Data Analytics at the Exascale for Free Electron Lasers Project
Innovative data system architecture for LCLS-II upgrade, addressing high-throughput challenges with real-time analysis, fast feedback, and data reduction while preserving scientific content.
Advanced Database Systems - Spring 2019
Comprehensive exploration of advanced database systems, covering in-memory databases, concurrency control, indexing, storage models, query processing, and optimization techniques for modern DBMS architectures.
CUDA Crash Course
Comprehensive introduction to CUDA programming, covering vector operations, matrix multiplication, memory optimization, and performance tuning for GPU-accelerated computing.
Singularity on OpenMind
Explore Singularity, an HPC container service, for efficient and reproducible research workflows. Learn implementation techniques and best practices for OpenMind integration.
Playing With Fire - Pyro SOP Solver, Houdini Tutorial
Learn top tips for Houdini 18's Pyro SOP solver, covering setup, simulation, shaping, and rendering techniques for creating realistic fire effects in 3D VFX.
High Performance Computing
Comprehensive exploration of advanced parallel computing techniques, covering MPI, OpenMP, GPU acceleration, and applications in scientific domains. Includes hands-on exercises for practical skill development.
Stanford Seminar - Algorithmic Extremism- Examining YouTube's Rabbit Hole of Radicalization
Examination of YouTube's recommendation algorithm, challenging claims of far-right radicalization. Data analysis reveals a preference for mainstream media over fringe content, with implications for online political discourse.
Nanosecond-Level Clock Synchronization in a Data Center
Explore nanosecond-level clock synchronization in data centers using Huygens algorithm, which achieves precision without special hardware through advanced networking and machine learning techniques.
Stanford Seminar - Accelerating ML Recommendation with Over a Thousand RISC-V-Tensor Processors
Explore Esperanto's innovative 7nm chip with 1000+ RISC-V processors, designed for efficient ML recommendation. Learn about its architecture, performance, and energy-saving features.
Stanford Seminar - Dataflow for Convergence of AI and HPC - GroqChip
Explore dataflow history, AI-HPC convergence, and Groq's tensor streaming processor architecture. Learn about stream programming, deterministic execution, and distributed scale-out systems for efficient deep learning computations.
Tiny Functions for Codecs, Compilation, and - Maybe - Soon Everything
Exploring the potential of tiny, pure functions in improving network systems, video codecs, and cloud computing, with real-world examples and future applications.
NVIDIA GPU Computing - A Journey from PC Gaming to Deep Learning
Explore NVIDIA GPU's evolution from gaming to deep learning, covering key architectures and applications in supercomputing, data centers, and autonomous vehicles.
Multiscale Dataflow Computing - Competitive Advantage at the Exascale Frontier
Explore multiscale dataflow computing for high-performance, energy-efficient systems. Learn about Maxeler's innovative approach, ecosystem, and applications in various industries.
Stanford Seminar - Beyond Floating Point - Next Generation Computer Arithmetic
Exploring posits as a superior alternative to IEEE 754 floats, offering larger dynamic range, higher accuracy, and simpler implementation for next-generation computer arithmetic.
Deep Learning in the Age of Zen, Vega, and Beyond
Explore deep learning challenges and solutions using AMD's Zen and Vega platforms, focusing on high-performance computing for training and inference in various applications.
The Science of Pandemics - C4 Public Lecture
Explore global pandemics, influenza threats, and the role of mathematical modeling in disease surveillance and control through advanced computing techniques.
Advanced Database Systems - Spring 2018
Explore advanced database systems, covering in-memory databases, query optimization, concurrency control, indexing, storage models, logging, and parallel execution techniques for high-performance data management.
Pushing Java to the Limits: Processing a Billion Rows in Under 2 Seconds
Dive into an in-depth conference talk exploring how to optimize Java performance for processing massive datasets. Learn about the journey from a 4-minute reference implementation to parsing one billion rows of weather data in under two seconds. Discover…
Why I Use Julia for Quantum Computing
Explore the intersection of quantum computing and Julia programming in this 58-minute keynote address from JuliaCon 2024. Delve into various hardware platforms and quantum algorithms, presented in a manner accessible to classical computing experts. Exami…
Advancements in Peridynamics.jl for Dynamic Fracture Simulations
Explore the latest advancements in Peridynamics.jl for dynamic fracture simulations in this 25-minute conference talk presented at JuliaCon 2024. Dive into the nonlocal continuum formulation of Peridynamics, which uses integro-differential equations to m…
Synthetic Data Generation and Fine-tuning for OpenAI GPT-4 or Llama 3
Dive into an extensive tutorial on synthetic data generation and fine-tuning techniques for large language models like OpenAI GPT-4o and Llama 3. Learn how to create synthetic questions and answers, implement chain of thought reasoning, and augment data…