[llvm] [LV] Don't ignore invariant stores when costing (PR #158682)

[LLVM Continuous Integration via llvm-commits]

llvm-ci wrote:

LLVM Buildbot has detected a new failure on builder `ml-opt-devrel-x86-64` running on `ml-opt-devrel-x86-64-b1` while building `llvm` at step 6 "test-build-unified-tree-check-all".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/175/builds/25932

<details>
<summary>Here is the relevant piece of the build log for the reference</summary>

```
Step 6 (test-build-unified-tree-check-all) failure: test (failure)
******************** TEST 'LLVM :: Transforms/LoopVectorize/X86/invariant-store-vectorization.ll' FAILED ********************
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 2
/b/ml-opt-devrel-x86-64-b1/build/bin/opt -passes=loop-vectorize -mattr=avx512f -S /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll | /b/ml-opt-devrel-x86-64-b1/build/bin/FileCheck /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
# executed command: /b/ml-opt-devrel-x86-64-b1/build/bin/opt -passes=loop-vectorize -mattr=avx512f -S /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
# executed command: /b/ml-opt-devrel-x86-64-b1/build/bin/FileCheck /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
# .---command stderr------------
# | /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll:402:15: error: CHECK-NEXT: expected string not found in input
# | ; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
# |               ^
# | <stdin>:366:7: note: scanning from here
# | entry:
# |       ^
# | <stdin>:394:2: note: possible intended match here
# |  br i1 %ec, label %exit, label %loop
# |  ^
# | 
# | Input file: <stdin>
# | Check file: /b/ml-opt-devrel-x86-64-b1/llvm-project/llvm/test/Transforms/LoopVectorize/X86/invariant-store-vectorization.ll
# | 
# | -dump-input=help explains the following input dump.
# | 
# | Input was:
# | <<<<<<
# |             .
# |             .
# |             .
# |           361: for.end: ; preds = %vec.epilog.middle.block, %middle.block, %latch 
# |           362:  ret void 
# |           363: } 
# |           364:  
# |           365: define void @test_store_of_final_reduction_value(i64 %x, ptr %dst) #0 { 
# |           366: entry: 
# | next:402'0           X error: no match found
# |           367:  br label %vector.ph 
# | next:402'0     ~~~~~~~~~~~~~~~~~~~~~
# |           368:  
# | next:402'0     ~
# |           369: vector.ph: ; preds = %entry 
# | next:402'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |           370:  %broadcast.splatinsert = insertelement <2 x i64> poison, i64 %x, i64 0 
# | next:402'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |           371:  %broadcast.splat = shufflevector <2 x i64> %broadcast.splatinsert, <2 x i64> poison, <2 x i32> zeroinitializer 
# | next:402'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |             .
# |             .
# |             .
...

```

</details>

https://github.com/llvm/llvm-project/pull/158682