The Netflix TechBlog

NOVEMBER 13, 2023

Practical use cases for speech & music activity Audio dataset preparation Speech & music activity is an important preprocessing step to prepare corpora for training. Content, genre and languages Instead of augmenting or synthesizing training data, we sample the large scale data available in the Netflix catalog with noisy labels.

Architecture 224

Architecture Energy Benchmarking Processing 224

Scalegrid

JANUARY 12, 2024

This is sometimes referred to as using an “over-cloud” model that involves a centrally managed resource pool that spans all parts of a connected global network with internal connections between regional borders, such as two instances in IAD-ORD for NYC-JS webpage DNS routing. Additionally. This also aids scalability down the line.

Cloud 130

Cloud Virtualization Storage Efficiency 130

The Netflix TechBlog

MAY 21, 2019

Netflix engineers run a series of tests and benchmarks to validate the device across multiple dimensions including compatibility of the device with the Netflix SDK, device performance, audio-video playback quality, license handling, encryption and security. Likewise it has very low requirements on the initial amount of training data.

Testing 163

Testing AWS Lambda Network 163

Adrian Cockcroft

JUNE 21, 2022

The early days at Sun Cambridge were special, I absorbed a lot about networking and the technical side of the role from my fellow systems engineer Martin Baines, and we were driving all over the region in cool company cars (I had a Citroen BX 16V) selling a really hot product.

Tuning 52

Tuning Benchmarking Engineering C++ 52

Adrian Cockcroft

JANUARY 20, 2023

Here’s some predictions I’m making: Jack Dongarra’s efforts to highlight the low efficiency of the HPCG benchmark as an issue will influence the next generation of supercomputer architectures to optimize for sparse matrix computations. In early January a related paper was published by Satoshi Matsuoka et. petaflops, which is 0.8%

Architecture 52

Architecture Latency Benchmarking AWS 52

The Morning Paper

JUNE 27, 2019

Systems researchers are doing an excellent job improving the performance of 5-year old benchmarks, but gradually making it harder to explore innovative machine learning research ideas. Performance on accelerators matters because almost all current machine learning research, and most training of production models, uses them.

Systems 87

Systems Tuning Programming Innovation 87

O'Reilly

JULY 25, 2023

The inspiration (and title) for it comes from Mike Loukides’ Radar article on Real World Programming with ChatGPT , which shares a similar spirit of digging into the potential and limits of AI tools for more realistic end-to-end programming tasks. Setting the Stage: Who Am I and What Am I Trying to Build?

Programming 98

Programming Code Design Benchmarking 98