Retrospective of a year writing C code again (for those not also on twitter): http://floooh.github.io/2018/06/02/one-year-of-c.html
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. http://aras-p.info/blog/2018/05/30/Pathtracer-14-iOS/
(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. http://aras-p.info/blog/2018/05/28/Pathtracer-13-GPU-threadgroup-memory-is-useful/
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!
The first Unity 2018.2 linux beta build is live! Featuring high dpi support!
Daily Pathtracer part 12: buffer-oriented approach on the GPU. I produced some accidental garbage renderings, and learned some nsights. http://aras-p.info/blog/2018/04/25/Daily-Pathtracer-12-GPU-Buffer-Oriented-D3D11/
Daily Pathtracer part 11: let's try a "buffer oriented" approach (is that what "wavefront" or "stream" tracing is? I don't know!) http://aras-p.info/blog/2018/04/19/Daily-Pathtracer-11-Buffer-Oriented/
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. http://aras-p.info/blog/2018/04/16/Daily-Pathtracer-10-Update-CsharpGPU/
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! http://aras-p.info/blog/2018/04/13/Daily-Pathtracer-9-A-wild-ryg-appears/
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. http://aras-p.info/blog/2018/04/11/Daily-Pathtracer-8-SSE-HitSpheres/
Daily Pathtracer is back! Part 7, where I'm learning about SIMD. http://aras-p.info/blog/2018/04/10/Daily-Pathtracer-Part-7-Initial-SIMD/
Next up: more SIMD.
New Unity Linux builds for 2017.4.0f1 and 2018.1.0b13 are available!
Release notes and downloads at https://forum.unity.com/threads/unity-on-linux-release-notes-and-known-issues.350256/page-2#post-3450797
Daily Pathtracer, Part 6. DX11/HLSL implementation (still not optimized whatsoever). http://aras-p.info/blog/2018/04/04/Daily-Pathtracer-Part-6-D3D11-GPU/
Next up: will do a break for a couple days; sustaining daily posts is hard :)
Daily Pathtracer, Part 5. Let's make a naïve, suboptimal, port to GPU via Apple Metal instead. http://aras-p.info/blog/2018/04/03/Daily-Pathtracer-Part-5-Metal-GPU/
Next up: I dunno, maybe a DX11 GPU implementation?
Daily Pathtracer, Part 4. Fixing wrong rendering, and using Mitsuba to know what "correct rendering" is. http://aras-p.info/blog/2018/03/31/Daily-Pathtracer-Part-4-Fixes--Mitsuba/
Next week: a super naïve ISPC implementation!