Adrian Cockcroft

JUNE 21, 2022

Another big jump, but now it was my job to run benchmarks in the lab, and write white papers that explained the new products to the world, as they were launched. I also learned how marketing worked, and began to build my presentation and training skills as I was sent around the world by Sun to teach workshops and speak at events.

Tuning 52

Tuning Benchmarking Engineering C++ 52

The Morning Paper

JUNE 11, 2019

The goal here is to reduce the training times of DNNs by finding efficient parallel execution strategies, and even including its search time, FlexFlow is able to increase training throughput by up to 3.3x FlexFlow is evaluated over six real-world DNN benchmarks on two different GPU clusters. Expanding the search space.

Network 81

Network Strategy Hardware Benchmarking 81

Percona

JUNE 22, 2023

Typically, the servers are configured in a primary/replica configuration, with one server designated as the primary server that handles all incoming requests and the others designated as replica servers that monitor the primary and take over its workload if it fails. This flexibility can be crucial in designing a scalable architecture.

Availability 104

Availability Database Open Source Hardware 104

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

The Morning Paper

MAY 14, 2019

Last time around we looked at the DeathStarBench suite of microservices-based benchmark applications and learned that microservices systems can be especially latency sensitive, and that hotspots can propagate through a microservices architecture in interesting ways. ASPLOS’19. Seer in action.

Big Data 45

Big Data Cloud Performance Hardware 45

The Netflix TechBlog

JUNE 20, 2023

In the second approach, we show that a relatively simple, supervised sequential model (bidirectional LSTM or GRU) that uses rich, pretrained shot-level embeddings can outperform the current state-of-the-art baselines on our internal benchmarks. Figure 1: a scene consists of a sequence of shots.

Benchmarking 253

Benchmarking C++ Availability Programming 253

IO River

NOVEMBER 15, 2023

For example, if a request activates a rule designed to block SQL injection attempts, the WAF might automatically block that request, preventing it from reaching your web application.‍Security Custom rules can be designed to look for typical SQL injection patterns like UNION SELECT, --, or /*.‍2.

Traffic 52

Traffic Network Logistics Architecture 52

Alex Russell

APRIL 29, 2021

As an engineer on a browser team, I'm privy to the blow-by-blow of various performance projects, benchmark fire drills, and the ways performance marketing (deeply) impacts engineering priorities. With each team, benchmarks lost are understood as bugs. For example, an area where Apple is absolutely killing it is in mobile CPU design.

Media 145

Media Games Education Engineering 145

IO River

NOVEMBER 2, 2023

For example, if a request activates a rule designed to block SQL injection attempts, the WAF might automatically block that request, preventing it from reaching your web application.‍Security Flywheel‍‍When it comes to fortifying web applications, think of security as a flywheel—an ever-revolving cycle that gains momentum with each turn.

Traffic 40

Traffic Network Logistics Architecture 40

Alex Russell

MAY 9, 2022

Design: Performance is the gap between Figma mockups and the user experience of products for many, but not all , users. The extent to which a product performs well, the higher its likelihood of behaving in accordance to the approved design spec. At Level 5, serious training and guardrails are required to integrate new talent.

Performance 86

Performance Latency Metrics Engineering 86

O'Reilly

JULY 25, 2023

Here’s how I worked on it: I subscribed to ChatGPT Plus and used the GPT-4 model in ChatGPT (first the May 12, 2023 version, then the May 24 version) to help me with design and implementation. I liked how ChatGPT helped me work through the tradeoffs of these initial design decisions before diving head-first into coding.

Programming 98

Programming Code Design Benchmarking 98

The Netflix TechBlog

MARCH 14, 2023

Much of the ML literature focuses on model training, evaluation, and scoring. Dawn Chenette , Design Lead This approach had several benefits for product engineering. At the same time, we kept the design open enough to allow future extensibility. Incredible!” Thus, we didn’t build all the modules completely.

Media 291

Media Innovation Energy Architecture 291

Alex Russell

JANUARY 30, 2024

Engineering is the discipline of designing solutions under specific constraints. I fear we will not be so lucky; an entire generation has been trained to ignore reality, to prize tribalism rather than engineering rigor, and to devalue fundamentals. Those folks may not find the next couple of years to their liking.

Performance 90

Performance Network Mobile Speed 90

High Scalability

NOVEMBER 9, 2018

matei_zaharia : Since we opened #DAWNBench deep learning benchmark rolling submissions, there have been some cool entires. You can now train CIFAR10 for just $0.06 AMD is now using the second-gen Infinity Fabric to connect a multi-chip design with a 14nm I/O die serving as the linchpin of the design.

Internet 192

Internet Internet Scalability Blockchain 192

Highly Scalable

MARCH 10, 2015

Although these problems are very different, we are trying to establish a common framework that helps to design optimization and data mining tasks required for solutions. The design of the model heavily depends on the problem. This model helps to design targeted usage expansion campaigns. Propensity to category expansion.

Retail 152

Retail C++ Analytics Metrics 152

Smashing Magazine

AUGUST 24, 2021

TAPP is a transit application (for buses and trains). Continue reading below ↓ Meet Smashing Email Newsletter with useful tips on front-end, design & UX. Subscribe and get “Smart Interface Design Checklists” — a free PDF deck with 150+ questions to ask yourself when designing and building almost anything.

Development 119

Development Benchmarking Code Engineering 119

O'Reilly

OCTOBER 18, 2022

System designs can be wrong. When that data is used to train an AI system, that system can replicate our bad behavior with speed and scale. In this context, bias is often about system design and not about data or models. Data can be wrong. Predictions can be wrong. These errors can hurt people in very unfair ways.

Artificial Intelligence 116

Artificial Intelligence Government Healthcare Metrics 116

High Scalability

NOVEMBER 25, 2019

To help our customers manage ongoing data explosion, we have designed many of the core components over the last few years. I mean that as your scale grows then design patterns and strategies that used to work 2 years ago and allowed you to go from defensive to offensive positioning may buckle under pressure or becomes cost-prohibitive.

Architecture 52

Architecture Cache Azure Storage 52