Interesting issues around cascading deletes in Postgres and how the indices are managed.

Need to mind the memory layout of your structs to get good performance. Often overlooked but that also includes the padding.

Probably more than you think in this setup. And even more in C++ with the STL having years of smart tricks behind it.

There's really something brewing at AMD. They're on a roll performance wise.

Indeed it's a very good new type of maps in many cases. Again a good illustration that nowadays memory layout is often more important than algorithmic complexity.

Too often people mistake the algorithmic complexity theory for the real performances you would get. This can't be further from the truth. The memory layout trumps all. As usual you need to measure.

A reminder that web frontend work isn't as easy as it sounds. It brings quite some caveats and his difficult to do well. Otherwise you wonder why things stutter or render badly.

When more concurrency might not help. Illustration with the case of database queries.

Careful how you use DISTINCT or ORDER BY on very large tables. You might want to reevaluate (after checking if there's a problem of course).

They're definitely handling this part right, they seem well ahead everyone else.

Nice post on how to approach problems suitable for SIMD.

This is too often forgotten. If you can avoid the "if" and your CPU will thank you for it.

Excellent piece diving deep into the opportunities to optimise an algorithm. The final speed up is impressive.

Interesting trick to detect table scans with SQLite. I can see that useful in development to optimize systems.

Or how to properly paginate results when you have a database.

More latency exploration on Linux for games. The results are interesting. Unsurprisingly the X11 vs Wayland difference is much less dramatic than what people make of it.

There are ways to have a lighter web. It leads to interesting techniques too.

Interesting Rust options to limit the amount of heap allocations if you're constrained by memory or for performance reasons.

Unsurprisingly cache locality is a very important factor. What's interesting here is that it still applies to a language like Javascript where you'd expect to not have enough control on the memory layout to reap any benefits.

Interesting article applying data oriented design to parsing tasks. This is really a good approach for performance.