Projects sharing features with GPU Puzzles

This library is a web-based framework designed for general-purpose parallel processing and high-performance computation on graphics hardware. It provides a toolkit for executing complex mathematical operations, physics simulations, and procedural visualizations directly within the browser by leveraging the graphics processor for data-intensive tasks. The framework distinguishes itself through automated shader management, which ensures consistent execution across diverse hardware and browser environments. It achieves this by transpiling modern shader syntax into legacy versions and automatical

Material for gpu-mode lectures

Shader School is an interactive learning platform and graphics programming course designed for mastering GLSL shader development. It provides a structured curriculum for learning GPU programming and the technical foundations of programmable shaders through a series of browser-based coding exercises. The platform functions as an interactive shader sandbox and WebGL graphics tutorial, allowing users to write and test code within a real-time interface. This environment provides immediate visual feedback, enabling the practice of interactive graphics development and web-based shader workshopping

ArrayFire is a hardware-agnostic compute framework and JIT-compiled tensor engine designed for high-performance numerical computing. It serves as a GPU numerical computing library and parallel signal processing toolkit that abstracts hardware backends, allowing the same codebase to execute across various GPU architectures and CPUs. The project distinguishes itself through a JIT engine that uses expression compilation to fuse operations and minimize memory overhead. It employs a deferred execution graph to optimize computation chains and provides interoperability primitives to share data and e

Mistral Inference is a library for running Mistral large language models on a GPU, generating text from prompts with token streaming. It loads pretrained model weights from local disk or a remote registry into GPU memory, then produces output tokens one by one for real-time display in interactive applications. The library supports multimodal prompts that accept image URLs alongside text, enabling visual description and reasoning. It includes content safety guardrails that scan generated text against predefined policies to block or flag policy violations. For structured interactions, it provid

Gorgonia is a Go library that provides an automatic differentiation engine and a computation graph framework for building and training neural networks. It functions as a CUDA-accelerated tensor library and a SIMD-optimized math library, enabling machine learning workflows entirely within the Go ecosystem. The library distinguishes itself through a dual-backend architecture that dispatches neural network operations to either a GPU or CPU depending on CUDA availability at runtime. It constructs differentiable directed acyclic graphs of tensor operations, supports reverse-mode automatic gradient

Chainer is an open-source deep learning framework built around define-by-run automatic differentiation, where computation graphs are constructed dynamically during forward execution. This imperative approach allows networks to be built using standard Python control flow, with gradients computed automatically through reverse-mode differentiation on the dynamically recorded graph. The framework supports GPU acceleration through a NumPy-compatible array backend with CUDA and cuDNN support, and provides a pluggable device abstraction that lets users switch between CPU and GPU computation without c

Caffe is a high-performance deep learning framework and convolutional neural network library designed for training and deploying neural networks. It functions as a GPU-accelerated machine learning engine with a core implemented in C++ to enable high-throughput tensor operations. The project utilizes a declarative configuration system where model architectures and hyperparameters are defined in external text files, separating the network design from the execution code. It includes a model serialization system to export trained weights and topologies into binary files for efficient deployment a

Lenia is a scientific research tool and computational framework for modeling, visualizing, and analyzing artificial life. It functions as a continuous cellular automata engine that simulates emergent biological patterns using continuous space-time grids and kernel-based convolutional dynamics. The system leverages a GPU-accelerated simulation framework to perform parallel tensor computations and massive grid updates in real time. It includes hardware-accelerated 3D rendering to visualize high-dimensional cellular structures and their structural complexity. The platform provides capabilities

CUDA.jl provides a programming interface for executing custom kernels and performing parallel array computing directly on NVIDIA graphics hardware using the Julia language. It serves as a framework for compiling and scheduling user-defined functions across multiple processing cores, enabling high-performance data processing and task synchronization. The library distinguishes itself through a custom compiler backend that translates high-level language functions into hardware-specific machine code. It manages complex hardware interactions through asynchronous stream scheduling, unified memory m

Codon is an LLVM-based Python compiler and statically typed implementation that translates source code into optimized machine instructions. It functions as a high-performance numerical backend and a GPU computing framework designed to remove runtime overhead. The project implements a compiled alternative to NumPy, translating array logic directly into machine code. It differentiates itself by generating specialized hardware kernels for graphics processors and utilizing static type inference to enable aggressive machine-code optimization. The system provides capabilities for parallel workload

This project provides Rust bindings for the TensorFlow C API, serving as a tensor computation interface and machine learning library. It enables the construction and execution of machine learning models and neural networks by bridging a systems language to high-performance backends. The framework supports GPU-accelerated computing to increase the speed of model training and inference by offloading mathematical operations to graphics processing units. It offers both graph-based computation for defining static network architectures and an eager execution mode for immediate operation calls durin

Flux.jl is a deep learning framework and numerical computing toolkit written in Julia. It serves as a machine learning library for designing and training neural networks, providing a system for automatic differentiation to optimize model parameters. The framework enables deep learning development and machine learning research by representing layers as parameterized functions. It supports scientific machine learning, integrating neural networks into workflows for solving physical and mathematical problems. The toolkit provides native GPU acceleration for tensor computations and utilizes rever

This project is a PyTorch deep learning tutorial and educational resource. It provides a structured curriculum and step-by-step guides for designing, training, and validating neural networks from scratch. The resource includes specific guides on computer vision implementation, focusing on object detection and image classification using convolutional neural networks. It also provides instructions for optimizing model performance through hardware acceleration to reduce training time. The materials cover the full model development lifecycle, including tensor operations, image dataset preparatio

Hedgehog Lab is a browser-based scientific computing environment designed for executing numerical analysis, matrix operations, and symbolic computation directly within a web browser. It functions as a native engine for algebraic manipulation and equation solving, allowing users to perform complex mathematical tasks without requiring external server-side infrastructure or software installations. The platform distinguishes itself by leveraging hardware acceleration to process large-scale linear algebra and matrix calculations. It integrates a symbolic engine that parses mathematical expressions

Keras-js is a JavaScript inference engine and browser-based machine learning framework designed to execute pre-trained Keras neural networks. It allows for client-side model inference in web browsers or Node.js environments without the requirement of a backend server. The library utilizes a WebGL tensor accelerator to map mathematical operations to the graphics processor for hardware acceleration. To maintain user interface responsiveness during heavy computations, it incorporates a web worker inference runtime that executes neural network processing in background threads. The system support

This repository is a collection of reference implementations and programming examples for the CUDA Toolkit. It serves as a GPGPU implementation guide and a parallel computing reference, providing code for using graphics hardware to perform general-purpose calculations and high-performance parallel processing. The project provides specific samples for GPU kernel development and resource management. These include demonstrations of multi-GPU communication, peer-to-peer memory access, and system hardware inspection to coordinate distributed GPU resources. The codebase covers a wide range of capa

Tiny-gpu is an educational hardware emulator designed to model the fundamental operations of a graphics processing unit. It provides a software environment that simulates hardware data flow and parallel computing logic, allowing users to visualize the internal execution cycles and memory structures characteristic of graphics hardware. The project distinguishes itself by implementing a cycle-accurate execution model that tracks the progression of operations through discrete processing steps. It utilizes a fixed-function pipeline to process geometric data through sequential transformation and r

NumPy is a foundational library for scientific computing in Python, providing a comprehensive framework for managing and manipulating large-scale numerical information. It centers on high-performance multidimensional array objects that serve as the primary data structure for complex mathematical operations and data analysis workflows. The library distinguishes itself through specialized mechanisms for handling multidimensional data, including advanced indexing, slicing, and broadcasting techniques that allow for efficient operations across arrays of varying shapes. It utilizes strided metadat

This project is a video quality assessment library and suite of tools designed to quantify video degradation and identify banding artifacts. It provides a perceptual video quality metric that compares distorted video streams against a high-quality reference to estimate human visual perception. The toolkit includes a specialized system for training and validating custom perceptual quality models using specific datasets. It also features a contrast-aware multiscale index specifically for detecting contouring and banding artifacts in video streams. The library covers objective video metric calc

snarkOS is a distributed runtime environment and zero-knowledge proof blockchain designed for deploying and managing applications that rely on zero-knowledge cryptographic primitives. It functions as a decentralized ledger that uses zero-knowledge proofs to verify state transitions and transactions without revealing private data. The system utilizes a bonded-account consensus network where validators lock assets as collateral to secure a global state. It features an encrypted state ledger to track application data privately and a GPU-accelerated prover that offloads heavy cryptographic comput

pybind11 is a header-only C++ binding library that exposes C++ functions and classes as Python modules. It serves as a language bridge, mapping native types, inheritance hierarchies, and lambda functions into compatible Python objects to enable high-performance native code execution. The library includes specialized integration for NumPy arrays, utilizing buffer protocols to bind native C++ data without copying memory. It provides a toolkit for mapping C++ standard library data structures and smart pointers into the Python environment while maintaining cross-language memory management. The p

Drake is a robotics simulation framework and control system modeling tool used for designing, simulating, and verifying the dynamics of complex robotic systems. It functions as a multibody dynamics simulator and a mathematical optimization library, providing a suite of algorithms for trajectory optimization and the simulation of articulated robots. The framework is distinguished by its block-diagram system for composing dynamical subsystems and its ability to formulate and solve diverse mathematical programs, including linear, quadratic, and nonconvex nonlinear problems. It supports specializ

This project is an academic curriculum repository and educational resource center for studying probability, statistics, and machine learning. It serves as a deep learning course website and a hub for instructional materials, providing a structured collection of content designed to teach neural network architectures. The repository distinguishes itself by combining a comprehensive educational resource with a machine learning project archive. It provides a curated set of research examples and implementation guides for a wide range of models, including multilayer perceptrons, convolutional netwo

This project is an educational resource and comprehensive guide for implementing and deploying deep learning models using the PyTorch framework. It provides a structured learning curriculum consisting of tutorials and notebooks that cover neural network architectures, data pipelines, and model optimization across multiple AI domains. The curriculum includes practical implementation guides for building convolutional networks, transformers, and recurrent models. It specifically focuses on workflows for computer vision, including image classification, object detection, and segmentation, as well

dlib is a C++ machine learning toolkit and data analysis framework. It provides a collection of algorithms and utilities for building predictive modeling applications and performing statistical analysis on large datasets within native C++ environments. The project functions as a binding library that wraps low-level C++ machine learning algorithms into high-level Python scripting interfaces. This allows for the integration of high-performance native implementations with Python for machine learning development. The framework covers the implementation of predictive models, the execution of mach

webgl-fundamentals is a comprehensive educational resource and graphics tutorial for learning hardware-accelerated 2D and 3D rendering using the WebGL API. It serves as a structured 3D graphics curriculum and GPU programming reference, guiding users through the graphics pipeline from basic geometry to advanced rendering techniques. The project provides detailed guides on GLSL shader development, including the creation of vertex and fragment shaders. It specifically focuses on the implementation of real-time lighting models—such as directional, point, and spot lighting—and the application of s