Improve cache locality in BYTE_STREAM_SPLIT decoding reconstruction

## Description

In `parquet/src/encodings/decoding/byte_stream_split_decoder.rs`, `BYTE_STREAM_SPLIT` decoding currently reconstructs values using a nested scalar loop over values and byte streams in `join_streams_const` and `join_streams_variable`.

The current implementation iterates value-by-value while performing strided reads across the split byte streams, which results in poor memory locality during reconstruction of the original value layout.

This impacts the `BYTE_STREAM_SPLIT` decoding benchmarks in `parquet/benches/encoding.rs`, particularly for floating-point and fixed-length byte array decoding.

---

## Root Cause

The current reconstruction logic processes values in a scalar, value-major order:

```rust
for i in 0..dst.len() / TYPE_SIZE {
for j in 0..TYPE_SIZE {
dst[i * TYPE_SIZE + j] = sub_src[i + j * stride];
}
}
```

This results in:

* strided memory access patterns across byte streams
* reduced cache locality
* limited compiler vectorization opportunities
* increased memory access overhead during reconstruction

The issue becomes more pronounced for larger fixed-width types such as `f32` and `f64`.

---

## Proposed Solution

Rework the reconstruction logic to process values in contiguous blocks instead of value-by-value scalar iteration.

This improves cache locality by reading contiguous regions from each byte stream before writing reconstructed values back into the destination buffer.

Start in parquet/src/encodings/decoding/byte_stream_split_decoder.rs by reading join_streams_const and join_streams_variable, then run the BYTE_STREAM_SPLIT decoding benchmarks in parquet/benches/encoding.rs. Compare reconstruction performance for floating-point and fixed-length byte array decoding; done means the reconstruction uses contiguous blocks and the affected benchmarks improve without changing decoding results.

Written by the indexing model from the issue text.