My name is Arseny Kapoulkine and this is my blog where I write about computer graphics, optimization, programming languages and related topics. I’m the author of pugixml, meshoptimizer and other projects.

22 January 2020 Learning from data

Machine learning is taking the world by storm. There’s amazing progress in many areas that were either considered intractable or had not reached a satisfying solution despite decades of research. A lot of results in machine learning are obtained using neural networks, but that’s just one class of algorithms. Today we’ll look at one key algorithm from meshoptimizer that was improved by getting the machine to find the best answer instead of me, the human1.

  1. A necessary disclaimer: I’m not a machine learning expert. It’s entirely possible that this article misuses some terms and that some analysis and conclusions here are wrong. You have been warned. 

12 December 2019 Three years of Metal

3 years ago, we ported our renderer to Metal. It didn’t take much time, it was a blast and it worked really well on iOS. Today Metal is in better shape than ever - and I’d like to talk a bit about that.

But first, if you have not read the original article, you might want to start with that; most of that still holds today.

17 July 2019 Robust pipeline cache serialization

When writing a Vulkan renderer, one has to learn a lot of new concepts. Some of them are easier to deal with than others, and one of the pretty straightforward additions is the pipeline cache. To make sure pipeline creation is as efficient as possible, you need to create a pipeline cache and use it whenever you need to create a new pipeline. To make sure subsequent runs of your application don’t have to spend the time repeatedly compiling the shader microcode, you need to save the pipeline cache data to a file, and load it next time your application starts. How hard can this possibly be?

20 April 2019 qgrep internals

In 2011-2012 I worked on FIFA Street, followed by FIFA EURO 2012 DLC and finally FIFA 13 - all of these games were based on the same codebase, and this codebase was HUGE. Given an unknown codebase, you need a way to quickly get around it - since you don’t know the code, you resort to search-based navigation, aka grep. Using Visual Studio Ctrl+Shift+F search on a HDD on a codebase this size means that every search takes minutes. This was frustrating and as such I decided to solve this problem.

11 March 2019 Small, fast, web

When implementing vertex/index decoders in meshoptimizer, the main focus was on lean implementation and decompression performance.

When your streaming source is capable of delivering hundreds of megabytes per second, as is the case with SSD drives, and you want to accelerate loading by compressing the data further, you need to be decompressing at multiple hundreds of megabytes per second, ideally a gigabyte, to make sure a small number of CPU cores can keep up with IO. Keeping implementation lean meant it was easy to understand and optimize. To supplant the inevitable loss of compression ratio, the codecs were designed in such a way that their output can be compressed further using lossless general purpose compressors such as lz4 or zstd, thus offering an easy tradeoff between compression ratio and performance.

This set of implementation decisions unexpectedly resulted in algorithms that are a pretty good fit for delivering web content. The performance penalty often induced by running code in the browser is offset by the incredibly high baseline performance, and most web content has “free” gzip compression efficiently applied during the download process. This article will describe the evolution of decoder.js, a WebAssembly port of geometry decoders from meshoptimizer.

More…