Bartosz Tomczyk 8d919ba384 mesa/glthread: Call unmarshal_batch directly in glthread_finish ... Call it directly when batch queue is empty. This avoids costly thread synchronisation. This commit improves performance of games that have previously regressed with mesa_glthread=true. Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>		2017-04-03 10:33:31 +10:00
..
amd	amd/addrlib: fix optimized build warnings	2017-04-03 00:48:26 +02:00
compiler	glsl: use -O1 optimization for builtin_functions.cpp with MinGW	2017-03-31 13:36:25 -06:00
egl	Android: drop Android 4.4 (KitKat) support	2017-03-22 17:53:31 +00:00
gallium	radeonsi: use unreachable to fix a warning	2017-04-03 00:46:35 +02:00
gbm	gbm/dri: Check dri extension version before flush after unmap	2017-03-31 10:25:46 +02:00
getopt
glx	glx: Remove #include <GL/glxint.h>	2017-03-28 14:48:12 -04:00
gtest	gtest: Update to 1.8.0.	2017-01-20 11:40:52 -08:00
hgl
intel	intel: genxml: fix out of tree builds	2017-03-31 15:29:57 +01:00
loader	loader: use drmGetDevice[s]2 API	2017-03-15 11:37:55 +00:00
mapi	mesa: disable glthread when DEBUG_OUTPUT_SYNCHRONOUS is enabled	2017-04-03 09:31:11 +10:00
mesa	mesa/glthread: Call unmarshal_batch directly in glthread_finish	2017-04-03 10:33:31 +10:00
util	util/disk_cache: don't deadlock on premature EOF	2017-03-25 13:08:37 +11:00
vulkan	vulkan: Bump the header and XML to the latest public version	2017-03-31 22:41:43 -07:00
Makefile.am	intel/vulkan: Get rid of recursive make	2017-03-13 11:16:35 +00:00
SConscript