Bloom filter Join Step I: create benchmark

[Lordworms]

Which issue does this PR close?

part of #7955

Closes #.

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

[alamb]

Thanks @Lordworms -- I realize i am very behind on reviews in DataFusion

My first question on these benchmarks is are they measuring the right thing (namely are they dominated by the join time). Have you had a chance to run any profiling (flamegraphs, etc) to confirm these benchmarks are actually join dominated?

[alamb]

Marking as draft as I think this PR is no longer waiting on feedback. Please mark it as ready for review when it is ready for another look

[Lordworms]

for TPCH query 17, when we create 1000000 rows for lineitem and part table, the time spent on join is 50% (the other 80% of time spent on creating parquet files)

[Lordworms]

For the second case, 95% of the time spent on join

[Lordworms]

I think it worth a try to implement join predicate pushdown