Where the OBS AMD Encoder Is Heading

If you’ve actively watched the OBS AMD Encoder repository, you most certainly noticed a huge gap in code submissions and sudden bursts of commits now. This all has a reason. Read more

The Encoder Rebirth Update (OBS Studio AMD Encoder Plugin v1.9.9.6)

Today I bring you one of the only public pre-releases that are going to happen, as everything else requires AMD to release a Driver which fixes the AMF runtime and firmware. But enough of me, here’s the update which is the true star of this post: Read more

The future of AMD Encoder: HEVC on RX 4xx, Pre-Pass, VBAQ and more!

AMD released version 1.4 of the AMF SDK back in January and I quickly got to work familiarizing myself with the changes and new sample tools. I did some rather extreme tests with the encoder, which resulted in me reporting 8 Issues to the AMF Issue Tracker – mostly GPU crashes or encoding failures. But with that out of the way, Patrons have now finally received the first official pre-release build, just as I promised back in December 2016. But what’s actually inside? Read more

What is the fastest way to get an Inverse Square Root? (Part 2)

Part 1: What is the fastest way to get an Inverse Square Root? Last time I covered what the fastest way was for single precision floating point, but what about double precision floating point numbers? Do they behave the same or will we run into even more issues on older hardware? Since the market starts looking towards 128-bit integers and quad precision floating point numbers, it’s time to also test this one while it’s still ‘fresh’. Read more

What is the fastest way to get an Inverse Square Root?

Everyone who works with a 2D or 3D development studio knows that eventually you will run into hardware that is too slow. Wether that hardware is what you currently have or what your target demographic has doesn‘t matter – you‘ll hit this limit, even if you try not to. That‘s why some clever people came up with different ways to make things faster. Seperating the FPU from the IPU, SSE and AVX and the famous Quake III floating point hack. But which one performs the fastest, and can we make that one even faster? Read more

The Encoder Plugin has finally reached 1.3.0!

It has been a long road from 1.1.2 to 1.3.0 now, even going through two complete rewrites and a huge amount of pre-releases and release candidates. It definitely would not have been possible without all the support I have gotten throughout developing the plugin, be it through reporting issues, using the plugin, spreading the word or generally just chatting with me. Special thanks go out to my Patreon supporters: Kytos, nwgat.ninja, Markus, vektorDex, SneakyJoe, Kristian Kirkesaether (Sorry, I don’t know how you do the messed up ae), AJ, Jeremy Nieth, John Difool, Nico Thato and DaOrgest. Read more