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

nir/opt_peephole_select: Don't peephole_select expensive math instructions

Browse Source 
On some GPUs, especially older Intel GPUs, some math instructions are
very expensive.  On those architectures, don't reduce flow control to a
csel if one of the branches contains one of these expensive math
instructions.

This prevents a bunch of cycle count regressions on pre-Gen6 platforms
with a later patch (intel/compiler: More peephole select for pre-Gen6).

v2: Remove stray #if block.  Noticed by Thomas.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
This commit is contained in:
Ian Romanick
2018-06-18 16:11:55 -07:00
parent 8fb8ebfbb0
commit 378f996771
9 changed files with 40 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/broadcom/compiler/nir_to_vir.c
+1 -1
View File
@@ -1241,7 +1241,7 @@ v3d_optimize_nir(struct nir_shader *s)
NIR_PASS(progress, s, nir_opt_dce);
NIR_PASS(progress, s, nir_opt_dead_cf);
NIR_PASS(progress, s, nir_opt_cse);
NIR_PASS(progress, s, nir_opt_peephole_select, 8, true);
NIR_PASS(progress, s, nir_opt_peephole_select, 8, true, true);
NIR_PASS(progress, s, nir_opt_algebraic);
NIR_PASS(progress, s, nir_opt_constant_folding);
NIR_PASS(progress, s, nir_opt_undef);