acm-header
Sign In

Communications of the ACM

Latest Practice



Research for Practice
From Communications of the ACM

Research for Practice: Troubling Trends in Machine-Learning Scholarship

Some ML papers suffer from flaws that could mislead the public and stymie future research.

Identity by Any Other Name
From Communications of the ACM

Identity by Any Other Name

The complex cacophony of intertwined systems.

Research for Practice: Edge Computing
From Communications of the ACM

Research for Practice: Edge Computing

Scaling resources within multiple administrative domains.

Corp to Cloud: Google's Virtual Desktops
From Communications of the ACM

Corp to Cloud: Google's Virtual Desktops

How Google moved its virtual desktops to the cloud.

Research for Practice
From Communications of the ACM

Research for Practice: Knowledge Base Construction in the Machine-Learning Era

Three critical design points: Joint learning, weak supervision, and new representations.

The Mythos of Model Interpretability
From Communications of the ACM

The Mythos of Model Interpretability

In machine learning, the concept of interpretability is both important and slippery.

Workload Frequency Scaling Law
From Communications of the ACM

Workload Frequency Scaling Law: Derivation and Verification

Workload scalability has a cascade relation via the scale factor.

Research for Practice
From Communications of the ACM

Research for Practice: FPGAs in Datacenters

Expert-curated guides to the best of CS research.

Research for Practice: Prediction-Serving Systems
From Communications of the ACM

Research for Practice: Prediction-Serving Systems

What happens when we wish to actually deploy a machine learning model to production?

C Is Not a Low-Level Language
From Communications of the ACM

C Is Not a Low-Level Language

Your computer is not a fast PDP-11.

Canary Analysis Service
From Communications of the ACM

Canary Analysis Service

Automated canarying quickens development, improves production safety, and helps prevent outages.

Titus
From Communications of the ACM

Titus: Introducing Containers to the Netflix Cloud

Approaching container adoption in an already cloud-native infrastructure.

The Calculus of Service Availability
From Communications of the ACM

The Calculus of Service Availability

You're only as available as the sum of your dependencies.

Research For Practice
From Communications of the ACM

Research For Practice: Cryptocurrencies, Blockchains, and Smart Contracts; Hardware For Deep Learning

Expert-curated guides to the best of CS research.

Heterogeneous Computing
From Communications of the ACM

Heterogeneous Computing: Here to Stay

Hardware and software perspectives.

Research For Practice
From Communications of the ACM

Research For Practice: Distributed Transactions and Networks as Physical Sensors

Expert-curated guides to the best of CS research.

Life Beyond Distributed Transactions
From Communications of the ACM

Life Beyond Distributed Transactions

An apostate's opinion.

Should You Upload or Ship Big Data to the Cloud?
From Communications of the ACM

Should You Upload or Ship Big Data to the Cloud?

The accepted wisdom does not always hold true.

Challenges of Memory Management on Modern N-UMA Systems
From Communications of the ACM

Challenges of Memory Management on Modern N-UMA Systems

Optimizing NUMA systems applications with Carrefour.

Fail at Scale
From Communications of the ACM

Fail at Scale

Reliability in the face of rapid change
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account