It needs to be written down

atomics, AMD Radeon and SYCL (Part 4)

Jan 10, 20241 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...

atomics, AMD Radeon and SYCL (part 3)

Dec 28, 20231 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, AMD Radeon and SYCL (Part 2)

Dec 22, 20231 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...

atomics, AMD Radeon and SYCL

Dec 21, 20231 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....

WSL2, ZeroMQ and Windows sockets

Dec 1, 20231 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...

oneAPI and Nvidia

Nov 18, 20231 min read

I forgot, oneAPI and Nvidia integration isn't available on Windows yet. sigh