AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

aco: Add a simple heuristic to decide early or late primitive export.

Browse Source 
Late export is theoretically better if used with LATE_ALLOC,
but in practice, the early export has an advantage of
lower register usage, therefore more concurrent waves.

The idea of this commit is that "small" shaders benefit from early
primitive export more, due to being able to launch much more waves.

Let's consider a NIR shader "small" when it has only 1 block.
This yields both better performance, and better stats, than always
using late export.

Fossil DB on Sienna:

Totals from 12807 (8.76% of 146265) affected shaders:
VGPRs: 609128 -> 620216 (+1.82%); split: -0.01%, +1.83%
SpillSGPRs: 1458 -> 1538 (+5.49%)
CodeSize: 37028204 -> 37019320 (-0.02%); split: -0.17%, +0.14%
MaxWaves: 282902 -> 278516 (-1.55%)
Instrs: 7163142 -> 7162925 (-0.00%); split: -0.18%, +0.18%
VClause: 169285 -> 169547 (+0.15%); split: -1.15%, +1.30%
SClause: 267373 -> 267151 (-0.08%); split: -0.24%, +0.16%
Copies: 446442 -> 444567 (-0.42%); split: -2.68%, +2.26%
Branches: 156245 -> 156195 (-0.03%); split: -0.30%, +0.26%
PreSGPRs: 434701 -> 447396 (+2.92%)
PreVGPRs: 527783 -> 540527 (+2.41%)

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10106>
This commit is contained in:
Timur Kristóf
2021-04-08 17:40:28 +02:00
committed by Marge Bot
parent 5dbab03a80
commit f3e004cb56
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/amd/compiler/aco_instruction_selection_setup.cpp
+2 -3
View File
@@ -392,7 +392,7 @@ setup_vs_variables(isel_context *ctx, nir_shader *nir)
assert(!ctx->args->shader_info->so.num_outputs);
/* TODO: check if the shader writes edge flags (not in Vulkan) */
ctx->ngg_nogs_early_prim_export = true;
ctx->ngg_nogs_early_prim_export = exec_list_is_singular(&nir_shader_get_entrypoint(nir)->body);
}
if (ctx->stage == vertex_ngg && ctx->args->options->key.vs_common_out.export_prim_id) {
@@ -464,8 +464,7 @@ setup_tes_variables(isel_context *ctx, nir_shader *nir)
if (ctx->stage.hw == HWStage::NGG)
assert(!ctx->args->shader_info->so.num_outputs);
/* Tess eval shaders can't write edge flags, so this can be always true. */
ctx->ngg_nogs_early_prim_export = true;
ctx->ngg_nogs_early_prim_export = exec_list_is_singular(&nir_shader_get_entrypoint(nir)->body);
}
}