Casey Destroys Optimization Myths | TheStandup
Computer architecture Gpu Ai infrastructure Floating Point math Cpu optimization Nvidia Microsoft Rtx spark Unmetered intelligence Professional bowling trash facts
This episode dives into common optimization myths, specifically examining whether multiplying by a reciprocal is actually faster than division on modern CPUs. The hosts also discuss NVIDIA's RTX Spark and Microsoft's vision for 'unmetered intelligence,' mixed with lighter segments like professional bowling trivia. Ideal for developers interested in low-level performance optimization and tech industry news.
Related videos
Elon kinda won after all
Azure Storage for AI workloads | OD870
Spite-Driven Engineering: A New Blueprint for Cloud Security in the AI Native Era
Keynote: Engineering Population-Scale AI & AI Infrastructure with Cloud Native Tec... Tittu Varghese
Keynote: From Platforms to AI Factories. Has Kubernetes Solved It? - Saiyam Pathak
Azure Storage for AI workloads | OD870
GPU-accelerated virtual drug screening with cuML and Agent Platform
How Xoople Scales Python for AI using Anyscale on Azure | LIVE148
NVIDIA quick take: Live from Microsoft Build | LIVESP123
Shipping custom models at scale from fine-tuning to inference | BRK234
Build Apps w/ Local AI for Unmetered Intelligence on every Windows PC | BRK260
