OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

broadcom/compiler: don't spill in between multop and umul24

Browse Source 
The multop instruction implicitly writes rtop which is not preserved
acrosss thread switches. We can spill the sources of the multop
(since these would happen before multop) and the destination of
umul24 (since that would happen after umul24).

Fixes some OpenCL tests when V3D_DEBUG=opt_compile_time is used to
choose a different compile configuration.

cc: mesa-stable

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29909>
This commit is contained in:
Iago Toral Quiroga
2024-06-26 08:06:33 +02:00
committed by Marge Bot
parent da1a7c04bc
commit 38b7f411a1
1 changed files with 20 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/broadcom/compiler/vir_register_allocate.c
View File

@@ -271,6 +271,7 @@ v3d_choose_spill_node(struct v3d_compile *c)
float block_scale = 1.0;
float spill_costs[c->num_temps];
bool in_tmu_operation = false;
bool rtop_hazard = false;
bool started_last_seg = false;
for (unsigned i = 0; i < c->num_temps; i++)
@@ -279,6 +280,20 @@ v3d_choose_spill_node(struct v3d_compile *c)
/* XXX: Scale the cost up when inside of a loop. */
vir_for_each_block(block, c) {
vir_for_each_inst(inst, block) {
/* RTOP is not preserved across thread switches, so
* we can't spill in the middle of multop + umul24.
*/
bool is_multop = false;
bool is_umul24 = false;
if (inst->qpu.type == V3D_QPU_INSTR_TYPE_ALU) {
if (inst->qpu.alu.mul.op == V3D_QPU_M_MULTOP) {
is_multop = true;
rtop_hazard = true;
} else if (inst->qpu.alu.mul.op == V3D_QPU_M_UMUL24) {
is_umul24 = true;
}
}
/* We can't insert new thread switches after
* starting output writes.
*/
@@ -297,7 +312,7 @@ v3d_choose_spill_node(struct v3d_compile *c)
if (spill_type != SPILL_TYPE_TMU) {
spill_costs[temp] += block_scale;
} else if (!no_spilling) {
} else if (!no_spilling && (!rtop_hazard || is_multop)) {
float tmu_op_scale = in_tmu_operation ?
3.0 : 1.0;
spill_costs[temp] += (block_scale *
@@ -315,7 +330,7 @@ v3d_choose_spill_node(struct v3d_compile *c)
if (spill_type != SPILL_TYPE_TMU) {
/* We just rematerialize it later */
} else if (!no_spilling) {
} else if (!no_spilling && (!rtop_hazard || is_umul24)) {
spill_costs[temp] += (block_scale *
tmu_scale);
} else {
@@ -344,6 +359,9 @@ v3d_choose_spill_node(struct v3d_compile *c)
if (qinst_writes_tmu(c->devinfo, inst))
in_tmu_operation = true;
if (is_umul24)
rtop_hazard = false;
}
}