OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

intel/fs: don't consider fixup_nomask_control_flow SENDs predicate

Browse Source 
Those SENDs are still doing a full register write. We just inserted
some predication for a workaround.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21853>
This commit is contained in:
Lionel Landwerlin
2023-03-14 18:22:50 +02:00
committed by Marge Bot
parent 34d8bfe65f
commit 362a07db3a
2 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/intel/compiler/brw_ir.h
View File

@@ -178,6 +178,12 @@ struct backend_instruction {
* the scratch surface offset to build
* extended descriptor
*/
bool predicate_trivial:1; /**< The predication mask applied to this
* instruction is guaranteed to be uniform and
* a superset of the execution mask of the
* present block, no currently enabled channels
* will be disabled by the predicate.
*/
bool eot:1;
/* Chooses which flag subregister (f0.0 to f1.1) is used for conditional