4;
- break;
+ goto do_default;
+
CASE_OP_32_64(movcond):
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;
}
+ args += 6;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_add2_i32:
+ case INDEX_op_sub2_i32:
+ if (temps[args[2]].state == TCG_TEMP_CONST
+ && temps[args[3]].state == TCG_TEMP_CONST
+ && temps[args[4]].state == TCG_TEMP_CONST
+ && temps[args[5]].state == TCG_TEMP_CONST) {
+ uint32_t al = temps[args[2]].val;
+ uint32_t ah = temps[args[3]].val;
+ uint32_t bl = temps[args[4]].val;
+ uint32_t bh = temps[args[5]].val;
+ uint64_t a = ((uint64_t)ah << 32) | al;
+ uint64_t b = ((uint64_t)bh << 32) | bl;
+ TCGArg rl, rh;
+
+ if (op == INDEX_op_add2_i32) {
+ a += b;
+ } else {
+ a -= b;
+ }
+
+ /* We emit the extra nop when we emit the add2/sub2. */
+ assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+ rl = args[0];
+ rh = args[1];
+ 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;
+ args += 6;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_mulu2_i32:
+ if (temps[args[2]].state == TCG_TEMP_CONST
+ && temps[args[3]].state == TCG_TEMP_CONST) {
+ uint32_t a = temps[args[2]].val;
+ uint32_t b = temps[args[3]].val;
+ uint64_t r = (uint64_t)a * b;
+ TCGArg rl, rh;
+
+ /* We emit the extra nop when we emit the mulu2. */
+ assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+ rl = args[0];
+ rh = args[1];
+ 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;
+ args += 4;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_brcond2_i32:
+ tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
+ if (tmp != 2) {
+ if (tmp) {
+ reset_all_temps(nb_temps);
+ s->gen_opc_buf[op_index] = INDEX_op_br;
+ gen_args[0] = args[5];
+ gen_args += 1;
+ } else {
+ 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]].state == TCG_TEMP_CONST
+ && temps[args[2]].val == 0
+ && temps[args[3]].val == 0) {
+ /* Simplify LT/GE comparisons vs zero to a single compare
+ vs the high word of the input. */
+ 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];
+ gen_args[3] = args[5];
+ gen_args += 4;
} else {
+ goto do_default;
+ }
+ args += 6;
+ break;
+
+ case INDEX_op_setcond2_i32:
+ tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
+ if (tmp != 2) {
+ 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[3]].state == TCG_TEMP_CONST
+ && temps[args[4]].state == TCG_TEMP_CONST
+ && temps[args[3]].val == 0
+ && temps[args[4]].val == 0) {
+ /* Simplify LT/GE comparisons vs zero to a single compare
+ vs the high word of the input. */
+ s->gen_opc_buf[op_index] = INDEX_op_setcond_i32;
reset_temp(args[0]);
gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args[4] = args[4];
- gen_args[5] = args[5];
- gen_args += 6;
+ gen_args[1] = args[2];
+ gen_args[2] = args[4];
+ gen_args[3] = args[5];
+ gen_args += 4;
+ } else {
+ goto do_default;
}
args += 6;
break;
+
case INDEX_op_call:
nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
- if (!(args[nb_call_args + 1] & (TCG_CALL_CONST | TCG_CALL_PURE))) {
+ if (!(args[nb_call_args + 1] & (TCG_CALL_NO_READ_GLOBALS |
+ TCG_CALL_NO_WRITE_GLOBALS))) {
for (i = 0; i < nb_globals; i++) {
reset_temp(i);
}
i--;
}
break;
+
default:
- /* Default case: we do know nothing about operation 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. */
+ do_default:
+ /* 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. "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