Nothing here yet.
Nothing here yet.
Jan 10, 2024 · 1 min read · Looking closely at the atomics used in the backwards rasterizer, it appears that the computation only occurs across a block. The atomics could be replaced with a reduction! So, I tried writing it in SYCL and there's warp stalling and it crashes the c...
Join discussionDec 28, 2023 · 1 min read · Well, I tried to use AdaptiveCpp, but there's some weirdness about memcpy and memset going on. And, it looks like I'm not the only one to notice that atomics are terrible. Here's something that just came up five days ago that's exactly what I'm strug...
Join discussionDec 22, 2023 · 1 min read · I couldn't get AdaptiveCpp to compile the project. It segfaulted. Here are some resources for inlining assembly into SYCL for HIP/ROCm. Atomic performance issues in AdaptiveCpp. Dumping (or at least trying to) IR from icpx. HIP Clang inline assemb...
Join discussionDec 21, 2023 · 1 min read · Performance is atrocious for atomics on the 6600XT. Specifically, with SYCL. There's a thread from the GROMACS developers on why using AdaptiveCPP. And a thread from the IntelLLVM team. How bad is it for Gaussian Splatting? 100 iterations of ~30k par...
Join discussionDec 1, 2023 · 1 min read · Trying to fun SYCL-DiffRast through ZeroMQ between laptops using WSL2. There's a problem though: using zmq from WSL2 on the Zenbook Pro 15 locks the port out from the Windows side. The error is ZMQError: Address in use and it's apparently a WSL2 bug....
Join discussion