Aras Pranckevičius is a user on You can follow them or interact with them if you have an account anywhere in the fediverse. If you don't, you can sign up here.

Aras Pranckevičius

"Number One / Another One" by Fairlight & CNCD from Assembly 2018 just blew my mind. Absolute masterpiece.

RenderDoc v1.1 is now out! This release focusses on improved API and OS support, as well as a boatload of bug fixes.

Disney has released full data set of Motunui island from Moana movie:

Matt Pharr has an excellent blog series on making pbrt better at rendering it.

Retrospective of a year writing C code again (for those not also on twitter):

Me: Why is the rain pink in this area?

N: I just assumed it was a shader error.

Pathtracer part 14: I made it run on iOS, both CPU & GPU parts. Some info on Xcode GPU performance tools, and a tiny bit of NEON code.

(definitely not daily :)) Pathtracer part 13: nice GPU thread group data optimization suggested by @gfxbean, and a quick realization that Metal IR is just LLVM IR.

Ugh, so this Mastodon instance seems to be getting ~30 "fake" new users every day, and some of those end up posting spam. Are they trying to do a DoS attack on me, or what.

Really wish for some less-clicks user suspension / spam clearing tools in Mastodon right now :|

Woke up this morning to ~50 spam moderation reports on this Mastodon. Some influx of spam bots. Thx for reports everyone!

Daily Pathtracer part 12: buffer-oriented approach on the GPU. I produced some accidental garbage renderings, and learned some nsights.

Daily Pathtracer part 11: let's try a "buffer oriented" approach (is that what "wavefront" or "stream" tracing is? I don't know!)

Next up: maybe try the same on a GPU

Daily Pathtracer part 10: small update to have all implementations on the same page again; and a note on Mono C# performance tweaks.

Next up: let's do a stream/buffers oriented path tracer setup! (why? I don't know)

Daily Pathtracer part 9: a wild ryg appears and optimizes my code!

Next up: put these optimizations into C#, C#/Burst, GPU implementations.

I blogged about compilation time – compiling with -std=c++98 is (sometimes) much faster than -std=c++11

Daily Pathtracer part 8, where I'm learning more SIMD, and add more spheres to the test scene.

Daily Pathtracer is back! Part 7, where I'm learning about SIMD.

Next up: more SIMD.