2026-10-16T11:40:37Z https://njump.me Dave Airlie (Unofficial) https://njump.me/npub15gapztwfejxsq7tan60p9cpetdkv0jctf80epugh5vey4wr3r6vszzu8pe https://cdn.jsdelivr.net/gh/twitter/twemoji@14.0.2/assets/72x72/1f427.png https://cdn.jsdelivr.net/gh/twitter/twemoji@14.0.2/assets/72x72/1f427.png https://njump.me/nevent1qqsg4lf4yvxqztk72rtd36w8smhxkjkduur4cacp6wwl84kx9256vwszyz3r5yfde8xg6qre0k0fuyhq89dke37tpdyaly83z73nyj4cwy0fjr5en5h jetlag diversions - llvmpipe 512-wide vector support<br/><br/>I was travelling last week, and got back to Mike rebasing the zink-video branch and using LLM powerups to fix the final bits of it. We had been locked in a death stare for a few years, and he flinched first. But it got me thinking about another stalled branch I started working on ages ago.<br/>Adding support for avx512 to llvmpipe. The basics have been there, but running LP_NATIVE_VECTOR_WIDTH=512 piglit exploded in a bunch of fragment shading paths, mostly blending and depth handling. This should work even without actual avx512, we just make LLVM generate worse code. I&#39;d gotten it most of the way and then fell over some 1d texture and RGB32 type failures and let it slide when more urgent work came up.<br/>Well this week I had tiredness, and inspired by Mike I decided to dust off my old branch and let Opencode + GPT Terra Pro 5.6 have a go at closing the final gaps. It started finding a bunch of problem, and I chewed through a lot of my monthly quota, and it was generating a lot of good work, but costing a lot of tokens and taking a long time. It closed the gap on a bunch of the 512 wide work over a day or two.<br/>I then decided to switch to Astra, and it was so much better/quicker/cheaper for this job. It started to find other problems in llvmpipe that I hadn&#39;t seen, it found some bugs in the 128-wide handling for 1D framebuffer fetch while looking at the code for 512-wide framebuffer fetch. It identified the current test gap and wrote a test filling it. It found a 128/256 difference on a misc piglit fog test and it identified the conversion path that was failing. I had it review the patch series I wrote and Terra had fixed, and it found a bunch of cleanups and cases where the 4/8/16 lane code be made common.<br/>I fixed a niche bug in geometry shader indirect loads (without the LLM) and an egl fd = -1 problem valgrind popped up.<br/>All the niche fixes are pushed, and the 512-wide support is in an MR, it&#39;s still all my code, I&#39;ve just cleaned it up a lot.<br/>I also don&#39;t have any avx512 hardware, so I can&#39;t answer is it faster until I either rent some AWS time or find a machine in RH, but if anyone else wants to test gears at least it should be possible now.<br/><br/><a href="https://airlied.blogspot.com/2026/10/jetlag-diversions-llvmpipe-512-wide.html">https://airlied.blogspot.com/2026/10/jetlag-diversions-llvmpipe-512-wide.html</a><br/><br/>#support #llvmpipe #mike #llm #terra #gptterra<br/><br/>#rss #feeds #linksharing #qwibbit 2026-10-17T02:53:37Z