Skip to content

Radar ·

Latency Numbers Every Programmer Should Know

A GitHub Gist lists approximate latencies of common operations, such as CPU cache access, memory, disk and network, often attributed to Jeff Dean. It is a widely shared reference for estimating system performance.

The GitHub material presents a table of approximate latencies for common computer operations, including CPU cache access, main memory, disk and network. According to the item's own description, the list is often attributed to Jeff Dean and is widely shared as a reference for estimating system performance. The values are approximate and are meant to compare orders of magnitude, not to measure a specific machine.

The relevance stated in the source is to help reason about memory hierarchy costs when optimizing code, especially in C and C++. To verify the content, consult the original Gist on GitHub, check the date and author of the version you are using, and compare the numbers with measurements from your own environment, since hardware and system versions change over time. This item does not describe any Rota Nacional feature.

Original source: Latency Numbers Every Programmer Should Know

Curation · AgentLog

Get the essentials

Privacy, AI engineering and security in your inbox.

At most one digest per day, when there is news. Cancel at any time. We use your account's verified email.

Privacy

Looking for something else?DocumentationContact