summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/r300/r300_winsys.h
diff options
context:
space:
mode:
authorTörök Edwin <[email protected]>2010-05-03 07:43:03 -0700
committerJosé Fonseca <[email protected]>2010-05-03 17:01:20 +0100
commit15af543f106db9e6ff840828905df4978e68f715 (patch)
tree0794233d006e148767eaefb8b488acfb74adcbf6 /src/gallium/drivers/r300/r300_winsys.h
parent723ab664f617e60812ea236761b429e999abc83c (diff)
Reorder LLVM passes, running mem2reg earlier.
This gives a ~30% shader optimization time improvement on blender. Tested by comparing the dumped LLVM modules. Current ordering: time ~/llvm-git/obj/Release-Asserts/bin/opt l.bc -constprop -instcombine -mem2reg -gvn -simplifycfg real 0m1.126s user 0m1.108s sys 0m0.012s With this patch: time ~/llvm-git/obj/Release-Asserts/bin/opt l.bc -mem2reg -constprop -instcombine -gvn -simplifycfg real 0m0.885s user 0m0.880s sys 0m0.000s The overall improvement in blender is ~15%. Blender without the patch takes 1m13s: edwin 5934 87.6 11.5 729440 458296 pts/5 SLl+ 17:35 1:13 blender Blender with the patch takes 1m3s: edwin 5726 94.2 11.2 716424 446168 pts/5 SLl+ 17:32 1:03 blender It is still slow with the patch, but better (most of the optimization time is taken up by GVN, see LLVM PR7023). Signed-off-by: Török Edwin <[email protected]> Signed-off-by: José Fonseca <[email protected]>
Diffstat (limited to 'src/gallium/drivers/r300/r300_winsys.h')
0 files changed, 0 insertions, 0 deletions