fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-22 04:50:11 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

broadcom/compiler: try harder to merge thread switch earlier

Browse source 
We have been stopping as soon as we find a conflict but that doesn't
mean we can't merge it in an earlier slot, so keep going. Going by
shader-db, this sometimes allows us to merge the final thrsw a bit
earlier and avoid emitting NOP instructions at the program end to
make up for its delay slots. I have not observed cases where this
helps with regular thrsw though, but it doesn't hurt to try with
those too.

total instructions in shared programs: 11526876 -> 11526354 (<.01%)
instructions in affected programs: 10760 -> 10238 (-4.85%)
helped: 236
HURT: 0
Instructions are helped.

total max-temps in shared programs: 2231705 -> 2231677 (<.01%)
max-temps in affected programs: 276 -> 248 (-10.14%)
helped: 27
HURT: 0
Max-temps are helped.

total inst-and-stalls in shared programs: 11545177 -> 11544655 (<.01%)
inst-and-stalls in affected programs: 10777 -> 10255 (-4.84%)
helped: 236
HURT: 0
Inst-and-stalls are helped.

total nops in shared programs: 321624 -> 321152 (-0.15%)
nops in affected programs: 751 -> 279 (-62.85%)
helped: 236
HURT: 0
Nops are helped.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22679>
This commit is contained in:
Iago Toral Quiroga 2023-04-26 09:45:03 +02:00 • committed by Marge Bot
parent 13f258fae3
commit 0468ce3791
1 changed files with 22 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
src/broadcom/compiler/qpu_schedule.c
View file

@ -1766,12 +1766,6 @@ valid_thrsw_sequence(struct v3d_compile *c, struct choose_scoreboard *scoreboard
struct qinst *qinst, int instructions_in_sequence,
bool is_thrend)
{
/* No emitting our thrsw while the previous thrsw hasn't happened yet. */
if (scoreboard->last_thrsw_tick + 3 >
scoreboard->tick - instructions_in_sequence) {
return false;
}
for (int slot = 0; slot < instructions_in_sequence; slot++) {
if (!qpu_inst_before_thrsw_valid_in_delay_slot(c, qinst, slot))
return false;
@ -1825,13 +1819,28 @@ emit_thrsw(struct v3d_compile *c,
/* Find how far back into previous instructions we can put the THRSW. */
int slots_filled = 0;
int invalid_sig_count = 0;
int invalid_seq_count = 0;
bool last_thrsw_after_invalid_ok = false;
struct qinst *merge_inst = NULL;
vir_for_each_inst_rev(prev_inst, block) {
/* No emitting our thrsw while the previous thrsw hasn't
* happened yet.
*/
if (scoreboard->last_thrsw_tick + 3 >
scoreboard->tick - (slots_filled + 1)) {
break;
}
if (!valid_thrsw_sequence(c, scoreboard,
prev_inst, slots_filled + 1,
is_thrend)) {
break;
/* Even if the current sequence isn't valid, we may
* be able to get a valid sequence by trying to move the
* thrsw earlier, so keep going.
*/
invalid_seq_count++;
goto cont_block;
}
struct v3d_qpu_sig sig = prev_inst->qpu.sig;
@ -1858,8 +1867,10 @@ emit_thrsw(struct v3d_compile *c,
goto cont_block;
}
/* We can merge the thrsw in this instruction */
last_thrsw_after_invalid_ok = false;
invalid_sig_count = 0;
invalid_seq_count = 0;
merge_inst = prev_inst;
cont_block:
@ -1871,9 +1882,12 @@ cont_block:
* merge the thrsw in the end, we need to adjust slots filled to match
* the last valid merge point.
*/
assert(invalid_sig_count == 0 || slots_filled >= invalid_sig_count);
assert((invalid_sig_count == 0 && invalid_seq_count == 0) ||
slots_filled >= invalid_sig_count + invalid_seq_count);
if (invalid_sig_count > 0)
slots_filled -= invalid_sig_count;
if (invalid_seq_count > 0)
slots_filled -= invalid_seq_count;
bool needs_free = false;
if (merge_inst) {