CUDA Jobs

My 3D scanner streams PCD point-cloud files that contain spiral-shank bolts mixed with other hardware. I need a compact, CUDA-friendly C++ solution that runs directly on an NVIDIA Jetson Orin NX, spots every bolt in each cloud, records the head-center XYZ (and, if practical, its axis direction), and writes the results to a structured XML file. Performance targets • Accuracy: at least 95 % correct identification on the annotated dataset I will supply. • Speed: real-time or near real-time processing on the Orin NX under the standard JetPack image. You are welcome to build on open-source libraries such as PCL, Open3D, Eigen, cuBLAS or TensorRT, provided everything can be compiled through CMake and redistributed without license issues. Deliverables • Well-documented...

I am rapidly up-skilling in CUDA C++ and want an experienced mentor who can walk me through the real-world use of the core foundational libraries—Thrust, CUB, and libcudacxx. My main need is to see clean, well-explained example implementations and concrete use cases rather than abstract theory. Here is what I have in mind: • Short, focused code samples that highlight best-practice patterns in each library (device vectors, reductions, custom kernels, cooperative groups, etc.). • Step-by-step explanations of how these examples map to GPU execution, memory hierarchies, and performance considerations. • Guidance on how to slot each snippet into an existing CMake-based project so I can experiment immediately. I already have a CUDA 12.x toolchain set up with Visual ...

A decentralized AI compute platform designed to connect GPU providers with AI workloads through a distributed computing network. Instead of running AI workloads entirely on centralized cloud infrastructure, the platform allows independent miners to contribute GPU resources for tasks such as AI inference, model processing, fine-tuning, and other compute-intensive workloads. The system coordinates available GPU resources, assigns workloads, monitors execution, and records completed compute jobs. A blockchain-based reward mechanism is used to track contributions and provide miners with transparent incentives based on the compute they provide. The architecture separates the blockchain layer from the actual AI computation: blockchain infrastructure handles identity, job accounting, verificati...