Distributed Accelerator OS

FpgaNIC is an FPGA-based Versatile 100Gb SmartNIC for GPUs

Synthesisable SIMT-style RISC-V GPGPU

Chisel: A Modern Hardware Design Language

The OpenCL ICD Loader project.

OpenCL SDK

F-Stack is an user space network development kit with high performance based on DPDK, FreeBSD TCP/IP stack and coroutine API.

Optimized primitives for collective multi-GPU communication

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

Basic LRP implementation in PyTorch