kompute
GLSL
Our great sponsors
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kompute
-
Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'
The two I know of are IREE and Kompute[1]. I'm not sure how much momentum the latter has, I don't see it referenced much. There's also a growing body of work that uses Vulkan indirectly through WebGPU. This is currently lagging in performance due to lack of subgroups and cooperative matrix mult, but I see that gap closing. There I think wonnx[2] has the most momentum, but I am aware of other efforts.
[1]: https://kompute.cc/
-
[P] - VkFFT version 1.3 released - major design and functionality improvements
Great to see the positive momentum of this framework! Best wishes and upvotes from the Vulkan Kompute team :)
-
VkFFT: Vulkan/CUDA/Hip/OpenCL/Level Zero/Metal Fast Fourier Transform Library
To a first approximation, Kompute[1] is that. It doesn't seem to be catching on, I'm seeing more buzz around WebGPU solutions, including wonnx[2] and more hand-rolled approaches, and IREE[3], the latter of which has a Vulkan back-end.
[1]: https://kompute.cc/
-
I'm Having Trouble Building this Library...
I look in an example and see similar instructions, stating that the build should be quite simple. But again, it doesn't work. It generates a bunch of folders with Visual Studio stuff, but no executables, no libraries, or anything like that.
I can't figure out how, and there are no tutorials. According to https://kompute.cc/overview/build-system.html I should simply run "cmake -Bbuild". But this doesn't output what I need, and when I look in the Makefile I get the sense that this is more an example Makefile... but then that contradicts the above tutorial.
-
How to properly construct an abstraction layer with Vulkan
Kompute is in my opinion good example to take inspiration for abstractions.
-
Vulkan for Image Processing? Good choice?
Currently, there's a few Vulkan compute frameworks floating around (like Kompute). I would work with those. Kompute simplifies a lot of the biolerplate and seems like you could benefit from using it.
-
Paralell computing project
Try Kompute, a project from the Linux foundation. It is quite simple to use, and does not require deep knowledge of graphics API. It’s a bit painful to setup, but it kinda works well (and I have a project going on on it)
GLSL
-
GLSL shaders resources
You have access to physical (u64) global memory pointers through buffer_reference in GLSL, note you should be using buffer_reference2
-
You Can Use Vulkan Without Pipelines Today - Khronos Blog
GL_NV_ray_tracing is a vendor extension, but it does exist.
-
Learning Modern 3D Graphics Programming
The reports of my death are greatly exaggerated
https://github.com/KhronosGroup/GLSL/blob/master/extensions/...
-
Announcing Rust-CUDA 0.3; Hardware raytracing, cuBLAS, cuDNN, atomics, and more
Great work, I think you should look at memory semantics scope semantics https://github.com/KhronosGroup/GLSL/blob/master/extensions/khr/GL_KHR_memory_scope_semantics.txt
-
Resources for Vulkan GPGPU searched
memory scope semantics
-
Web-Based Vulkan GLSL Ray Tracing Emulator
Vulkan ray tracing typically uses GLSL as shader language. DirectX Raytracing (DXR) uses HLSL (but is restricted to run only on Windows).
Because Vulkan ray tracing is cross-platform, I have chosen GLSL for this project.
https://github.com/KhronosGroup/GLSL/blob/master/extensions/...
-
Web-based Vulkan GLSL Ray Tracing Emulator
The Vulkan GLSL Ray Tracing Emulator is an online application that aims to simulate the ray tracing shader pipeline from the Vulkan GL EXT ray tracing specification.
Yes, it is like "Shadertoy" for the new Vulkan GL EXT ray tracing specification.
-
Cross Platform GPU-Capable Framework?
This gets you most of small int arithmetic and 64 bit arithmetic (though f16 is missing, and that's annoying...) robust buffer access errors on out of bounds access in shader (can be disabled in other builds), descriptr indexing allows you to index descriptors, scalar block layout allows contiguous homogenous layouts of non pow2 aligned types ie float3, timeline semaphores allow better synchronization control, bufferDeviceAddess allows usage of pointers in shader code for global memory.
What are some alternatives?
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
VkFFT - Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library
OpenCLOn12 - The OpenCL-on-D3D12 mapping layer
godot-proposals - Godot Improvement Proposals (GIPs)
VulkanExamples - Examples and demos for the Vulkan C++ API
clspv - Clspv is a compiler for OpenCL C to Vulkan compute shaders
futhark - :boom::computer::boom: A data-parallel functional programming language
datoviz - ⚡ High-performance GPU interactive scientific data visualization with Vulkan
Rust-CUDA - Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
HIP - HIP: C++ Heterogeneous-Compute Interface for Portability