From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PATCH v2 02/48] tcg/optimize: Split out OptContext
Date: Thu, 7 Oct 2021 12:54:10 -0700 [thread overview]
Message-ID: <20211007195456.1168070-3-richard.henderson@linaro.org> (raw)
In-Reply-To: <20211007195456.1168070-1-richard.henderson@linaro.org>
Provide what will become a larger context for splitting
the very large tcg_optimize function.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/optimize.c | 77 ++++++++++++++++++++++++++------------------------
1 file changed, 40 insertions(+), 37 deletions(-)
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 148e360fc6..b76991215e 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -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++) {
--
2.25.1
next prev parent reply other threads:[~2021-10-07 19:57 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-07 19:54 [PATCH v2 00/48] tcg: optimize redundant sign extensions Richard Henderson
2021-10-07 19:54 ` [PATCH v2 01/48] tcg/optimize: Rename "mask" to "z_mask" Richard Henderson
2021-10-19 15:23 ` Alex Bennée
2021-10-20 22:26 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` Richard Henderson [this message]
2021-10-19 15:25 ` [PATCH v2 02/48] tcg/optimize: Split out OptContext Alex Bennée
2021-10-19 15:37 ` Richard Henderson
2021-10-20 22:26 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 03/48] tcg/optimize: Remove do_default label Richard Henderson
2021-10-19 15:37 ` Alex Bennée
2021-10-20 22:26 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 04/48] tcg/optimize: Change tcg_opt_gen_{mov, movi} interface Richard Henderson
2021-10-19 15:38 ` Alex Bennée
2021-10-20 22:26 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 05/48] tcg/optimize: Move prev_mb into OptContext Richard Henderson
2021-10-19 15:44 ` Alex Bennée
2021-10-19 15:59 ` Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 06/48] tcg/optimize: Split out init_arguments Richard Henderson
2021-10-19 16:13 ` Alex Bennée
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 07/48] tcg/optimize: Split out copy_propagate Richard Henderson
2021-10-20 16:01 ` Alex Bennée
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 08/48] tcg/optimize: Split out fold_call Richard Henderson
2021-10-20 16:05 ` Alex Bennée
2021-10-21 2:04 ` Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 09/48] tcg/optimize: Drop nb_oargs, nb_iargs locals Richard Henderson
2021-10-20 16:17 ` Alex Bennée
2021-10-21 2:09 ` Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 10/48] tcg/optimize: Change fail return for do_constant_folding_cond* Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 11/48] tcg/optimize: Return true from tcg_opt_gen_{mov, movi} Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 12/48] tcg/optimize: Split out finish_folding Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 13/48] tcg/optimize: Use a boolean to avoid a mass of continues Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 14/48] tcg/optimize: Split out fold_mb, fold_qemu_{ld,st} Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 15/48] tcg/optimize: Split out fold_const{1,2} Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 16/48] tcg/optimize: Split out fold_setcond2 Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 17/48] tcg/optimize: Split out fold_brcond2 Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-21 2:32 ` Richard Henderson
2021-10-07 19:54 ` [PATCH v2 18/48] tcg/optimize: Split out fold_brcond Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 19/48] tcg/optimize: Split out fold_setcond Richard Henderson
2021-10-20 22:27 ` Luis Fernando Fujita Pires
2021-10-07 19:54 ` [PATCH v2 20/48] tcg/optimize: Split out fold_mulu2_i32 Richard Henderson
2021-10-07 19:54 ` [PATCH v2 21/48] tcg/optimize: Split out fold_addsub2_i32 Richard Henderson
2021-10-07 19:54 ` [PATCH v2 22/48] tcg/optimize: Split out fold_movcond Richard Henderson
2021-10-07 19:54 ` [PATCH v2 23/48] tcg/optimize: Split out fold_extract2 Richard Henderson
2021-10-07 19:54 ` [PATCH v2 24/48] tcg/optimize: Split out fold_extract, fold_sextract Richard Henderson
2021-10-07 19:54 ` [PATCH v2 25/48] tcg/optimize: Split out fold_deposit Richard Henderson
2021-10-07 19:54 ` [PATCH v2 26/48] tcg/optimize: Split out fold_count_zeros Richard Henderson
2021-10-07 19:54 ` [PATCH v2 27/48] tcg/optimize: Split out fold_bswap Richard Henderson
2021-10-07 19:54 ` [PATCH v2 28/48] tcg/optimize: Split out fold_dup, fold_dup2 Richard Henderson
2021-10-07 19:54 ` [PATCH v2 29/48] tcg/optimize: Split out fold_mov Richard Henderson
2021-10-07 19:54 ` [PATCH v2 30/48] tcg/optimize: Split out fold_xx_to_i Richard Henderson
2021-10-07 19:54 ` [PATCH v2 31/48] tcg/optimize: Split out fold_xx_to_x Richard Henderson
2021-10-07 19:54 ` [PATCH v2 32/48] tcg/optimize: Split out fold_xi_to_i Richard Henderson
2021-10-07 19:54 ` [PATCH v2 33/48] tcg/optimize: Add type to OptContext Richard Henderson
2021-10-07 19:54 ` [PATCH v2 34/48] tcg/optimize: Split out fold_to_not Richard Henderson
2021-10-07 19:54 ` [PATCH v2 35/48] tcg/optimize: Split out fold_sub_to_neg Richard Henderson
2021-10-07 19:54 ` [PATCH v2 36/48] tcg/optimize: Split out fold_xi_to_x Richard Henderson
2021-10-07 19:54 ` [PATCH v2 37/48] tcg/optimize: Split out fold_ix_to_i Richard Henderson
2021-10-07 19:54 ` [PATCH v2 38/48] tcg/optimize: Split out fold_masks Richard Henderson
2021-10-07 19:54 ` [PATCH v2 39/48] tcg/optimize: Expand fold_mulu2_i32 to all 4-arg multiplies Richard Henderson
2021-10-07 19:54 ` [PATCH v2 40/48] tcg/optimize: Expand fold_addsub2_i32 to 64-bit ops Richard Henderson
2021-10-19 15:34 ` Alex Bennée
2021-10-19 16:01 ` Richard Henderson
2021-10-07 19:54 ` [PATCH v2 41/48] tcg/optimize: Sink commutative operand swapping into fold functions Richard Henderson
2021-10-07 19:54 ` [PATCH v2 42/48] tcg/optimize: Add more simplifications for orc Richard Henderson
2021-10-07 19:54 ` [PATCH v2 43/48] tcg/optimize: Stop forcing z_mask to "garbage" for 32-bit values Richard Henderson
2021-10-07 19:54 ` [PATCH v2 44/48] tcg/optimize: Optimize sign extensions Richard Henderson
2021-10-07 19:54 ` [PATCH v2 45/48] tcg/optimize: Propagate sign info for logical operations Richard Henderson
2021-10-07 19:54 ` [PATCH v2 46/48] tcg/optimize: Propagate sign info for setcond Richard Henderson
2021-10-07 19:54 ` [PATCH v2 47/48] tcg/optimize: Propagate sign info for bit counting Richard Henderson
2021-10-07 19:54 ` [PATCH v2 48/48] tcg/optimize: Propagate sign info for shifting Richard Henderson
2021-10-15 23:41 ` [PATCH v2 00/48] tcg: optimize redundant sign extensions Richard Henderson
2021-10-20 16:13 ` Alex Bennée
2021-10-20 23:50 ` Richard Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211007195456.1168070-3-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).