Skip to content Skip to sidebar Skip to footer

Learning CUDA by optimizing matrix-vector multiplication for cuBLAS-like perf by rrampage

18 Jan, 2025 Matrix-vector multiplication is a foundational operation in linear algebra, where a matrix transforms an input vector into an output vector. This operation basically powers numerous fields including computer science and deep learning. Optimizing matrix-vector multiplication, especially in the context of GPU programming and CUDA can help us learn many new things. In

ByHackTechFebruary 21, 20250Comments

News

Optimizing compiler for ts-pattern (zero runtime) by stevekrouse

⚠️ Note: this is highly experimental software. Here be dragons 🐉 Zero-runtime pattern matching. (~10-12x faster 🔥) Pattycake is an optimizing compiler for ts-pattern that lets you have your cake (expressive pattern matching), and eat it too (zero runtime overhead). Install Next.js // next.config.js const pattycake = require(‘pattycake’); module.exports = pattycake.next({ // your next.js config

ByHackTechOctober 1, 20230Comments

News

Optimizing Rust Code for the LSM-Tree Iterator in RisingWave by Pacificar

Introduction to Hummock Read-Write PathIn RisingWave, we have developed our own cloud-native LSM storage engine called Hummock in Rust. We use it to store the state of stateful operators in stream processing.Similar to general LSM storage engines, data newly written to Hummock is stored in a mutable mem-table. Under specific conditions, the mutable mem-table is

ByHackTechSeptember 22, 20230Comments

News

Optimizing Open Addressing by TheNumbat

Your default hash table should be open-addressed, using Robin Hood linear probing with backward-shift deletion. When prioritizing deterministic performance over memory efficiency, two-way chaining is also a good choice. Code for this article may be found on GitHub. Open Addressing vs. Separate Chaining Benchmark Setup Discussion Separate Chaining Linear Probing Quadratic Probing Double Hashing Robin

ByHackTechMarch 19, 20230Comments

News

Optimizing a Toy Model Using Gradient Descent and Jax by frantzmiccoli

The deep learning community has been relying on powerful libraries enabling more than I can dream of in terms of mathematical capabilities. Back in the days, I worked on an artificial neural network project where we implemented the derivatives where we would need them. Seeing those projects made me willing to toy around with their

ByHackTechFebruary 12, 20230Comments

News

Optimizing Sequences by masijo

In this episode of jank’s development updates, we follow an exciting few weekends as I was digging deep into Clojure’s sequence implementation, building jank’s equivalent, and then benchmarking and profiling in a dizzying race to the bottom.IntroductionNot expecting a rabbit hole, I was originally surprised at how many allocations are involved in a normal sequence

ByHackTechJanuary 15, 20230Comments

Sign Up to Our Newsletter