fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-01-08 08:30:10 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

aco/ssa_elimination: also optimize branching sequence with s_and without saveexec

Browse source 
insert_exec will start using this in the future, handle it the same
just without the path to save exec before the v_cmpx instruction.

No Foz-DB changes.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31567>
This commit is contained in:
Georg Lehmann 2024-10-04 10:48:31 +02:00 • committed by Marge Bot
parent 68a372f6ce
commit 0338bb9ae8
1 changed files with 9 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/amd/compiler/aco_ssa_elimination.cpp
View file

@ -337,7 +337,15 @@ try_optimize_branching_sequence(ssa_elimination_ctx& ctx, Block& block, const in
const aco_opcode and_saveexec = ctx.program->lane_mask == s2 ? aco_opcode::s_and_saveexec_b64
: aco_opcode::s_and_saveexec_b32;
if (exec_copy->opcode != and_saveexec && exec_copy->opcode != aco_opcode::p_parallelcopy)
const aco_opcode s_and =
ctx.program->lane_mask == s2 ? aco_opcode::s_and_b64 : aco_opcode::s_and_b32;
if (exec_copy->opcode != and_saveexec && exec_copy->opcode != aco_opcode::p_parallelcopy &&
(exec_copy->opcode != s_and || exec_copy->operands[1].physReg() != exec))
return;
/* The SCC def of s_and/s_and_saveexec must be unused. */
if (exec_copy->opcode != aco_opcode::p_parallelcopy && !exec_copy->definitions[1].isKill())
return;
/* Only allow SALU with multiple definitions. */