From: Richard Henderson <rth@twiddle.net>
To: qemu-devel@nongnu.org
Cc: aurelien@aurel32.net
Subject: [Qemu-devel] [PATCH 09/16] tcg: Use per-temp state data in liveness
Date: Tue, 20 Jun 2017 19:48:24 -0700 [thread overview]
Message-ID: <20170621024831.26019-10-rth@twiddle.net> (raw)
In-Reply-To: <20170621024831.26019-1-rth@twiddle.net>
This avoids having to allocate external memory for each temporary.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/tcg.c | 232 ++++++++++++++++++++++++++++++--------------------------------
tcg/tcg.h | 6 ++
2 files changed, 120 insertions(+), 118 deletions(-)
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 0d758e4..e78140b 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1399,42 +1399,54 @@ TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *old_op,
/* liveness analysis: end of function: all temps are dead, and globals
should be in memory. */
-static inline void tcg_la_func_end(TCGContext *s, uint8_t *temp_state)
+static void tcg_la_func_end(TCGContext *s)
{
- memset(temp_state, TS_DEAD | TS_MEM, s->nb_globals);
- memset(temp_state + s->nb_globals, TS_DEAD, s->nb_temps - s->nb_globals);
+ int ng = s->nb_globals;
+ int nt = s->nb_temps;
+ int i;
+
+ for (i = 0; i < ng; ++i) {
+ s->temps[i].state = TS_DEAD | TS_MEM;
+ }
+ for (i = ng; i < nt; ++i) {
+ s->temps[i].state = TS_DEAD;
+ }
}
/* liveness analysis: end of basic block: all temps are dead, globals
and local temps should be in memory. */
-static inline void tcg_la_bb_end(TCGContext *s, uint8_t *temp_state)
+static void tcg_la_bb_end(TCGContext *s)
{
- int i, n;
+ int ng = s->nb_globals;
+ int nt = s->nb_temps;
+ int i;
- tcg_la_func_end(s, temp_state);
- for (i = s->nb_globals, n = s->nb_temps; i < n; i++) {
- if (s->temps[i].temp_local) {
- temp_state[i] |= TS_MEM;
- }
+ for (i = 0; i < ng; ++i) {
+ s->temps[i].state = TS_DEAD | TS_MEM;
+ }
+ for (i = ng; i < nt; ++i) {
+ s->temps[i].state = (s->temps[i].temp_local
+ ? TS_DEAD | TS_MEM
+ : TS_DEAD);
}
}
/* Liveness analysis : update the opc_arg_life array to tell if a
given input arguments is dead. Instructions updating dead
temporaries are removed. */
-static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
+static void liveness_pass_1(TCGContext *s)
{
int nb_globals = s->nb_globals;
int oi, oi_prev;
- tcg_la_func_end(s, temp_state);
+ tcg_la_func_end(s);
for (oi = s->gen_op_buf[0].prev; oi != 0; oi = oi_prev) {
int i, nb_iargs, nb_oargs;
TCGOpcode opc_new, opc_new2;
bool have_opc_new2;
TCGLifeData arg_life = 0;
- TCGArg arg;
+ TCGTemp *arg_ts;
TCGOp * const op = &s->gen_op_buf[oi];
TCGOpcode opc = op->opc;
@@ -1454,8 +1466,8 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
/* pure functions can be removed if their result is unused */
if (call_flags & TCG_CALL_NO_SIDE_EFFECTS) {
for (i = 0; i < nb_oargs; i++) {
- arg = op->args[i];
- if (temp_state[arg] != TS_DEAD) {
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts->state != TS_DEAD) {
goto do_not_remove_call;
}
}
@@ -1465,41 +1477,41 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
/* output args are dead */
for (i = 0; i < nb_oargs; i++) {
- arg = op->args[i];
- if (temp_state[arg] & TS_DEAD) {
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts->state & TS_DEAD) {
arg_life |= DEAD_ARG << i;
}
- if (temp_state[arg] & TS_MEM) {
+ if (arg_ts->state & TS_MEM) {
arg_life |= SYNC_ARG << i;
}
- temp_state[arg] = TS_DEAD;
+ arg_ts->state = TS_DEAD;
}
if (!(call_flags & (TCG_CALL_NO_WRITE_GLOBALS |
TCG_CALL_NO_READ_GLOBALS))) {
/* globals should go back to memory */
- memset(temp_state, TS_DEAD | TS_MEM, nb_globals);
+ for (i = 0; i < nb_globals; i++) {
+ s->temps[i].state = TS_DEAD | TS_MEM;
+ }
} else if (!(call_flags & TCG_CALL_NO_READ_GLOBALS)) {
/* globals should be synced to memory */
for (i = 0; i < nb_globals; i++) {
- temp_state[i] |= TS_MEM;
+ s->temps[i].state |= TS_MEM;
}
}
/* record arguments that die in this helper */
for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
- arg = op->args[i];
- if (arg != TCG_CALL_DUMMY_ARG) {
- if (temp_state[arg] & TS_DEAD) {
- arg_life |= DEAD_ARG << i;
- }
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts && arg_ts->state & TS_DEAD) {
+ arg_life |= DEAD_ARG << i;
}
}
/* input arguments are live for preceding opcodes */
for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
- arg = op->args[i];
- if (arg != TCG_CALL_DUMMY_ARG) {
- temp_state[arg] &= ~TS_DEAD;
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts) {
+ arg_ts->state &= ~TS_DEAD;
}
}
}
@@ -1509,7 +1521,7 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
break;
case INDEX_op_discard:
/* mark the temporary as dead */
- temp_state[op->args[0]] = TS_DEAD;
+ arg_temp(op->args[0])->state = TS_DEAD;
break;
case INDEX_op_add2_i32:
@@ -1530,8 +1542,8 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
the low part. The result can be optimized to a simple
add or sub. This happens often for x86_64 guest when the
cpu mode is set to 32 bit. */
- if (temp_state[op->args[1]] == TS_DEAD) {
- if (temp_state[op->args[0]] == TS_DEAD) {
+ if (arg_temp(op->args[1])->state == TS_DEAD) {
+ if (arg_temp(op->args[0])->state == TS_DEAD) {
goto do_remove;
}
/* Replace the opcode and adjust the args in place,
@@ -1568,8 +1580,8 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
do_mul2:
nb_iargs = 2;
nb_oargs = 2;
- if (temp_state[op->args[1]] == TS_DEAD) {
- if (temp_state[op->args[0]] == TS_DEAD) {
+ if (arg_temp(op->args[1])->state == TS_DEAD) {
+ if (arg_temp(op->args[0])->state == TS_DEAD) {
/* Both parts of the operation are dead. */
goto do_remove;
}
@@ -1577,7 +1589,7 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
op->opc = opc = opc_new;
op->args[1] = op->args[2];
op->args[2] = op->args[3];
- } else if (temp_state[op->args[0]] == TS_DEAD && have_opc_new2) {
+ } else if (arg_temp(op->args[0])->state == TS_DEAD && have_opc_new2) {
/* The low part of the operation is dead; generate the high. */
op->opc = opc = opc_new2;
op->args[0] = op->args[1];
@@ -1600,7 +1612,7 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
implies side effects */
if (!(def->flags & TCG_OPF_SIDE_EFFECTS) && nb_oargs != 0) {
for (i = 0; i < nb_oargs; i++) {
- if (temp_state[op->args[i]] != TS_DEAD) {
+ if (arg_temp(op->args[i])->state != TS_DEAD) {
goto do_not_remove;
}
}
@@ -1610,36 +1622,36 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
do_not_remove:
/* output args are dead */
for (i = 0; i < nb_oargs; i++) {
- arg = op->args[i];
- if (temp_state[arg] & TS_DEAD) {
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts->state & TS_DEAD) {
arg_life |= DEAD_ARG << i;
}
- if (temp_state[arg] & TS_MEM) {
+ if (arg_ts->state & TS_MEM) {
arg_life |= SYNC_ARG << i;
}
- temp_state[arg] = TS_DEAD;
+ arg_ts->state = TS_DEAD;
}
/* if end of basic block, update */
if (def->flags & TCG_OPF_BB_END) {
- tcg_la_bb_end(s, temp_state);
+ tcg_la_bb_end(s);
} else if (def->flags & TCG_OPF_SIDE_EFFECTS) {
/* globals should be synced to memory */
for (i = 0; i < nb_globals; i++) {
- temp_state[i] |= TS_MEM;
+ s->temps[i].state |= TS_MEM;
}
}
/* record arguments that die in this opcode */
for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
- arg = op->args[i];
- if (temp_state[arg] & TS_DEAD) {
+ arg_ts = arg_temp(op->args[i]);
+ if (arg_ts->state & TS_DEAD) {
arg_life |= DEAD_ARG << i;
}
}
/* input arguments are live for preceding opcodes */
for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
- temp_state[op->args[i]] &= ~TS_DEAD;
+ arg_temp(op->args[i])->state &= ~TS_DEAD;
}
}
break;
@@ -1649,16 +1661,12 @@ static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
}
/* Liveness analysis: Convert indirect regs to direct temporaries. */
-static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
+static bool liveness_pass_2(TCGContext *s)
{
int nb_globals = s->nb_globals;
- int16_t *dir_temps;
int i, oi, oi_next;
bool changes = false;
- dir_temps = tcg_malloc(nb_globals * sizeof(int16_t));
- memset(dir_temps, 0, nb_globals * sizeof(int16_t));
-
/* Create a temporary for each indirect global. */
for (i = 0; i < nb_globals; ++i) {
TCGTemp *its = &s->temps[i];
@@ -1666,19 +1674,19 @@ static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
TCGTemp *dts = tcg_temp_alloc(s);
dts->type = its->type;
dts->base_type = its->base_type;
- dir_temps[i] = temp_idx(s, dts);
+ its->state_ptr = dts;
}
+ /* All globals begin dead. */
+ its->state = TS_DEAD;
}
- memset(temp_state, TS_DEAD, nb_globals);
-
for (oi = s->gen_op_buf[0].next; oi != 0; oi = oi_next) {
TCGOp *op = &s->gen_op_buf[oi];
TCGOpcode opc = op->opc;
const TCGOpDef *def = &tcg_op_defs[opc];
TCGLifeData arg_life = op->life;
int nb_iargs, nb_oargs, call_flags;
- TCGArg arg, dir;
+ TCGTemp *arg_ts, *dir_ts;
oi_next = op->next;
@@ -1706,24 +1714,20 @@ static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
/* Make sure that input arguments are available. */
for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
- arg = op->args[i];
- /* Note this unsigned test catches TCG_CALL_ARG_DUMMY too. */
- if (arg < nb_globals) {
- dir = dir_temps[arg];
- if (dir != 0 && temp_state[arg] == TS_DEAD) {
- TCGTemp *its = arg_temp(arg);
- TCGOpcode lopc = (its->type == TCG_TYPE_I32
- ? INDEX_op_ld_i32
- : INDEX_op_ld_i64);
- TCGOp *lop = tcg_op_insert_before(s, op, lopc, 3);
-
- lop->args[0] = dir;
- lop->args[1] = temp_arg(its->mem_base);
- lop->args[2] = its->mem_offset;
-
- /* Loaded, but synced with memory. */
- temp_state[arg] = TS_MEM;
- }
+ arg_ts = arg_temp(op->args[i]);
+ dir_ts = arg_ts->state_ptr;
+ if (dir_ts && arg_ts->state == TS_DEAD) {
+ TCGOpcode lopc = (arg_ts->type == TCG_TYPE_I32
+ ? INDEX_op_ld_i32
+ : INDEX_op_ld_i64);
+ TCGOp *lop = tcg_op_insert_before(s, op, lopc, 3);
+
+ lop->args[0] = temp_arg(dir_ts);
+ lop->args[1] = temp_arg(arg_ts->mem_base);
+ lop->args[2] = arg_ts->mem_offset;
+
+ /* Loaded, but synced with memory. */
+ arg_ts->state = TS_MEM;
}
}
@@ -1731,15 +1735,13 @@ static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
No action is required except keeping temp_state up to date
so that we reload when needed. */
for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
- arg = op->args[i];
- if (arg < nb_globals) {
- dir = dir_temps[arg];
- if (dir != 0) {
- op->args[i] = dir;
- changes = true;
- if (IS_DEAD_ARG(i)) {
- temp_state[arg] = TS_DEAD;
- }
+ arg_ts = arg_temp(op->args[i]);
+ dir_ts = arg_ts->state_ptr;
+ if (dir_ts) {
+ op->args[i] = temp_arg(dir_ts);
+ changes = true;
+ if (IS_DEAD_ARG(i)) {
+ arg_ts->state = TS_DEAD;
}
}
}
@@ -1752,51 +1754,49 @@ static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
for (i = 0; i < nb_globals; ++i) {
/* Liveness should see that globals are synced back,
that is, either TS_DEAD or TS_MEM. */
- tcg_debug_assert(dir_temps[i] == 0
- || temp_state[i] != 0);
+ arg_ts = &s->temps[i];
+ tcg_debug_assert(arg_ts->state_ptr == 0
+ || arg_ts->state != 0);
}
} else {
for (i = 0; i < nb_globals; ++i) {
/* Liveness should see that globals are saved back,
that is, TS_DEAD, waiting to be reloaded. */
- tcg_debug_assert(dir_temps[i] == 0
- || temp_state[i] == TS_DEAD);
+ arg_ts = &s->temps[i];
+ tcg_debug_assert(arg_ts->state_ptr == 0
+ || arg_ts->state == TS_DEAD);
}
}
/* Outputs become available. */
for (i = 0; i < nb_oargs; i++) {
- arg = op->args[i];
- if (arg >= nb_globals) {
- continue;
- }
- dir = dir_temps[arg];
- if (dir == 0) {
+ arg_ts = arg_temp(op->args[i]);
+ dir_ts = arg_ts->state_ptr;
+ if (!dir_ts) {
continue;
}
- op->args[i] = dir;
+ op->args[i] = temp_arg(dir_ts);
changes = true;
/* The output is now live and modified. */
- temp_state[arg] = 0;
+ arg_ts->state = 0;
/* Sync outputs upon their last write. */
if (NEED_SYNC_ARG(i)) {
- TCGTemp *its = arg_temp(arg);
- TCGOpcode sopc = (its->type == TCG_TYPE_I32
+ TCGOpcode sopc = (arg_ts->type == TCG_TYPE_I32
? INDEX_op_st_i32
: INDEX_op_st_i64);
TCGOp *sop = tcg_op_insert_after(s, op, sopc, 3);
- sop->args[0] = dir;
- sop->args[1] = temp_arg(its->mem_base);
- sop->args[2] = its->mem_offset;
+ sop->args[0] = temp_arg(dir_ts);
+ sop->args[1] = temp_arg(arg_ts->mem_base);
+ sop->args[2] = arg_ts->mem_offset;
- temp_state[arg] = TS_MEM;
+ arg_ts->state = TS_MEM;
}
/* Drop outputs that are dead. */
if (IS_DEAD_ARG(i)) {
- temp_state[arg] = TS_DEAD;
+ arg_ts->state = TS_DEAD;
}
}
}
@@ -2569,27 +2569,23 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)
s->la_time -= profile_getclock();
#endif
- {
- uint8_t *temp_state = tcg_malloc(s->nb_temps + s->nb_indirects);
-
- liveness_pass_1(s, temp_state);
+ liveness_pass_1(s);
- if (s->nb_indirects > 0) {
+ if (s->nb_indirects > 0) {
#ifdef DEBUG_DISAS
- if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND)
- && qemu_log_in_addr_range(tb->pc))) {
- qemu_log_lock();
- qemu_log("OP before indirect lowering:\n");
- tcg_dump_ops(s);
- qemu_log("\n");
- qemu_log_unlock();
- }
+ if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND)
+ && qemu_log_in_addr_range(tb->pc))) {
+ qemu_log_lock();
+ qemu_log("OP before indirect lowering:\n");
+ tcg_dump_ops(s);
+ qemu_log("\n");
+ qemu_log_unlock();
+ }
#endif
- /* Replace indirect temps with direct temps. */
- if (liveness_pass_2(s, temp_state)) {
- /* If changes were made, re-run liveness. */
- liveness_pass_1(s, temp_state);
- }
+ /* Replace indirect temps with direct temps. */
+ if (liveness_pass_2(s)) {
+ /* If changes were made, re-run liveness. */
+ liveness_pass_1(s);
}
}
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 80012b5..1eeeca5 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -599,6 +599,12 @@ typedef struct TCGTemp {
struct TCGTemp *mem_base;
intptr_t mem_offset;
const char *name;
+
+ /* Pass-specific information that can be stored for a temporary.
+ One word worth of integer data, and one pointer to data
+ allocated separately. */
+ uintptr_t state;
+ void *state_ptr;
} TCGTemp;
typedef struct TCGContext TCGContext;
--
2.9.4
next prev parent reply other threads:[~2017-06-21 2:48 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-21 2:48 [Qemu-devel] [PATCH 00/16] Cleanups within TCG middle-end Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 01/16] tcg: Merge opcode arguments into TCGOp Richard Henderson
2017-06-26 14:44 ` Alex Bennée
2017-06-26 14:55 ` Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 02/16] tcg: Propagate args to op->args in optimizer Richard Henderson
2017-06-26 14:53 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 03/16] tcg: Propagate args to op->args in tcg.c Richard Henderson
2017-06-26 15:02 ` Alex Bennée
2017-06-26 15:07 ` Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 04/16] tcg: Propagate TCGOp down to allocators Richard Henderson
2017-06-26 15:08 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 05/16] tcg: Introduce arg_temp Richard Henderson
2017-06-26 16:37 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 06/16] tcg: Add temp_global bit to TCGTemp Richard Henderson
2017-06-27 8:39 ` Alex Bennée
2017-06-27 16:17 ` Richard Henderson
2017-06-28 8:52 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 07/16] tcg: Return NULL temp for TCG_CALL_DUMMY_ARG Richard Henderson
2017-06-27 8:47 ` Alex Bennée
2017-06-27 16:36 ` Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 08/16] tcg: Introduce temp_arg Richard Henderson
2017-06-21 2:48 ` Richard Henderson [this message]
2017-06-27 8:57 ` [Qemu-devel] [PATCH 09/16] tcg: Use per-temp state data in liveness Alex Bennée
2017-06-27 16:39 ` Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 10/16] tcg: Avoid loops against variable bounds Richard Henderson
2017-06-27 9:01 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 11/16] tcg: Change temp_allocate_frame arg to TCGTemp Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 12/16] tcg: Remove unused TCG_CALL_DUMMY_TCGV Richard Henderson
2017-06-27 9:42 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 13/16] tcg: Export temp_idx Richard Henderson
2017-06-27 9:46 ` Alex Bennée
2017-06-27 16:43 ` Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 14/16] tcg: Use per-temp state data in optimize Richard Henderson
2017-06-27 9:59 ` Alex Bennée
2017-06-21 2:48 ` [Qemu-devel] [PATCH 15/16] tcg: Define separate structures for TCGv_* Richard Henderson
2017-06-21 2:48 ` [Qemu-devel] [PATCH 16/16] tcg: Store pointers to temporaries directly in TCGArg Richard Henderson
2017-06-21 3:43 ` [Qemu-devel] [PATCH 00/16] Cleanups within TCG middle-end no-reply
2017-06-26 16:49 ` Alex Bennée
2017-06-26 17:47 ` Richard Henderson
2017-06-26 19:19 ` Alex Bennée
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=20170621024831.26019-10-rth@twiddle.net \
--to=rth@twiddle.net \
--cc=aurelien@aurel32.net \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.