[llvm-dev] No vectorization with -loop-vectorize and -slp-vectorizer

[hameeza ahmed via llvm-dev]

There is one problem.
For matrix multiplication code, I am not getting same IR with o3 and
individual passes as follows;

Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/clang -O1
-march=native -Xclang -disable-O0-optnone -disable-llvm-passes -emit-llvm
-S matmul.c -o matmul-noopt.ll

Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/opt  -O3  -S
matmul-noopt.ll -o matmul-noopt-o3.ll

Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/clang -mllvm
-debug-pass=Arguments -O3 -march=native -S -emit-llvm matmul.c -o
matmul-o3.ll

*obtain the o3 individual flags by above command to give as input in the
following command;*

Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/opt -tti
-targetlibinfo -tbaa -scoped-noalias -assumption-cache-tracker
-profile-summary-info -forceattrs -inferattrs -domtree -callsite-splitting
-ipsccp -called-value-propagation -attributor -globalopt -domtree -mem2reg
-deadargelim -domtree -basicaa -aa -loops -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -instcombine -simplifycfg -basiccg
-globals-aa -prune-eh -inline -functionattrs -argpromotion -domtree -sroa
-basicaa -aa -memoryssa -early-cse-memssa -speculative-execution -basicaa
-aa -lazy-value-info -jump-threading -correlated-propagation -simplifycfg
-domtree -aggressive-instcombine -basicaa -aa -loops -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -instcombine -libcalls-shrinkwrap
-loops -branch-prob -block-freq -lazy-branch-prob -lazy-block-freq
-opt-remark-emitter -pgo-memop-opt -basicaa -aa -loops -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -tailcallelim -simplifycfg
-reassociate -domtree -loops -loop-simplify -lcssa-verification -lcssa
-basicaa -aa -scalar-evolution -loop-rotate -licm -loop-unswitch
-simplifycfg -domtree -basicaa -aa -loops -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -instcombine -loop-simplify
-lcssa-verification -lcssa -scalar-evolution -indvars -loop-idiom
-loop-deletion -loop-unroll -mldst-motion -phi-values -basicaa -aa -memdep
-lazy-branch-prob -lazy-block-freq -opt-remark-emitter -gvn -phi-values
-basicaa -aa -memdep -memcpyopt -sccp -demanded-bits -bdce -basicaa -aa
-loops -lazy-branch-prob -lazy-block-freq -opt-remark-emitter -instcombine
-lazy-value-info -jump-threading -correlated-propagation -basicaa -aa
-phi-values -memdep -dse -loops -loop-simplify -lcssa-verification -lcssa
-basicaa -aa -scalar-evolution -licm -postdomtree -adce -simplifycfg
-domtree -basicaa -aa -loops -lazy-branch-prob -lazy-block-freq
-opt-remark-emitter -instcombine -barrier -elim-avail-extern -basiccg
-rpo-functionattrs -globalopt -globaldce -basiccg -globals-aa -float2int
-domtree -loops -loop-simplify -lcssa-verification -lcssa -basicaa -aa
-scalar-evolution -loop-rotate -loop-accesses -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -loop-distribute -branch-prob
-block-freq -scalar-evolution -basicaa -aa -loop-accesses -demanded-bits
-lazy-branch-prob -lazy-block-freq -opt-remark-emitter -loop-vectorize
-loop-simplify -scalar-evolution -aa -loop-accesses -lazy-branch-prob
-lazy-block-freq -loop-load-elim -basicaa -aa -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -instcombine -simplifycfg -domtree
-loops -scalar-evolution -basicaa -aa -demanded-bits -lazy-branch-prob
-lazy-block-freq -opt-remark-emitter -slp-vectorizer -opt-remark-emitter
-instcombine -loop-simplify -lcssa-verification -lcssa -scalar-evolution
-loop-unroll -lazy-branch-prob -lazy-block-freq -opt-remark-emitter
-instcombine -loop-simplify -lcssa-verification -lcssa -scalar-evolution
-licm -lazy-branch-prob -lazy-block-freq -opt-remark-emitter
-transform-warning -alignment-from-assumptions -strip-dead-prototypes
-globaldce -constmerge -domtree -loops -branch-prob -block-freq
-loop-simplify -lcssa-verification -lcssa -basicaa -aa -scalar-evolution
-block-freq -loop-sink -lazy-branch-prob -lazy-block-freq
-opt-remark-emitter -instsimplify -div-rem-pairs -simplifycfg  -S
matmul-noopt.ll -o matmul-noopt_o3_opt_parms.ll

Why the IRs matmul-noopt-o3.ll and matmul-noopt_o3_opt_parms.ll are not
same?

What is the mistake here?


On Mon, Oct 14, 2019 at 2:33 PM HAPPY Mahto <cs17btech11018 at iith.ac.in>
wrote:

>
>
> On Mon, Oct 14, 2019 at 2:52 PM hameeza ahmed via llvm-dev <
> llvm-dev at lists.llvm.org> wrote:
>
>> Hello,
>> I am trying to test individual optimizations of opt on unoptimized IR.
>> But, the IR is not getting vectorized by using following commands.
>>
>> Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/clang -O1
>> -Xclang -disable-llvm-passes -emit-llvm -S vecsum.c -o vecsum-noopt.ll
>>
>>
> Try this:
> Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/clang -O1
> -Xclang -disable-00-optnone -disable-llvm-passes -emit-llvm -S vecsum.c -o
> vecsum-noopt.ll
> Same for other commands too.
> You need to add '-disable-00-optnone' flag, or you can remove the optnone
> attribute from attributes #0 = { noinline , nounwind, optnone ... }
> I hope this helps.
>
> -Happy
>
> Documents/clang+llvm-9.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/opt
>> -loop-vectorize -slp-vectorizer -S vecsum-noopt.ll -o vecto.ll
>>
>> Though IR gets vectorized with O3 flag. Even I tried to replicate O3
>> behavior via individual flags with opt. But It is not showing same IR.
>>
>> Where am I doing mistake?
>>
>> Please help
>>
>> Thank You
>> Regards
>> _______________________________________________
>> LLVM Developers mailing list
>> llvm-dev at lists.llvm.org
>> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20191024/fe3fc16a/attachment.html>