cache-alignment

A cross-platform, multi-core optimized C++20 LRU Hash Table featuring zero runtime allocations, custom TTAS spinlocks, and Windows Kernel support.

Performance comparison of memory operations on different C++ container types before and after compiler optimization & cache alignment

Ultra-low-latency, header-only concurrent cache for C++20 multi-platform and Windows Kernel (WDM/KMDF). Utilizes SeqLocks, tiered backoff, and NUMA-aware sharding to deliver nanosecond tail latencies with minimal (Linux) or no (Windows/Mac) dependencies.

A very fast NN implementation on the MNIST dataset with custom training, evaluation, and matrix multiplication.

A high-throughput, starvation-resistant C++20 reader-writer lock. Features a lock-free atomic fast path, zero-allocation wait queues, and deterministic user-space fairness policies to prevent writer starvation. Built for high-concurrency environments like HFT, routing tables, and telemetry pipelines.

Multithreaded BFS Webcrawler optimized for low-latency concurrent crawling with cachline-aware synchronisation

Example extension for initializing Bigarray types that are allocated on cache lines