summaryrefslogtreecommitdiff
path: root/src/gallium/drivers/llvmpipe
diff options
context:
space:
mode:
authorTörök Edwin <edwintorok@gmail.com>2010-05-03 07:43:03 -0700
committerJosé Fonseca <jfonseca@vmware.com>2010-05-03 17:01:20 +0100
commit15af543f106db9e6ff840828905df4978e68f715 (patch)
tree0794233d006e148767eaefb8b488acfb74adcbf6 /src/gallium/drivers/llvmpipe
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 <edwintorok@gmail.com> Signed-off-by: José Fonseca <jfonseca@vmware.com>
Diffstat (limited to 'src/gallium/drivers/llvmpipe')
-rw-r--r--src/gallium/drivers/llvmpipe/lp_jit.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/src/gallium/drivers/llvmpipe/lp_jit.c b/src/gallium/drivers/llvmpipe/lp_jit.c
index 466a2f54fb..30e206a2b4 100644
--- a/src/gallium/drivers/llvmpipe/lp_jit.c
+++ b/src/gallium/drivers/llvmpipe/lp_jit.c
@@ -185,6 +185,8 @@ lp_jit_screen_init(struct llvmpipe_screen *screen)
/* These are the passes currently listed in llvm-c/Transforms/Scalar.h,
* but there are more on SVN. */
/* TODO: Add more passes */
+ LLVMAddCFGSimplificationPass(screen->pass);
+ LLVMAddPromoteMemoryToRegisterPass(screen->pass);
LLVMAddConstantPropagationPass(screen->pass);
if(util_cpu_caps.has_sse4_1) {
/* FIXME: There is a bug in this pass, whereby the combination of fptosi
@@ -193,9 +195,7 @@ lp_jit_screen_init(struct llvmpipe_screen *screen)
*/
LLVMAddInstructionCombiningPass(screen->pass);
}
- LLVMAddPromoteMemoryToRegisterPass(screen->pass);
LLVMAddGVNPass(screen->pass);
- LLVMAddCFGSimplificationPass(screen->pass);
}
lp_jit_init_globals(screen);