fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-01-01 03:10:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

aco: fix is_vector_intact for GFX11 BVH

Browse source 
fossil-db (navi31):
Totals from 44 (0.06% of 79395) affected shaders:
Instrs: 1539111 -> 1539109 (-0.00%); split: -0.00%, +0.00%
CodeSize: 7880452 -> 7880380 (-0.00%); split: -0.00%, +0.00%
Latency: 7578794 -> 7578844 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 1450872 -> 1450876 (+0.00%); split: -0.00%, +0.00%
VClause: 40014 -> 40010 (-0.01%)
Copies: 116005 -> 116001 (-0.00%); split: -0.01%, +0.01%
VALU: 854630 -> 854626 (-0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31346>
This commit is contained in:
Rhys Perry 2024-09-25 12:12:56 +01:00 • committed by Marge Bot
parent 24c60be1ad
commit 96e7cd89ea
1 changed files with 11 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
src/amd/compiler/aco_register_allocation.cpp
View file

@ -1538,7 +1538,12 @@ compact_relocate_vars(ra_ctx& ctx, const std::vector<IDAndRegClass>& vars,
bool
is_vector_intact(ra_ctx& ctx, const RegisterFile& reg_file, const vector_info& vec_info)
{
unsigned size = 0;
for (unsigned i = 0; i < vec_info.num_parts; i++)
size += vec_info.parts[i].bytes();
PhysReg first{512};
int offset = 0;
for (unsigned i = 0; i < vec_info.num_parts; i++) {
Operand op = vec_info.parts[i];
@ -1547,21 +1552,23 @@ is_vector_intact(ra_ctx& ctx, const RegisterFile& reg_file, const vector_info& v
if (first.reg() == 512) {
PhysRegInterval bounds = get_reg_bounds(ctx, RegType::vgpr, false);
first = reg.advance(i * -4);
PhysRegInterval vec = PhysRegInterval{first, vec_info.num_parts};
first = reg.advance(-offset);
PhysRegInterval vec = PhysRegInterval{first, DIV_ROUND_UP(size, 4)};
if (!bounds.contains(vec)) /* not enough space for other operands */
return false;
} else {
if (reg != first.advance(i * 4)) /* not at the best position */
if (reg != first.advance(offset)) /* not at the best position */
return false;
}
} else {
/* If there's an unexpected temporary, this operand is unlikely to be
* placed in the best position.
*/
if (first.reg() != 512 && reg_file.test(first.advance(i * 4), 4))
if (first.reg() != 512 && reg_file.test(first.advance(offset), op.bytes()))
return false;
}
offset += op.bytes();
}
return true;