LGTM. Thanks.

rebase

LG

Fixed issues revealed with more extensive test run.
Removed asserts from base implementation. Same GEPs origin is not guaranteed and and I don't find asserting for kinds of incoming pointers as quite useful.
Added assertion that Base is provided if sameBase is set.
PointersChainInfo changed to satisfy static assert condition on Windows.
Rebased.

Looks good with a nit. I'm fine if it addressed in a separate patch since we have quite a few places in SLP vectorizer like here:
for (auto [I, V] : enumerate(VL)) {

add zero initializer for reserved field as some compilers complain

Address comments

Address comments to add assertions.
Rebase.

LG. Thanks.

I thought they don't have remarks. Maybe add remarks to some other tests?

Address comment.
Rebase.

In D144770#4157226, @ABataev wrote:

In D144770#4157187, @vdmitrie wrote:

In D144770#4153415, @RKSimon wrote:

I'd expect this to cause cost changes - have you had any luck creating tests demonstrating that?

I was not able to make one. Existing tests that are sensitive to this cost modeling are:

• for plain wide loads:

llvm/test/Transforms/SLPVectorizer/X86/remark_horcost.ll
llvm/test/Transforms/SLPVectorizer/X86/remark_not_all_parts.ll

• for gather loads:

llvm/test/Transforms/SLPVectorizer/X86/remark_gather-load-redux-cost.ll

But yep, I agree that this is not a great coverage.

Make them to emit remarks with costs estimations?

In D144770#4153415, @RKSimon wrote:

I'd expect this to cause cost changes - have you had any luck creating tests demonstrating that?

Address comments. Rebase.

Perfect! Looks good. Thanks, Alexey!

Thanks. This revision basically looks good to me. So I'm going to accept it.
@RKSimon , do you have any remarks/comments/concerns?

I'm sorry for the delay. Was bit overloaded with an internal stuff.

I'll try to look at this closely next week (but not earlier than Monday). Just a quick note about terminology used. The option name "slp-same-scalars-reduction" does not actually tell much about what it actually controls.
Since you basically are trying to optimize away identity operations in reduction sequences I'd suggest you to use name for option and across the code that better reflect that.
The option name could be "-slp-optimize-identity-hor-reduction-ops=true|false" for example.

LG. Thanks.

A couple of general thoughts. Can you please add a knob that allows to turn off the optimization? And can some sort of debug tracing be added? Such as values that has been optimized away?

rename method as per suggestion

address comment

LG. Thanks

Address comment + rebase

LG. Please fix indentation before pushing the patch. Thanks.

Looks good. Thanks.

Looks good. Thanks!

Looks good. Thanks!