aco: propagate SGPRs into VOP1 instructions early.
This helps DCE. We should reconsider our optimization order or maybe do the dead code analysis twice Totals from 106 (0.08% of 136546) affected shaders (RAVEN): SGPRs: 7184 -> 7152 (-0.45%) CodeSize: 736912 -> 736052 (-0.12%) Instrs: 145739 -> 145509 (-0.16%) Cycles: 2085344 -> 2084268 (-0.05%) VMEM: 14819 -> 14807 (-0.08%) SMEM: 7109 -> 7100 (-0.13%); split: +0.04%, -0.17% SClause: 5383 -> 5385 (+0.04%) Copies: 13290 -> 13189 (-0.76%) PreSGPRs: 5265 -> 5221 (-0.84%) Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6777>
This commit is contained in:
parent
3424e17b9a
commit
d887eb141b
|
@ -877,6 +877,11 @@ void label_instruction(opt_ctx &ctx, Block& block, aco_ptr<Instruction>& instr)
|
|||
instr->operands[i].setTemp(info.temp);
|
||||
info = ctx.info[info.temp.id()];
|
||||
}
|
||||
/* applying SGPRs to VOP1 doesn't increase code size and DCE is helped by doing it earlier */
|
||||
if (info.is_temp() && info.temp.type() == RegType::sgpr && can_apply_sgprs(instr) && instr->operands.size() == 1) {
|
||||
instr->operands[i].setTemp(info.temp);
|
||||
info = ctx.info[info.temp.id()];
|
||||
}
|
||||
|
||||
/* for instructions other than v_cndmask_b32, the size of the instruction should match the operand size */
|
||||
unsigned can_use_mod = instr->opcode != aco_opcode::v_cndmask_b32 || instr->operands[i].getTemp().bytes() == 4;
|
||||
|
|
Loading…
Reference in New Issue