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

draw: fix draw_llvm_variant_key struct padding to avoid recompiles 

The struct padding got broken by c789b981b2.
This caused serious performance regression because part of the key was
uninitialized and hence the shader always recompiled (at least on release
builds...).
While here also fix key size calculation when the number of samplers
and the number of sampler views are different.

v2: add comment

Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
This commit is contained in:
Roland Scheidegger 2013-01-29 08:39:09 -08:00
parent 845130951f
commit 0eb588a37c
3 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/gallium/auxiliary/draw/draw_llvm.c
View File

@ -1378,7 +1378,8 @@ draw_llvm_make_variant_key(struct draw_llvm *llvm, char *store)
key->clip_halfz = !llvm->draw->rasterizer->gl_rasterization_rules;
key->need_edgeflags = (llvm->draw->vs.edgeflag_output ? TRUE : FALSE);
key->ucp_enable = llvm->draw->rasterizer->clip_plane_enable;
key->pad = 0;
key->pad1 = 0;
key->pad2 = 0;
/* All variants of this shader will have the same value for
* nr_samplers. Not yet trying to compact away holes in the

7
src/gallium/auxiliary/draw/draw_llvm.h
View File

@ -206,8 +206,13 @@ struct draw_llvm_variant_key
unsigned clip_halfz:1;
unsigned bypass_viewport:1;
unsigned need_edgeflags:1;
/*
* it is important there are no holes in this struct
* (and all padding gets zeroed).
*/
unsigned pad1:1;
unsigned ucp_enable:PIPE_MAX_CLIP_PLANES;
unsigned pad:33-PIPE_MAX_CLIP_PLANES;
unsigned pad2:32-PIPE_MAX_CLIP_PLANES;
/* Variable number of vertex elements:
*/

5
src/gallium/auxiliary/draw/draw_vs_llvm.c
View File

@ -100,8 +100,9 @@ draw_create_vs_llvm(struct draw_context *draw,
vs->variant_key_size =
draw_llvm_variant_key_size(
vs->base.info.file_max[TGSI_FILE_INPUT]+1,
vs->base.info.file_max[TGSI_FILE_SAMPLER]+1);
vs->base.info.file_max[TGSI_FILE_INPUT]+1,
MAX2(vs->base.info.file_max[TGSI_FILE_SAMPLER]+1,
vs->base.info.file_max[TGSI_FILE_SAMPLER_VIEW]+1));
vs->base.state.stream_output = state->stream_output;
vs->base.draw = draw;