Lock-Free

Illustration of a hash map with multiple threads accessing buckets without locks.

Designing Lock-Free Concurrent Hash Maps Without Atomic Contention

A deep dive into lock‑free hash map designs that sidestep atomic contention, covering bucket partitioning, versioned pointers, and practical performance results.

Illustration of two threads exchanging data atomically.

Solving Data Races with Lock‑Free Atomic Compare‑and‑Swap

A deep dive into lock‑free programming using atomic compare‑and‑swap, covering theory, implementation patterns, and real‑world best practices.

Implementing Lock-Free Concurrent B-Trees for High-Throughput Vector Indexing in Distributed Systems

Introduction Vector indexing—whether for similarity search in recommendation engines, nearest‑neighbor queries in machine‑learning pipelines, or high‑dimensional feature retrieval in bioinformatics—has become a core workload in modern distributed systems. Traditional indexing structures (KD‑trees, LSH tables, inverted files) either suffer from poor cache locality or become bottlenecks when many threads try to update or query simultaneously. Enter the lock‑free concurrent B‑tree. By marrying the proven I/O‑optimal layout of B‑trees with the non‑blocking guarantees of lock‑free algorithms, we can achieve: ...