tcg/optimize: Split out OptContext

Provide what will become a larger context for splitting
the very large tcg_optimize function.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Luis Pires <luis.pires@eldorado.org.br>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2021-08-23 22:06:31 -07:00
parent b1fde411d0
commit 3b3f847d75

View File

@ -44,6 +44,10 @@ typedef struct TempOptInfo {
uint64_t z_mask; /* mask bit is 0 if and only if value bit is 0 */
} TempOptInfo;
typedef struct OptContext {
TCGTempSet temps_used;
} OptContext;
static inline TempOptInfo *ts_info(TCGTemp *ts)
{
return ts->state_ptr;
@ -90,15 +94,15 @@ static void reset_temp(TCGArg arg)
}
/* Initialize and activate a temporary. */
static void init_ts_info(TCGTempSet *temps_used, TCGTemp *ts)
static void init_ts_info(OptContext *ctx, TCGTemp *ts)
{
size_t idx = temp_idx(ts);
TempOptInfo *ti;
if (test_bit(idx, temps_used->l)) {
if (test_bit(idx, ctx->temps_used.l)) {
return;
}
set_bit(idx, temps_used->l);
set_bit(idx, ctx->temps_used.l);
ti = ts->state_ptr;
if (ti == NULL) {
@ -122,9 +126,9 @@ static void init_ts_info(TCGTempSet *temps_used, TCGTemp *ts)
}
}
static void init_arg_info(TCGTempSet *temps_used, TCGArg arg)
static void init_arg_info(OptContext *ctx, TCGArg arg)
{
init_ts_info(temps_used, arg_temp(arg));
init_ts_info(ctx, arg_temp(arg));
}
static TCGTemp *find_better_copy(TCGContext *s, TCGTemp *ts)
@ -229,7 +233,7 @@ static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, TCGArg dst, TCGArg src)
}
}
static void tcg_opt_gen_movi(TCGContext *s, TCGTempSet *temps_used,
static void tcg_opt_gen_movi(TCGContext *s, OptContext *ctx,
TCGOp *op, TCGArg dst, uint64_t val)
{
const TCGOpDef *def = &tcg_op_defs[op->opc];
@ -246,7 +250,7 @@ static void tcg_opt_gen_movi(TCGContext *s, TCGTempSet *temps_used,
/* Convert movi to mov with constant temp. */
tv = tcg_constant_internal(type, val);
init_ts_info(temps_used, tv);
init_ts_info(ctx, tv);
tcg_opt_gen_mov(s, op, dst, temp_arg(tv));
}
@ -605,7 +609,7 @@ void tcg_optimize(TCGContext *s)
{
int nb_temps, nb_globals, i;
TCGOp *op, *op_next, *prev_mb = NULL;
TCGTempSet temps_used;
OptContext ctx = {};
/* Array VALS has an element for each temp.
If this temp holds a constant then its value is kept in VALS' element.
@ -615,7 +619,6 @@ void tcg_optimize(TCGContext *s)
nb_temps = s->nb_temps;
nb_globals = s->nb_globals;
memset(&temps_used, 0, sizeof(temps_used));
for (i = 0; i < nb_temps; ++i) {
s->temps[i].state_ptr = NULL;
}
@ -634,14 +637,14 @@ void tcg_optimize(TCGContext *s)
for (i = 0; i < nb_oargs + nb_iargs; i++) {
TCGTemp *ts = arg_temp(op->args[i]);
if (ts) {
init_ts_info(&temps_used, ts);
init_ts_info(&ctx, ts);
}
}
} else {
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
for (i = 0; i < nb_oargs + nb_iargs; i++) {
init_arg_info(&temps_used, op->args[i]);
init_arg_info(&ctx, op->args[i]);
}
}
@ -720,7 +723,7 @@ void tcg_optimize(TCGContext *s)
CASE_OP_32_64(rotr):
if (arg_is_const(op->args[1])
&& arg_info(op->args[1])->val == 0) {
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], 0);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], 0);
continue;
}
break;
@ -1085,7 +1088,7 @@ void tcg_optimize(TCGContext *s)
if (partmask == 0) {
tcg_debug_assert(nb_oargs == 1);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], 0);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], 0);
continue;
}
if (affected == 0) {
@ -1102,7 +1105,7 @@ void tcg_optimize(TCGContext *s)
CASE_OP_32_64(mulsh):
if (arg_is_const(op->args[2])
&& arg_info(op->args[2])->val == 0) {
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], 0);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], 0);
continue;
}
break;
@ -1129,7 +1132,7 @@ void tcg_optimize(TCGContext *s)
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, &temps_used, op, op->args[0], 0);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], 0);
continue;
}
break;
@ -1149,7 +1152,7 @@ void tcg_optimize(TCGContext *s)
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, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1157,7 +1160,7 @@ void tcg_optimize(TCGContext *s)
case INDEX_op_dup2_vec:
assert(TCG_TARGET_REG_BITS == 32);
if (arg_is_const(op->args[1]) && arg_is_const(op->args[2])) {
tcg_opt_gen_movi(s, &temps_used, op, op->args[0],
tcg_opt_gen_movi(s, &ctx, op, op->args[0],
deposit64(arg_info(op->args[1])->val, 32, 32,
arg_info(op->args[2])->val));
break;
@ -1183,7 +1186,7 @@ void tcg_optimize(TCGContext *s)
case INDEX_op_extrh_i64_i32:
if (arg_is_const(op->args[1])) {
tmp = do_constant_folding(opc, arg_info(op->args[1])->val, 0);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1194,7 +1197,7 @@ void tcg_optimize(TCGContext *s)
if (arg_is_const(op->args[1])) {
tmp = do_constant_folding(opc, arg_info(op->args[1])->val,
op->args[2]);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1224,7 +1227,7 @@ void tcg_optimize(TCGContext *s)
if (arg_is_const(op->args[1]) && arg_is_const(op->args[2])) {
tmp = do_constant_folding(opc, arg_info(op->args[1])->val,
arg_info(op->args[2])->val);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1235,7 +1238,7 @@ void tcg_optimize(TCGContext *s)
TCGArg v = arg_info(op->args[1])->val;
if (v != 0) {
tmp = do_constant_folding(opc, v, 0);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
} else {
tcg_opt_gen_mov(s, op, op->args[0], op->args[2]);
}
@ -1248,7 +1251,7 @@ void tcg_optimize(TCGContext *s)
tmp = deposit64(arg_info(op->args[1])->val,
op->args[3], op->args[4],
arg_info(op->args[2])->val);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1257,7 +1260,7 @@ void tcg_optimize(TCGContext *s)
if (arg_is_const(op->args[1])) {
tmp = extract64(arg_info(op->args[1])->val,
op->args[2], op->args[3]);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1266,7 +1269,7 @@ void tcg_optimize(TCGContext *s)
if (arg_is_const(op->args[1])) {
tmp = sextract64(arg_info(op->args[1])->val,
op->args[2], op->args[3]);
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1283,7 +1286,7 @@ void tcg_optimize(TCGContext *s)
tmp = (int32_t)(((uint32_t)v1 >> shr) |
((uint32_t)v2 << (32 - shr)));
}
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1292,7 +1295,7 @@ void tcg_optimize(TCGContext *s)
tmp = do_constant_folding_cond(opc, op->args[1],
op->args[2], op->args[3]);
if (tmp != 2) {
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
break;
}
goto do_default;
@ -1302,7 +1305,7 @@ void tcg_optimize(TCGContext *s)
op->args[1], op->args[2]);
if (tmp != 2) {
if (tmp) {
memset(&temps_used, 0, sizeof(temps_used));
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
op->opc = INDEX_op_br;
op->args[0] = op->args[3];
} else {
@ -1358,8 +1361,8 @@ void tcg_optimize(TCGContext *s)
rl = op->args[0];
rh = op->args[1];
tcg_opt_gen_movi(s, &temps_used, op, rl, (int32_t)a);
tcg_opt_gen_movi(s, &temps_used, op2, rh, (int32_t)(a >> 32));
tcg_opt_gen_movi(s, &ctx, op, rl, (int32_t)a);
tcg_opt_gen_movi(s, &ctx, op2, rh, (int32_t)(a >> 32));
break;
}
goto do_default;
@ -1374,8 +1377,8 @@ void tcg_optimize(TCGContext *s)
rl = op->args[0];
rh = op->args[1];
tcg_opt_gen_movi(s, &temps_used, op, rl, (int32_t)r);
tcg_opt_gen_movi(s, &temps_used, op2, rh, (int32_t)(r >> 32));
tcg_opt_gen_movi(s, &ctx, op, rl, (int32_t)r);
tcg_opt_gen_movi(s, &ctx, op2, rh, (int32_t)(r >> 32));
break;
}
goto do_default;
@ -1386,7 +1389,7 @@ void tcg_optimize(TCGContext *s)
if (tmp != 2) {
if (tmp) {
do_brcond_true:
memset(&temps_used, 0, sizeof(temps_used));
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
op->opc = INDEX_op_br;
op->args[0] = op->args[5];
} else {
@ -1402,7 +1405,7 @@ void tcg_optimize(TCGContext *s)
/* Simplify LT/GE comparisons vs zero to a single compare
vs the high word of the input. */
do_brcond_high:
memset(&temps_used, 0, sizeof(temps_used));
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
op->opc = INDEX_op_brcond_i32;
op->args[0] = op->args[1];
op->args[1] = op->args[3];
@ -1428,7 +1431,7 @@ void tcg_optimize(TCGContext *s)
goto do_default;
}
do_brcond_low:
memset(&temps_used, 0, sizeof(temps_used));
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
op->opc = INDEX_op_brcond_i32;
op->args[1] = op->args[2];
op->args[2] = op->args[4];
@ -1463,7 +1466,7 @@ void tcg_optimize(TCGContext *s)
op->args[5]);
if (tmp != 2) {
do_setcond_const:
tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
tcg_opt_gen_movi(s, &ctx, op, op->args[0], tmp);
} else if ((op->args[5] == TCG_COND_LT
|| op->args[5] == TCG_COND_GE)
&& arg_is_const(op->args[3])
@ -1533,7 +1536,7 @@ void tcg_optimize(TCGContext *s)
if (!(tcg_call_flags(op)
& (TCG_CALL_NO_READ_GLOBALS | TCG_CALL_NO_WRITE_GLOBALS))) {
for (i = 0; i < nb_globals; i++) {
if (test_bit(i, temps_used.l)) {
if (test_bit(i, ctx.temps_used.l)) {
reset_ts(&s->temps[i]);
}
}
@ -1548,7 +1551,7 @@ void tcg_optimize(TCGContext *s)
block, otherwise we only trash the output args. "z_mask" is
the non-zero bits mask for the first output arg. */
if (def->flags & TCG_OPF_BB_END) {
memset(&temps_used, 0, sizeof(temps_used));
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
} else {
do_reset_output:
for (i = 0; i < nb_oargs; i++) {