fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-02-22 01:10:32 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

aco: form mixed MTBUF/MUBUF clauses

Browse source 
This should be one clause (all of the instructions load from the same vertex buffer)

s_clause 0x2                                                ; bfa10002
tbuffer_load_format_xyzw v[8:11], v5, s[4:7], 0 format:[BUF_FMT_8_8_8_8_UNORM] idxen offset:36 ; e9c32024 80010805
tbuffer_load_format_xyzw v[12:15], v5, s[4:7], 0 format:[BUF_FMT_8_8_8_8_UNORM] idxen offset:16 ; e9c32010 80010c05
tbuffer_load_format_xyzw v[16:19], v5, s[4:7], 0 format:[BUF_FMT_8_8_8_8_UNORM] idxen offset:12 ; e9c3200c 80011005
s_clause 0x2                                                ; bfa10002
buffer_load_dwordx3 v[20:22], v5, s[4:7], 0 idxen           ; e03c2000 80011405
buffer_load_dwordx3 v[23:25], v5, s[4:7], 0 idxen offset:20 ; e03c2014 80011705
buffer_load_dwordx4 v[28:31], v5, s[4:7], 0 idxen offset:48 ; e0382030 80011c05
tbuffer_load_format_xy v[0:1], v5, s[4:7], 0 format:[BUF_FMT_8_8_UNORM] idxen offset:32 ; e8712020 80010005

Foz-DB Navi21:
Totals from 5624 (7.08% of 79395) affected shaders:
MaxWaves: 149894 -> 149898 (+0.00%)
Instrs: 3032697 -> 3034853 (+0.07%); split: -0.05%, +0.12%
CodeSize: 15907852 -> 15915752 (+0.05%); split: -0.05%, +0.10%
VGPRs: 216248 -> 216144 (-0.05%)
Latency: 10955137 -> 11008760 (+0.49%); split: -0.22%, +0.70%
InvThroughput: 2032857 -> 2033916 (+0.05%); split: -0.03%, +0.08%
VClause: 50120 -> 41778 (-16.64%); split: -16.66%, +0.02%
SClause: 62034 -> 62004 (-0.05%); split: -0.33%, +0.29%
Copies: 253836 -> 254505 (+0.26%); split: -0.17%, +0.43%
VALU: 1621606 -> 1622274 (+0.04%); split: -0.03%, +0.07%
SALU: 653251 -> 653252 (+0.00%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34379>
This commit is contained in:
Georg Lehmann 2025-01-21 01:12:58 +01:00 • committed by Marge Bot
parent babe7f3e12
commit 64cae5c48d
2 changed files with 13 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
src/amd/compiler/aco_ir.cpp
View file

@ -1380,8 +1380,11 @@ should_form_clause(const Instruction* a, const Instruction* b)
if (a->definitions.empty() != b->definitions.empty())
return false;
if (a->format != b->format)
/* MUBUF and MTBUF can appear in the same clause. */
if ((a->isMTBUF() && b->isMUBUF()) || (a->isMUBUF() && b->isMTBUF())) {
} else if (a->format != b->format) {
return false;
}
if (a->operands.empty() || b->operands.empty())
return false;

12
src/amd/compiler/tests/test_hard_clause.cpp
View file

@ -282,16 +282,22 @@ BEGIN_TEST(form_hard_clauses.heuristic)
create_smem_buffer(buf_desc0);
create_smem();
/* Only form clause between MUBUF and MTBUF if they load from the same binding. Ignore descriptor
* if they're te same binding.
*/
/* Form clause with MTBUF/MUBUF mix if they use the same descriptor. */
//>> p_unit_test 7
//! s_clause imm:1
//; search_re('buffer_load_dword')
//; search_re('tbuffer_load_format_x')
bld.pseudo(aco_opcode::p_unit_test, Operand::c32(7u));
create_mubuf(buf_desc0);
create_mtbuf(buf_desc0);
//>> p_unit_test 8
//; search_re('buffer_load_dword')
//; search_re('tbuffer_load_format_x')
bld.pseudo(aco_opcode::p_unit_test, Operand::c32(8u));
create_mubuf(buf_desc0);
create_mtbuf(buf_desc1);
finish_form_hard_clause_test();
END_TEST