fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-21 05:00:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

aco/cssa: don't create parallelcopies for constants and exec

Browse source 
if we are able to spill these directly.

Totals from 4913 (3.60% of 136546) affected shaders (Raven):
SpillSGPRs: 16021 -> 15451 (-3.56%); split: -3.87%, +0.31%
CodeSize: 58102020 -> 57371464 (-1.26%); split: -1.26%, +0.00%
Instrs: 11411454 -> 11230105 (-1.59%); split: -1.59%, +0.00%
Latency: 555706331 -> 550058635 (-1.02%); split: -1.07%, +0.05%
InvThroughput: 273023354 -> 271854469 (-0.43%); split: -0.44%, +0.01%
SClause: 385168 -> 385371 (+0.05%); split: -0.01%, +0.06%
Copies: 1342084 -> 1175762 (-12.39%); split: -12.40%, +0.01%
Branches: 392619 -> 378662 (-3.55%); split: -3.56%, +0.00%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
This commit is contained in:
Daniel Schürmann 2021-02-22 14:58:37 +01:00 • committed by Marge Bot
parent 18ba93e673
commit b6a28aaa8b
1 changed files with 26 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
src/amd/compiler/aco_lower_to_cssa.cpp
View file

@ -78,10 +78,17 @@ void collect_parallelcopies(cssa_ctx& ctx)
phi->opcode != aco_opcode::p_linear_phi)
break;
const Definition& def = phi->definitions[0];
/* if the definition is not temp, it is the exec mask.
* We can reload the exec mask directly from the spill slot.
*/
if (!def.isTemp())
continue;
std::vector<unsigned>& preds = phi->opcode == aco_opcode::p_phi ?
block.logical_preds :
block.linear_preds;
const Definition& def = phi->definitions[0];
uint32_t index = ctx.merge_sets.size();
merge_set set;
@ -91,6 +98,20 @@ void collect_parallelcopies(cssa_ctx& ctx)
if (op.isUndefined())
continue;
if (def.regClass().type() == RegType::sgpr && !op.isTemp()) {
/* SGPR inline constants and literals on GFX10+ can be spilled
* and reloaded directly (without intermediate register) */
if (op.isConstant()) {
if (ctx.program->chip_class >= GFX10)
continue;
if (op.size() == 1 && !op.isLiteral())
continue;
} else {
assert(op.isFixed() && op.physReg() == exec);
continue;
}
}
/* create new temporary and rename operands */
Temp tmp = bld.tmp(def.regClass());
ctx.parallelcopies[preds[i]].emplace_back(copy{Definition(tmp), op});
@ -107,6 +128,10 @@ void collect_parallelcopies(cssa_ctx& ctx)
has_preheader_copy |= i == 0 && block.kind & block_kind_loop_header;
}
if (set.empty())
continue;
/* place the definition in dominance-order */
if (def.isTemp()) {
if (has_preheader_copy)