fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-20 22:30:12 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

aco: fix combining add/sub to b2i if a new dest needs to be allocated

Browse source 
The uses vector needs to be expanded to avoid out of bounds access
and to make sure the number of uses is initialized to 0.

This fixes combining more v_and(a, v_subbrev_co_u32).

fossilds-db (Vega10):
Totals from 4574 (3.28% of 139517) affected shaders:
SGPRs: 291625 -> 292217 (+0.20%); split: -0.01%, +0.21%
VGPRs: 276368 -> 276188 (-0.07%); split: -0.07%, +0.01%
SpillSGPRs: 455 -> 533 (+17.14%)
SpillVGPRs: 76 -> 78 (+2.63%)
CodeSize: 23327500 -> 23304152 (-0.10%); split: -0.17%, +0.07%
MaxWaves: 22044 -> 22066 (+0.10%)
Instrs: 4583064 -> 4576301 (-0.15%); split: -0.15%, +0.01%
Cycles: 47925276 -> 47871968 (-0.11%); split: -0.13%, +0.01%
VMEM: 1599363 -> 1597473 (-0.12%); split: +0.08%, -0.19%
SMEM: 331461 -> 331126 (-0.10%); split: +0.08%, -0.18%
VClause: 80639 -> 80696 (+0.07%); split: -0.02%, +0.09%
SClause: 155992 -> 155993 (+0.00%); split: -0.02%, +0.02%
Copies: 333482 -> 333318 (-0.05%); split: -0.12%, +0.07%
Branches: 70967 -> 70968 (+0.00%)
PreSGPRs: 187078 -> 187711 (+0.34%); split: -0.01%, +0.35%
PreVGPRs: 244918 -> 244785 (-0.05%)

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7513>
This commit is contained in:
Samuel Pitoiset 2020-11-09 19:42:22 +01:00
parent 7004548bdf
commit ec347ee9bc
2 changed files with 16 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
src/amd/compiler/aco_optimizer.cpp
View file

@ -2260,9 +2260,16 @@ bool combine_add_sub_b2i(opt_ctx& ctx, aco_ptr<Instruction>& instr, aco_opcode n
}
ctx.uses[instr->operands[i].tempId()]--;
new_instr->definitions[0] = instr->definitions[0];
new_instr->definitions[1] =
instr->definitions.size() == 2 ? instr->definitions[1] :
Definition(ctx.program->allocateTmp(ctx.program->lane_mask));
if (instr->definitions.size() == 2) {
new_instr->definitions[1] = instr->definitions[1];
} else {
new_instr->definitions[1] =
Definition(ctx.program->allocateTmp(ctx.program->lane_mask));
/* Make sure the uses vector is large enough and the number of
* uses properly initialized to 0.
*/
ctx.uses.push_back(0);
}
new_instr->definitions[1].setHint(vcc);
new_instr->operands[0] = Operand(0u);
new_instr->operands[1] = instr->operands[!i];

6
src/amd/compiler/tests/test_optimizer.cpp
View file

@ -119,6 +119,12 @@ BEGIN_TEST(optimize.cndmask)
Temp xor_a = bld.vop2(aco_opcode::v_xor_b32, bld.def(v1), inputs[0], subbrev);
writeout(3, bld.vop2(aco_opcode::v_and_b32, bld.def(v1), xor_a, subbrev));
//! v1: %res4 = v_cndmask_b32 0, %a, %c
//! p_unit_test 4, %res4
Temp cndmask = bld.vop2_e64(aco_opcode::v_cndmask_b32, bld.def(v1), Operand(0u), Operand(1u), Operand(inputs[2]));
Temp sub = bld.vsub32(bld.def(v1), Operand(0u), cndmask);
writeout(4, bld.vop2(aco_opcode::v_and_b32, bld.def(v1), Operand(inputs[0]), sub));
finish_opt_test();
}
END_TEST