This is a bug/curiosity in PowerShell that I stumbled upon a few years ago, but never wrote up. The behavior hasn’t changed significantly in the intervening verions, so now I’m finally getting around to a quick blog post. Here’s a chart detailing the runtime of 4 different PowerShell approaches to de-duplicate a collection - i.e. filter an input collection to just its unique elements. Code used for the benchmark can be found here. Same chart, with log scale so it’s a little easier to distinguish the [...]

As part of the small minority of devs at my company who primarily run Windows, I’m accustomed to working around occasional Unix-specific behaviors in our build and deployment systems. Cygwin makes most stuff just work, I can fix simple incompatibilities myself, and as a last resort I can always boot into OSX for a while if needed. One oddity that took me quite some time to diagnose, though, was Git’s strange behavior when dealing with files in our repo whose names contained a colon. What happens when [...]

This blog started on wordpress.com back in February of 2012, then in November 2013 I moved it to a hosted WordPress.org site here at latkin.org. WordPress is quite nice, but it seemed like it was a bit heavyweight given my very basic needs. I’ve wanted to slim down the site and get more hands-on for a while, now. Over the past few weeks, I’ve been migrating the entire blog to the Hugo static site generator. I’m pleased to announce that the migration is complete! Why Hugo? No particular reason. I happe[...]

It's pretty straightforward to do basic benchmarking of a single, self-contained piece of code in .NET. You just make a Stopwatch sandwich (let sw = Stopwatch.StartNew(); <code goes here>; sw.Stop()), then read off the elapsed time from the Stopwatch. What about measuring the throughput of a data pipeline? In this case one is less interested in … Continue reading Benchmarking IEnumerables in F# - Seq.timed →

It’s pretty straightforward to do basic benchmarking of a single, self-contained piece of code in .NET. You just make a Stopwatch sandwich (let sw = Stopwatch.StartNew(); <code goes here>; sw.Stop()), then read off the elapsed time from the Stopwatch. What about measuring the throughput of a data pipeline? In this case one is less interested in timing a single block of code from start to finish, and more interested in bulk metrics like computations/sec or milliseconds/item. Oftentimes such pipelines are[...]