cutlass
Open3D
Our great sponsors
cutlass | Open3D | |
---|---|---|
16 | 11 | |
4,496 | 10,436 | |
5.5% | 2.3% | |
8.8 | 8.6 | |
3 days ago | 1 day ago | |
C++ | C++ | |
GNU General Public License v3.0 or later | MIT |
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.
cutlass
-
Optimization Techniques for GPU Programming [pdf]
I would recommend the course from Oxford (https://people.maths.ox.ac.uk/gilesm/cuda/). Also explore the tutorial section of cutlass (https://github.com/NVIDIA/cutlass/blob/main/media/docs/cute/...) if you want to learn more about high performance gemm.
-
Want to understand INT8 better
The latter (and I guess you were asking about this one) is designed to accelerate NN inference in reduced precision. It is possible to use Tensor Cores for you own purposes, mainly through CUTLASS. But because Tensor Cores are designed to execute matrix multiplications, it can be hard to adapt your problem to them. The performance with them is insane (IIRC 32x the performance of the INT32 pipeline), but only for matrix multiplication…
-
How do I deal with tensor core and cuda core with different precision?
If you want to learn about controlling Tensor Cores, the main way is through the CUTLASS library, that wraps the complexity of Tensor Cores into higher level abstractions. You can also look for mma/wmma instructions in the PTX specification, or for the WMMA API in CUDA.
-
AI’s compute fragmentation: what matrix multiplication teaches us
> we used tensor cores and managed to get back fp32 accuracy with 3 rounds of the things
Hey are you referring to 3xTF32 (https://github.com/NVIDIA/cutlass/tree/master/examples/28_am...)? IMO this is a perfect example where proper abstraction could save engineers non-trivial amount of time - imagine a compiler stack which allows 3xTF32 as a normal dtype and subsequent analysis compatible with this special dtype :-)
- With LLVM and MLIR, is manual cuda optimizing still important?
- CUTLASS 3.0 is now available
-
How to Optimize a CUDA Matmul Kernel for CuBLAS-Like Performance: A Worklog
This is a great post for people who are new to optimizing GPU code.
It is interesting to see that the author got this far without interchanging the innermost loop over k to the outermost loop, as is done in CUTLASS (https://github.com/NVIDIA/cutlass).
As you can see in this blog post the code ends up with a lot of compile-time constants (e.g. BLOCKSIZE, BM, BN, BK, TM, TN) one way to optimize this code further is to use an auto-tuner to find the optimal value for all of these parameters for your GPU and problem size, for example Kernel Tuner (https://github.com/KernelTuner/kernel_tuner)
-
pytorch example to actually see anything near 83 TFLOP/s on a RTX 4090?
Some examples here have a benchmark: https://github.com/NVIDIA/cutlass/blob/master/examples/24_gemm_grouped/gemm_grouped.cu
-
Create a bare CMake for Nvidia CUTLASS
I would like to make a minimum CMakeLists to use the CUDA CUTLASS library in another project. The build system is CMake, however I have little experience with CMake.
-
[D] What are some good resources to learn CUDA programming?
If you already know some C++, the Nvidia devblog is a great resource. Going further, Cub and Cutlass provide examples of efficient implementations for key operations at all hardware levels. Finally, this is more anecdotal but I always start my lectures on Cuda programming with the pictures in this doc page, to provide some intuition on the different memory layers that you can leverage to speed up a program. In any case, good luck :-)
Open3D
-
Does anyone else agree that the links to the latest development version of Open3D don't work?
I was going to file a bug about another issue, but I have to download the development version. This is why I want this solved quickly. None of the links seem to work: https://github.com/isl-org/Open3D/issues/6259
-
Import many photogrammetry software's scenes into Blender
Open3D (JSON, LOG, PLY) 1
- Open3D v0.17
-
CD PROJEKT RED announce The Witcher Remake in Unreal Engine 5
There's also Open3D (O3D) the point cloud library... http://www.open3d.org/
-
Update: Python code that takes pictures from different view points of a 3D model
would this help?
-
Creating a simple 3d engine to render a car for ML, how hard is it? Sim
http://www.open3d.org/ seems like a good choice. Is there anything better I'm missing?
-
3D Reconstruction of Indoor Environments using SLAM and deep learning on RGB-D Data.
Open3D v0.13.0 http://www.open3d.org/
-
Show HN: 3dasd – open-source DIY room-scale 3D scanner
Sweet work! If you are interested in 3D reconstruction, have a look at http://www.open3d.org.
- I have an idea for a project, not sure where or how to begin.
-
[D] Need advice on how to generate HD point clouds visuals for a presentation
I normally use Open3D (http://www.open3d.org/) for point cloud visualization, which besides free view also provides an interface for rendering. For the rotation effect, place your object in the world origin, and the camera at a fixed world position looking towards the object. For every desired angle, rotate your object around the required axis by that angle and render the view. Then combine to a gif or video for presentations.
What are some alternatives?
TensorRT - PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
PCL - Point Cloud Library (PCL)
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
pyrender - Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.
GPU-Puzzles - Solve puzzles. Learn CUDA.
Meshroom - 3D Reconstruction Software
triton - Development repository for the Triton language and compiler
three.js - JavaScript 3D Library.
Chess_BinaryNeuralNetwork - Training and Code Emitting Library for Binary Neural Networks
moderngl - Modern OpenGL binding for Python
shark-samples
blender - Official mirror of Blender