[llvm] [X86] Enable MaximizeBandwidth by default and price predicate mask-expansion fanout (PR #201666)

[via llvm-commits]

github-actions[bot] wrote:

<!--LLVM CODE FORMAT COMMENT: {undef deprecator}-->


:warning: undef deprecator found issues in your code. :warning:

<details>
<summary>
You can test this locally with the following command:
</summary>

``````````bash
git diff -U0 --pickaxe-regex -S '([^a-zA-Z0-9#_-]undef([^a-zA-Z0-9_-]|$)|UndefValue::get)' 'HEAD~1' HEAD llvm/test/Analysis/CostModel/X86/gather-scatter-mask-expansion.ll llvm/test/Analysis/CostModel/X86/masked-mem-mask-expansion.ll llvm/test/Analysis/CostModel/X86/select-mask-expansion.ll llvm/test/Transforms/LoopVectorize/X86/maxbw-cast-cost.ll llvm/lib/Target/X86/X86TargetTransformInfo.cpp llvm/lib/Target/X86/X86TargetTransformInfo.h llvm/test/Analysis/CostModel/X86/fptoi_sat.ll llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-8.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-scatter-i32-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-scatter-i64-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/scatter-i32-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/CostModel/scatter-i64-with-i8-index.ll llvm/test/Transforms/LoopVectorize/X86/conditional-scalar-assignment.ll llvm/test/Transforms/LoopVectorize/X86/cost-conditional-branches.ll llvm/test/Transforms/LoopVectorize/X86/cost-model.ll llvm/test/Transforms/LoopVectorize/X86/gcc-examples.ll llvm/test/Transforms/LoopVectorize/X86/induction-costs.ll llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll llvm/test/Transforms/LoopVectorize/X86/no_fpmath.ll llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll llvm/test/Transforms/LoopVectorize/X86/nondetermisitic-widening-cost.ll llvm/test/Transforms/LoopVectorize/X86/pr47437.ll llvm/test/Transforms/LoopVectorize/X86/reduction-crash.ll llvm/test/Transforms/LoopVectorize/X86/replicating-load-store-costs.ll llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-loopid-dbg.ll llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll llvm/test/Transforms/PhaseOrdering/X86/pixel-splat.ll llvm/test/Transforms/PhaseOrdering/X86/preserve-access-group.ll llvm/test/Transforms/PhaseOrdering/X86/vector-reduction-known-first-value.ll
``````````

</details>


The following files introduce new uses of undef:
 - llvm/test/Analysis/CostModel/X86/masked-mem-mask-expansion.ll

[Undef](https://llvm.org/docs/LangRef.html#undefined-values) is now deprecated and should only be used in the rare cases where no replacement is possible. For example, a load of uninitialized memory yields `undef`. You should use `poison` values for placeholders instead.

In tests, avoid using `undef` and having tests that trigger undefined behavior. If you need an operand with some unimportant value, you can add a new argument to the function and use that instead.

For example, this is considered a bad practice:
```llvm
define void @fn() {
  ...
  br i1 undef, ...
}
```

Please use the following instead:
```llvm
define void @fn(i1 %cond) {
  ...
  br i1 %cond, ...
}
```

Please refer to the [Undefined Behavior Manual](https://llvm.org/docs/UndefinedBehavior.html) for more information.



https://github.com/llvm/llvm-project/pull/201666