search for: rd58

Displaying 5 results from an estimated 5 matches for "rd58".

Did you mean: r258
2013 Sep 05
1
[LLVMdev] why functionattrs doesn't add dependency of AliasAnalysis
...edulePass(llvm::Pass*): Assertion `PI && "Expected required passes to be initialized"' failed. The strangest thing is the opt doesn't suffer from this issue. please note that directly use -functionattrs, it can run without AliasAnalysis. Could you explain why? liuxin at rd58:~/testbed$ opt -functionattrs -debug-pass=Structure < pf.bc > /dev/null Pass Arguments: -targetlibinfo -no-aa -basiccg -functionattrs -preverify -domtree -verify Target Library Information No Alias Analysis (always returns 'may' alias) ModulePass Manager Basic CallGraph Constr...
2013 Oct 30
2
[LLVMdev] Is there pass to break down <4 x float> to scalars
...rks for me. I found my program have complex memory accesses, such as bi-dimentional arrays. Sorry, I am not good at AA. In my concept, TBAA is just for C++. Do you mean that you can make use of TBAA to help DSE? Why TBAA is total null for my program ? basicaa is even better than -tbaa. liuxin at rd58:~/testbed$ opt -tbaa -aa-eval -decompose-vectors -mem2reg -dse test.bc -debug-pass=Structure -o test.opt.bc -stats Pass Arguments: -targetlibinfo -no-aa -tbaa -aa-eval -decompose-vectors -domtree -mem2reg -memdep -dse -preverify -verify Target Library Information No Alias Analysis (always return...
2013 Oct 30
0
[LLVMdev] Is there pass to break down <4 x float> to scalars
...an that you can make use of TBAA to help DSE? The main reason I wanted TBAA is to help scheduling. None of the accesses are dead, but I want to able to interleave them to reduce register pressure. > Why TBAA is total null for my program ? basicaa is even better than -tbaa. > > liuxin at rd58:~/testbed$ opt -tbaa -aa-eval -decompose-vectors -mem2reg -dse > test.bc -debug-pass=Structure -o test.opt.bc -stats > Pass Arguments: -targetlibinfo -no-aa -tbaa -aa-eval -decompose-vectors > -domtree -mem2reg -memdep -dse -preverify -verify > Target Library Information > No Alia...
2013 Oct 25
0
[LLVMdev] Is there pass to break down <4 x float> to scalars
Liu Xin <navy.xliu at gmail.com> writes: > I think we are solving a same problem. I am working on shader language > too. I am not satisfied with current binaries because vector operations > are kept in llvm opt. > > glsl shader language has an operation called "swizzle". It can select > sub-components of a vector. If a shader only takes components "xy"
2013 Oct 25
3
[LLVMdev] Is there pass to break down <4 x float> to scalars
Hi, Richard, I think we are solving a same problem. I am working on shader language too. I am not satisfied with current binaries because vector operations are kept in llvm opt. glsl shader language has an operation called "swizzle". It can select sub-components of a vector. If a shader only takes components "xy" for a vec4. it's certainly wasteful to generate 4