Awesome GitHub RepositoriesTiled Memory Access Patterns

Triton is a parallel computing framework and high-level programming language designed for writing custom compute kernels. It functions as a deep learning compiler, translating complex mathematical operations into high-throughput instructions that maximize hardware utilization and memory efficiency on graphics processing units. The framework distinguishes itself through a hardware-agnostic compute abstraction that allows developers to define kernels without manual low-level tuning. It employs just-in-time compilation to generate optimized binary instructions at runtime, utilizing static data f

AISystem is a comprehensive AI full-stack infrastructure project covering the entire pipeline from AI chip architecture to high-level training frameworks. It encompasses the development of AI compiler frameworks, inference engines, and distributed training orchestrators designed to coordinate workloads across a heterogeneous compute stack of CPUs, GPUs, and NPUs. The project focuses on the deep integration of software and hardware, employing software-hardware co-design to align tensor layouts with physical memory structures. It provides specialized capabilities for accelerating Transformer mo

This project is a comprehensive educational resource and programming course covering C++ language semantics and features from C++03 through C++26. It provides structured tutorials and technical guides focused on modern C++ development. The material offers specialized instruction on template metaprogramming, including the use of type traits and compile-time computations. It features detailed guides on concurrency and parallelism for multi-core execution, as well as a reference for software design applying SOLID principles and RAII. Additionally, it covers build performance optimization to redu

Cutlass is a collection of C++ templates and Python interfaces for implementing high-performance linear algebra operations on NVIDIA GPUs. It provides a kernel composition framework for designing custom GPU kernels and a mixed-precision tensor library capable of executing operations across diverse data formats, ranging from 64-bit floating point to 4-bit integers. The project features a toolkit for operator fusion that integrates activation functions and bias calculations directly into matrix multiplication kernels to reduce memory passes. It also includes a Python-based domain-specific langu

LeetCUDA is a collection of high-performance GPU kernel libraries focusing on memory optimization, activation functions, and attention mechanisms. It serves as a reference library for CUDA kernel implementations, ranging from basic element-wise operations to complex neural network components, and provides Python bindings to integrate these kernels into deep learning workflows. The project is distinguished by its focus on low-level hardware optimizations. This includes the use of tensor cores for half-precision matrix multiplication, asynchronous data pipelining with double buffering, and shar

XiangShan is a high-performance RISC-V processor core and a hardware description language framework. It provides a construction-based system for designing, simulating, and verifying complex processor micro-architectures and peripheral devices. The project includes a high-performance CPU simulator used for architectural exploration and functional verification of processor execution. The project implements a superscalar out-of-order CPU architecture that uses renaming and reorder buffers to execute instructions in parallel. It generates synthesizable Verilog files from hardware descriptions to

Flashlight ist eine eigenständige C++-Bibliothek für maschinelles Lernen und Tensor-Berechnungen, die zum Erstellen und Trainieren neuronaler Netze verwendet wird. Sie fungiert als umfassendes Framework für neuronale Netze und Engine für automatische Differenzierung und bietet Werkzeuge zur Konstruktion von Berechnungsgraphen und zur Berechnung von Gradienten via Backpropagation. Das Projekt dient als Framework für verteiltes Training und nutzt All-Reduce-Operationen zur Synchronisation von Gradienten und Parametern über mehrere Rechenknoten und Geräte hinweg. Es zeichnet sich durch eine tiefe Integration von leistungsstarker Tensor-Manipulation, nativer Interoperabilität mit Gerätespeichern und einem System zur Synchronisation von Gewichten über verteilte Worker aus, um das Training großskaliger Modelle zu beschleunigen. Das Framework deckt eine breite Palette an Deep-Learning-Funktionen ab, einschließlich modularer Schichtkomposition für den Entwurf komplexer Architekturen wie Residual-Blöcke und rekurrente Zellen. Es bietet umfangreiche Datenmanagement-Utilities für Ingestion und Prefetching sowie Serialisierungssysteme zur Persistierung von Modellzuständen. Zusätzlich enthält es eine Suite an Überwachungs- und Observability-Tools zur Verfolgung von Trainingsmetriken und zur Messung von Sequenzfehlern. Die Bibliothek ist in C++ implementiert.

TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc

perf-ninja is a collection of educational resources and curricula focused on CPU architecture, memory hierarchies, SIMD programming, and low-level performance engineering. It provides instructional material and practical labs for identifying and fixing CPU bottlenecks, such as cache misses and branch mispredictions. The project differentiates itself through specialized training in hardware-level optimizations, including the use of compiler intrinsics for SIMD vectorization and the implementation of branchless predicate execution to eliminate pipeline stalls. It also covers advanced binary-lev