All Projects → hughperkins → Tf Coriander

hughperkins / Tf Coriander

Licence: apache-2.0
OpenCL 1.2 implementation for Tensorflow

Projects that are alternatives of or similar to Tf Coriander

Coriander
Build NVIDIA® CUDA™ code for OpenCL™ 1.2 devices
Stars: ✭ 665 (-14.19%)
Mutual labels:  nvidia, intel, gpu, opencl, ubuntu, mac
Parenchyma
An extensible HPC framework for CUDA, OpenCL and native CPU.
Stars: ✭ 71 (-90.84%)
Mutual labels:  nvidia, intel, gpu, opencl
Ilgpu
ILGPU JIT Compiler for high-performance .Net GPU programs
Stars: ✭ 374 (-51.74%)
Mutual labels:  nvidia, intel, gpu, opencl
Realsr Ncnn Vulkan
RealSR super resolution implemented with ncnn library
Stars: ✭ 357 (-53.94%)
Mutual labels:  nvidia, intel, gpu
Pyopencl
OpenCL integration for Python, plus shiny features
Stars: ✭ 790 (+1.94%)
Mutual labels:  nvidia, gpu, opencl
Srmd Ncnn Vulkan
SRMD super resolution implemented with ncnn library
Stars: ✭ 186 (-76%)
Mutual labels:  nvidia, intel, gpu
Waifu2x Ncnn Vulkan
waifu2x converter ncnn version, runs fast on intel / amd / nvidia GPU with vulkan
Stars: ✭ 1,258 (+62.32%)
Mutual labels:  nvidia, intel, gpu
docker-nvidia-glx-desktop
MATE Desktop container designed for Kubernetes supporting OpenGL GLX and Vulkan for NVIDIA GPUs with WebRTC and HTML5, providing an open source remote cloud graphics or game streaming platform. Spawns its own fully isolated X Server instead of using the host X server, therefore not requiring /tmp/.X11-unix host sockets or host configuration.
Stars: ✭ 47 (-93.94%)
Mutual labels:  ubuntu, gpu, nvidia
gpu-passthrough
A GPU passthrough tutorial using libvirt and KVM on GNU/Linux
Stars: ✭ 57 (-92.65%)
Mutual labels:  ubuntu, intel, nvidia
darknet
Darknet on OpenCL Convolutional Neural Networks on OpenCL on Intel & NVidia & AMD & Mali GPUs for macOS & GNU/Linux
Stars: ✭ 160 (-79.35%)
Mutual labels:  opencl, intel, nvidia
Macos Egpu Cuda Guide
Set up CUDA for machine learning (and gaming) on macOS using a NVIDIA eGPU
Stars: ✭ 187 (-75.87%)
Mutual labels:  nvidia, gpu, mac
Clojurecl
ClojureCL is a Clojure library for parallel computations with OpenCL.
Stars: ✭ 266 (-65.68%)
Mutual labels:  nvidia, intel, opencl
Compute Runtime
Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
Stars: ✭ 593 (-23.48%)
Mutual labels:  intel, gpu, opencl
Aparapi
The New Official Aparapi: a framework for executing native Java and Scala code on the GPU.
Stars: ✭ 352 (-54.58%)
Mutual labels:  gpu, opencl
Arrayfire Python
Python bindings for ArrayFire: A general purpose GPU library.
Stars: ✭ 358 (-53.81%)
Mutual labels:  gpu, opencl
Bayadera
High-performance Bayesian Data Analysis on the GPU in Clojure
Stars: ✭ 342 (-55.87%)
Mutual labels:  gpu, opencl
Cuda Api Wrappers
Thin C++-flavored wrappers for the CUDA Runtime API
Stars: ✭ 362 (-53.29%)
Mutual labels:  nvidia, gpu
Hipsycl
Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs
Stars: ✭ 377 (-51.35%)
Mutual labels:  gpu, opencl
Bitcracker
BitCracker is the first open source password cracking tool for memory units encrypted with BitLocker
Stars: ✭ 463 (-40.26%)
Mutual labels:  gpu, opencl
Anakin
High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.
Stars: ✭ 488 (-37.03%)
Mutual labels:  nvidia, intel

Tensorflow-cl

Run Tensorflow on OpenCL™ 1.2 devices

  • tested on:
    • Mac Sierra using Radeon Pro 450 GPU (thank you ASAPP :-) )
    • Ubuntu 16.04, using NVIDIA K520
  • should work theoretically on any OpenCL 1.2 GPU

Piccie

On a Mac:

Execution speed

What's working

Installation

Tests

Design/architecture

  • tensorflow code stays 100% NVIDIA® CUDA™
  • Coriander compiles the NVIDIA® CUDA™ code into OpenCL
  • Cedric Nugteren's CLBlast provides BLAS (matrix multiplications)

Presentation on Coriander at this year's IWOCL 2017

Related projects

News

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].