glue(glue(case INDEX_op_, x), _i32): \
glue(glue(case INDEX_op_, x), _i64)
+#define CASE_OP_32_64_VEC(x) \
+ glue(glue(case INDEX_op_, x), _i32): \
+ glue(glue(case INDEX_op_, x), _i64): \
+ glue(glue(case INDEX_op_, x), _vec)
+
struct tcg_temp_info {
bool is_const;
TCGTemp *prev_copy;
init_ts_info(infos, temps_used, arg_temp(arg));
}
-static int op_bits(TCGOpcode op)
-{
- const TCGOpDef *def = &tcg_op_defs[op];
- return def->flags & TCG_OPF_64BIT ? 64 : 32;
-}
-
-static TCGOpcode op_to_mov(TCGOpcode op)
-{
- switch (op_bits(op)) {
- case 32:
- return INDEX_op_mov_i32;
- case 64:
- return INDEX_op_mov_i64;
- default:
- fprintf(stderr, "op_to_mov: unexpected return value of "
- "function op_bits.\n");
- tcg_abort();
- }
-}
-
-static TCGOpcode op_to_movi(TCGOpcode op)
-{
- switch (op_bits(op)) {
- case 32:
- return INDEX_op_movi_i32;
- case 64:
- return INDEX_op_movi_i64;
- default:
- fprintf(stderr, "op_to_movi: unexpected return value of "
- "function op_bits.\n");
- tcg_abort();
- }
-}
-
static TCGTemp *find_better_copy(TCGContext *s, TCGTemp *ts)
{
TCGTemp *i;
static void tcg_opt_gen_movi(TCGContext *s, TCGOp *op, TCGArg dst, TCGArg val)
{
- TCGOpcode new_op = op_to_movi(op->opc);
+ const TCGOpDef *def;
+ TCGOpcode new_op;
tcg_target_ulong mask;
struct tcg_temp_info *di = arg_info(dst);
+ def = &tcg_op_defs[op->opc];
+ if (def->flags & TCG_OPF_VECTOR) {
+ new_op = INDEX_op_dupi_vec;
+ } else if (def->flags & TCG_OPF_64BIT) {
+ new_op = INDEX_op_movi_i64;
+ } else {
+ new_op = INDEX_op_movi_i32;
+ }
op->opc = new_op;
+ /* TCGOP_VECL and TCGOP_VECE remain unchanged. */
+ op->args[0] = dst;
+ op->args[1] = val;
reset_temp(dst);
di->is_const = true;
mask |= ~0xffffffffull;
}
di->mask = mask;
-
- op->args[0] = dst;
- op->args[1] = val;
}
static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, TCGArg dst, TCGArg src)
{
TCGTemp *dst_ts = arg_temp(dst);
TCGTemp *src_ts = arg_temp(src);
+ const TCGOpDef *def;
struct tcg_temp_info *di;
struct tcg_temp_info *si;
tcg_target_ulong mask;
reset_ts(dst_ts);
di = ts_info(dst_ts);
si = ts_info(src_ts);
- new_op = op_to_mov(op->opc);
-
+ def = &tcg_op_defs[op->opc];
+ if (def->flags & TCG_OPF_VECTOR) {
+ new_op = INDEX_op_mov_vec;
+ } else if (def->flags & TCG_OPF_64BIT) {
+ new_op = INDEX_op_mov_i64;
+ } else {
+ new_op = INDEX_op_mov_i32;
+ }
op->opc = new_op;
+ /* TCGOP_VECL and TCGOP_VECE remain unchanged. */
op->args[0] = dst;
op->args[1] = src;
CASE_OP_32_64(ext16u):
return (uint16_t)x;
+ CASE_OP_32_64(bswap16):
+ return bswap16(x);
+
+ CASE_OP_32_64(bswap32):
+ return bswap32(x);
+
+ case INDEX_op_bswap64_i64:
+ return bswap64(x);
+
case INDEX_op_ext_i32_i64:
case INDEX_op_ext32s_i64:
return (int32_t)x;
static TCGArg do_constant_folding(TCGOpcode op, TCGArg x, TCGArg y)
{
+ const TCGOpDef *def = &tcg_op_defs[op];
TCGArg res = do_constant_folding_2(op, x, y);
- if (op_bits(op) == 32) {
+ if (!(def->flags & TCG_OPF_64BIT)) {
res = (int32_t)res;
}
return res;
tcg_target_ulong xv = arg_info(x)->val;
tcg_target_ulong yv = arg_info(y)->val;
if (arg_is_const(x) && arg_is_const(y)) {
- switch (op_bits(op)) {
- case 32:
- return do_constant_folding_cond_32(xv, yv, c);
- case 64:
+ const TCGOpDef *def = &tcg_op_defs[op];
+ tcg_debug_assert(!(def->flags & TCG_OPF_VECTOR));
+ if (def->flags & TCG_OPF_64BIT) {
return do_constant_folding_cond_64(xv, yv, c);
- default:
- tcg_abort();
+ } else {
+ return do_constant_folding_cond_32(xv, yv, c);
}
} else if (args_are_copies(x, y)) {
return do_constant_folding_cond_eq(c);
/* Count the arguments, and initialize the temps that are
going to be used */
if (opc == INDEX_op_call) {
- nb_oargs = op->callo;
- nb_iargs = op->calli;
+ nb_oargs = TCGOP_CALLO(op);
+ nb_iargs = TCGOP_CALLI(op);
for (i = 0; i < nb_oargs + nb_iargs; i++) {
TCGTemp *ts = arg_temp(op->args[i]);
if (ts) {
/* For commutative operations make constant second argument */
switch (opc) {
- CASE_OP_32_64(add):
- CASE_OP_32_64(mul):
- CASE_OP_32_64(and):
- CASE_OP_32_64(or):
- CASE_OP_32_64(xor):
+ CASE_OP_32_64_VEC(add):
+ CASE_OP_32_64_VEC(mul):
+ CASE_OP_32_64_VEC(and):
+ CASE_OP_32_64_VEC(or):
+ CASE_OP_32_64_VEC(xor):
CASE_OP_32_64(eqv):
CASE_OP_32_64(nand):
CASE_OP_32_64(nor):
continue;
}
break;
- CASE_OP_32_64(sub):
+ CASE_OP_32_64_VEC(sub):
{
TCGOpcode neg_op;
bool have_neg;
if (opc == INDEX_op_sub_i32) {
neg_op = INDEX_op_neg_i32;
have_neg = TCG_TARGET_HAS_neg_i32;
- } else {
+ } else if (opc == INDEX_op_sub_i64) {
neg_op = INDEX_op_neg_i64;
have_neg = TCG_TARGET_HAS_neg_i64;
+ } else if (TCG_TARGET_HAS_neg_vec) {
+ TCGType type = TCGOP_VECL(op) + TCG_TYPE_V64;
+ unsigned vece = TCGOP_VECE(op);
+ neg_op = INDEX_op_neg_vec;
+ have_neg = tcg_can_emit_vec_op(neg_op, type, vece) > 0;
+ } else {
+ break;
}
if (!have_neg) {
break;
}
}
break;
- CASE_OP_32_64(xor):
+ CASE_OP_32_64_VEC(xor):
CASE_OP_32_64(nand):
if (!arg_is_const(op->args[1])
&& arg_is_const(op->args[2])
goto try_not;
}
break;
- CASE_OP_32_64(andc):
+ CASE_OP_32_64_VEC(andc):
if (!arg_is_const(op->args[2])
&& arg_is_const(op->args[1])
&& arg_info(op->args[1])->val == -1) {
goto try_not;
}
break;
- CASE_OP_32_64(orc):
+ CASE_OP_32_64_VEC(orc):
CASE_OP_32_64(eqv):
if (!arg_is_const(op->args[2])
&& arg_is_const(op->args[1])
TCGOpcode not_op;
bool have_not;
- if (def->flags & TCG_OPF_64BIT) {
+ if (def->flags & TCG_OPF_VECTOR) {
+ not_op = INDEX_op_not_vec;
+ have_not = TCG_TARGET_HAS_not_vec;
+ } else if (def->flags & TCG_OPF_64BIT) {
not_op = INDEX_op_not_i64;
have_not = TCG_TARGET_HAS_not_i64;
} else {
/* Simplify expression for "op r, a, const => mov r, a" cases */
switch (opc) {
- CASE_OP_32_64(add):
- CASE_OP_32_64(sub):
+ CASE_OP_32_64_VEC(add):
+ CASE_OP_32_64_VEC(sub):
+ CASE_OP_32_64_VEC(or):
+ CASE_OP_32_64_VEC(xor):
+ CASE_OP_32_64_VEC(andc):
CASE_OP_32_64(shl):
CASE_OP_32_64(shr):
CASE_OP_32_64(sar):
CASE_OP_32_64(rotl):
CASE_OP_32_64(rotr):
- CASE_OP_32_64(or):
- CASE_OP_32_64(xor):
- CASE_OP_32_64(andc):
if (!arg_is_const(op->args[1])
&& arg_is_const(op->args[2])
&& arg_info(op->args[2])->val == 0) {
continue;
}
break;
- CASE_OP_32_64(and):
- CASE_OP_32_64(orc):
+ CASE_OP_32_64_VEC(and):
+ CASE_OP_32_64_VEC(orc):
CASE_OP_32_64(eqv):
if (!arg_is_const(op->args[1])
&& arg_is_const(op->args[2])
/* Simplify expression for "op r, a, 0 => movi r, 0" cases */
switch (opc) {
- CASE_OP_32_64(and):
- CASE_OP_32_64(mul):
+ CASE_OP_32_64_VEC(and):
+ CASE_OP_32_64_VEC(mul):
CASE_OP_32_64(muluh):
CASE_OP_32_64(mulsh):
if (arg_is_const(op->args[2])
/* Simplify expression for "op r, a, a => mov r, a" cases */
switch (opc) {
- CASE_OP_32_64(or):
- CASE_OP_32_64(and):
+ CASE_OP_32_64_VEC(or):
+ CASE_OP_32_64_VEC(and):
if (args_are_copies(op->args[1], op->args[2])) {
tcg_opt_gen_mov(s, op, op->args[0], op->args[1]);
continue;
/* Simplify expression for "op r, a, a => movi r, 0" cases */
switch (opc) {
- CASE_OP_32_64(andc):
- CASE_OP_32_64(sub):
- CASE_OP_32_64(xor):
+ CASE_OP_32_64_VEC(andc):
+ CASE_OP_32_64_VEC(sub):
+ CASE_OP_32_64_VEC(xor):
if (args_are_copies(op->args[1], op->args[2])) {
tcg_opt_gen_movi(s, op, op->args[0], 0);
continue;
folding. Constants will be substituted to arguments by register
allocator where needed and possible. Also detect copies. */
switch (opc) {
- CASE_OP_32_64(mov):
+ CASE_OP_32_64_VEC(mov):
tcg_opt_gen_mov(s, op, op->args[0], op->args[1]);
break;
CASE_OP_32_64(movi):
+ case INDEX_op_dupi_vec:
tcg_opt_gen_movi(s, op, op->args[0], op->args[1]);
break;
+ case INDEX_op_dup_vec:
+ if (arg_is_const(op->args[1])) {
+ tmp = arg_info(op->args[1])->val;
+ tmp = dup_const(TCGOP_VECE(op), tmp);
+ tcg_opt_gen_movi(s, op, op->args[0], tmp);
+ break;
+ }
+ goto do_default;
+
CASE_OP_32_64(not):
CASE_OP_32_64(neg):
CASE_OP_32_64(ext8s):
CASE_OP_32_64(ext16s):
CASE_OP_32_64(ext16u):
CASE_OP_32_64(ctpop):
+ CASE_OP_32_64(bswap16):
+ CASE_OP_32_64(bswap32):
+ case INDEX_op_bswap64_i64:
case INDEX_op_ext32s_i64:
case INDEX_op_ext32u_i64:
case INDEX_op_ext_i32_i64:
}
goto do_default;
+ CASE_OP_32_64(extract2):
+ if (arg_is_const(op->args[1]) && arg_is_const(op->args[2])) {
+ TCGArg v1 = arg_info(op->args[1])->val;
+ TCGArg v2 = arg_info(op->args[2])->val;
+
+ if (opc == INDEX_op_extract2_i64) {
+ tmp = (v1 >> op->args[3]) | (v2 << (64 - op->args[3]));
+ } else {
+ tmp = (v1 >> op->args[3]) | (v2 << (32 - op->args[3]));
+ tmp = (int32_t)tmp;
+ }
+ tcg_opt_gen_movi(s, op, op->args[0], tmp);
+ break;
+ }
+ goto do_default;
+
CASE_OP_32_64(setcond):
tmp = do_constant_folding_cond(opc, op->args[1],
op->args[2], op->args[3]);
uint64_t a = ((uint64_t)ah << 32) | al;
uint64_t b = ((uint64_t)bh << 32) | bl;
TCGArg rl, rh;
- TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32, 2);
+ TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32);
if (opc == INDEX_op_add2_i32) {
a += b;
uint32_t b = arg_info(op->args[3])->val;
uint64_t r = (uint64_t)a * b;
TCGArg rl, rh;
- TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32, 2);
+ TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32);
rl = op->args[0];
rh = op->args[1];
projects / mirror_qemu.git / blobdiff