Perf: Optimize performance of ByteViewGroupValueBuilder on batches with inlined views

[zhuqi-lucas]

Which issue does this PR close?

Optimize following cases, and add more fast path.

do_append_val_inner
do_equal_to_inner

This is wasteful if there is no data buffer, in which case we can improve the performance.

Also, i do some fast path which is done in arrow-rs.

• Closes #16330

Rationale for this change

Optimize following cases, and add more fast path.

do_append_val_inner
do_equal_to_inner

What changes are included in this PR?

Optimize following cases, and add more fast path.

do_append_val_inner
do_equal_to_inner

Are these changes tested?

Yes

Are there any user-facing changes?

No

[Rachelint]

Thanks @zhuqi-lucas ! How about the benchmark result?

[zhuqi-lucas]

Thank you @Rachelint , it seems no performance improvement for clickbench from my local Mac benchmark, i need to investigate further.

[Rachelint]

Thank you @Rachelint , it seems no performance improvement for clickbench from my local Mac benchmark, i need to investigate further.

Yes... I made a simple try only in append path before, and also found no obvious improvement... We indeed need further investigation maybe

[zhuqi-lucas]

Thank you @Rachelint , it seems no performance improvement for clickbench from my local Mac benchmark, i need to investigate further.

Yes... I made a simple try only in append path before, and also found no obvious improvement... We indeed need further investigation maybe

I agree, converted it a draft now.