vuda
vuda copied to clipboard
VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.
The notes say: VUDA does not provide any support for compiling CUDA C kernels directly to SPIR-V (yet) Is there a roadmap or technical approach you're planning to support that?...
In my opinion, a very strange startup syntax has been chosen. ```cpp #if defined(__NVCC__) add(dev_a, dev_b, dev_c, N); #else const int stream_id = 0; vuda::launchKernel("add.spv", "main", stream_id, blocks, threads, dev_a,...
I suggest using the real device buffer address for pointers. And use the extension `VK_KHR_buffer_device_address`. For passing in device, I suggest using inline uniform or push constant. Also, I suggest...
I'm new to Vuda, Vulkan and MoltenVK. I have the recent MoltenVK and the Vulkan SDK installed (and validation examples run - vkcube, vkvia and vulkaninfo) but I'm stuck with...
Hi, trying Vuda for the first time here. To get the `simple` example to compile, I had to fix a few errors in the `inc` folder that my `g++` (version...
Tested and builds against Vulkan 1.4.328.1
## Description I recently implemented push constant support for a VUDA fork that I have. This feature allows efficient passing of small amounts of data (like configurations or flags) from...