Overview
News
Salaries
Products
People
Growth
Offices
Financials
Overview
About Building Unum Cloud since 2015. Computer Science & AI researcher (unpublished, by choice). Twice an Astrophysics dropout, lifelong Bioinformatics fan. Investing in deep-tech, cloud, & semiconductors. Fluent in English, Russian & Armenian. Lived in & . Frequent host of.
News
Full Unicode Search at 50 ICU Speed with AVX-512
ICU gets Unicode right and pays for it. This post shows a different approach: fold-safe windows, SIMD probes, and verifiers for fast UTF-8 search.
Read more
Report
Tuning TLS: AES-256 Beats ChaCha20 on Every CPU
AES-256-GCM now beats ChaCha20-Poly1305 by up to 3x on every modern CPU with hardware acceleration, reversing the 2015 mobile performance advice.
Read more
Report
Scaling Elections with GPUs and Mojo across Nvidia and AMD
Taking the computationally expensive Schulze voting method from theory to practice on GPUs - exploring parallel algorithms, hardware optimizations, and why Mojo surprised me.
Read more
Report
2x Faster Hashes on AWS Graviton: NEON SVE2
SVE2 AES on AWS Graviton 4 delivers 2x faster string hashing than NEON, but SVE
Read more
Report
Before AI
Like Ptolemaic astronomers stacking circles to predict planetary motion, we stack transformer layers to approximate intelligence-accurate yet awaiting our Kepler moment.
Read more
Report
Report
Processing Strings 109x Faster than Nvidia on H100
StringZilla v4 brings CUDA acceleration for string processing: 109x faster than Nvidia
Read more
Report
Beyond OpenMP in C++ & Rust: Taskflow, Rayon, Fork Union
Most C++ and Rust thread pools run 10x slower than OpenMP on fork-join workloads. Fork Union closes the gap to 20% with 300 lines, dodging mutexes and CAS.
Read more
Report
CUDA Hello World: Done Less Wrong
Moving beyond triple-bracket kernel launches to production-ready CUDA: proper error handling, CUDA Driver API, cooperative groups, and inline PTX for robust GPU code.
Read more
Report
GitHub - ashvardanian/less_slow.cpp: Playing around "Less Slow" coding practices in C++ 20, C, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception handling, networking and user-space IO
Playing around "Less Slow" coding practices in C++ 20, C, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception handling, networking and user-space IO - ashvardanian/less_slow.cpp
Read more
Report
Show more news