My Homelab Journal

Unvieling the world of Deep Learning • Kernel Optimization • CUDA • AI Systems

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Categories GPU Optimization

Category

GPU Optimization 1

From 30ms to 2ms: My Wild Ride Optimizing GPU Kernels (And Why Memory is Actually Everything) Feb 15, 2025

Recently Updated

From 30ms to 2ms: My Wild Ride Optimizing GPU Kernels (And Why Memory is Actually Everything)
From Confusion to Colors: My Journey Learning Parallel Image Magic with CUDA Threads
From Matrix Multiplication to Warp Optimizations — My Journey and Insights.
AI Action Item Extractor: Meeting Dialogue to JSON.
My Journey Optimizing Attention: Why My First CUDA Optimization Barely Worked

Trending Tags

gpu optimization performance learning-journey profiling cuda matrix-multiplication parallel-computing shared-memory tiling

© 2026 Umang Singh. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

gpu optimization performance learning-journey profiling cuda matrix-multiplication parallel-computing shared-memory tiling

A new version of content is available.