Module executor 

Parallel execution engine

Core parallel execution primitives for distributing work across threads using scoped threads.

Functions

calculate_chunk_size

Calculate optimal chunk size based on data length and CPU count

get_min_chunk_size

Get minimum chunk size (configurable via avx_MIN_CHUNK_SIZE env var)

num_cpus

Get number of CPUs

parallel_count

Count elements that satisfy predicate (parallel)

parallel_filter

Execute a filter operation in parallel

parallel_find

Find first element that satisfies predicate (parallel with early termination)

parallel_for_each

Execute function on each item in parallel using scoped threads

parallel_map

Execute a map operation in parallel

parallel_partition

Partition elements based on predicate (parallel)

parallel_reduce

Execute a reduce operation in parallel

parallel_sum

Sum elements in parallel