All Episodes

#143 – SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

#141: SQL Has Problems. We Can Fix Them: Pipe Syntax In SQL

#139: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

#137: Optimal Quantile Approximation in Streams

#135: In-Datacenter Performance Analysis of a Tensor Processing Unit

#133: Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations

#131: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

#129: Programming Massively Parallel Processors (Ch.4- Ch.6)

#127: Programming Massively Parallel Processors (Ch.1- Ch.3)

#125: Always-on Vision Processing Unit for Mobile Applications

#123: SYCL 2020 Specification

#121: The SPACE of Developer Productivity

#119: Overlapping Experiment Infrastructure

#117: DuckDB: an Embeddable Analytical Database

#115: Constitutional AI: Harmlessness from AI Feedback

#113: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

#111: Formal Algorithms for Transformers

#110.5

#109: A Measure of Transaction Processing Power

#107: Simple Ideas That Changed Printing and Publishing

#105: Volcano – An Extensible and Parallel Query Evaluation System

#103: GPU-Accelerated Path Rendering

#101: Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics

#100 AMA!

#99.5 AMA?

#98: Dynamo: Amazon’s Highly Available Key-value Store

#96: Amazon DynamoDB: A Scalable, Predictably Performant, and Fully Managed NoSQL Database Service

#93: SEQUEL: A structured English query language

#92: Software Development Waste

#91: Serverless in the Wild

#89: Conflict-free Replicated Data Types

#87: From Laptop to Lambda: Outsourcing Everyday Jobs to Thousands of Transient Functional Containers

#86: JavaScript: the first 20 years

#84: Profiling a warehouse-scale computer

#82: Glass: A New Media for a New Era?

#80.5

#80: TrueSkill™ Ranking System

#78: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

#76: XPC: Architectural Support for Secure and Efficient Cross Process Call

#74: FaceNet: A Unified Embedding for Face Recognition and Clustering

#72: How (and How Not) to Write a Good Systems Paper

#70: Reality Engine Graphics

#68: Introduction to MCMC

#66: The Rendering Equation

#64: Automating Chaos Experiments in Production

#62 – A History Of Erlang

#60 – XGBoost: A Scalable Tree Boosting System

#58 – Gradient Boosting Decision Trees

#56 – Cloud Programming Simplified

#54 – Tales of the Tail

#52 – Convolutional Color Constancy

#50 – Geodesic Discrete Global Grid Systems

#48 – Real-time Personalization using Embeddings for Search Ranking at Airbnb

#46 – An Introduction to Neural Information Retrieval

#44 – Firecracker

#42 – kvm: the Linux Virtual Machine Monitor

#40

#39 – Service Fabric: A Distributed Platform for Building Microservices in the Cloud

#37 – Synthetic Depth-of-Field with a Single-Camera Mobile Phone

#35 – Darkroom: Compiling High-Level Image Processing Code into Hardware Pipelines

#33 – Distinctive Image Features from Scale-Invariant Keypoints

#31 – Big.Little

#29 – Image Analogies and Image Style Transfer

#27 – Julia: A Fresh Approach to Numerical Computing

#25 – Burst photography for high dynamic range and low-light imaging on mobile cameras

#23 – Halide: Decoupling Algorithms from Schedules for High-Performance Image Processing

#21 – The Frankencamera

#19 – Light Field Rendering

#17 – Unikernels: Library Operating Systems for the Cloud

#15 – Neural Machine Translation by Jointly Learning to Align and Translate

#13 – HyperLogLog in Practice

#11 – The Story in the Notebook

#09 – Automatic Differentiation in Machine Learning: a Survey

#07 – One VM to Rule Them All

#05: Agile CPU / Versioned Golang

#04: Filesystem on NVM / Self-Driving Car on Dessert

#03: New Grads Struggle / Data Scientists Strive

#02: Android Intent / GPU Raytracer

#01: Tensor Comprehensions, Rust Belt