An Open Source Machine Learning Framework for Everyone

GoogleTest - Google Testing and Mocking Framework

Turi Create simplifies the development of custom machine learning models.

Optimized primitives for collective multi-GPU communication

Patterns and behaviors for GPU computing

Compressed numerical arrays that support high-speed random access

Numerical linear algebra software package

A fast deep neural network library (CPU) for speech recognition

Emulating DMA Engines on GPUs for Performance and Portability

A project to quickly detect discrepancies in floating point computation across hardware, compilers, libraries and software.

Half precision floating point C++ library (imported from sourceforge upstream).

Distributed adaptive octree construction, 2:1 balancing & partitioning based on space filling curves

Multi-dimensional array programming framework for C++ and multi-GPU CUDA applications

GPU Drano Static Analysis for GPU programs.

Convert CUDA programs from float data type to half or half2 with SIMDization

Evaluating high order derivative tensors directly via reverse mode AD in Cpp.

Playground for learning languages, libraries, and frameworks

Intermediate Computational Graph Representation for Deep Learning Systems

VULFI

Protecting Structured Address Computations against Soft Errors