tf-coriander

OpenCL 1.2 implementation for Tensorflow

Github stars Tracking Chart

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

News

Main metrics

Overview
Name With Ownerhughperkins/tf-coriander
Primary LanguageC++
Program languagePython (Language Count: 15)
Platform
License:Apache License 2.0
所有者活动
Created At2016-10-13 11:50:41
Pushed At2022-10-15 18:30:25
Last Commit At2018-02-06 18:48:39
Release Count23
Last Release Namev0.18.3 (Posted on )
First Release Namev0.1.0 (Posted on )
用户参与
Stargazers Count791
Watchers Count68
Fork Count91
Commits Count9.5k
Has Issues Enabled
Issues Count93
Issue Open Count42
Pull Requests Count8
Pull Requests Open Count1
Pull Requests Close Count0
项目设置
Has Wiki Enabled
Is Archived
Is Fork
Is Locked
Is Mirror
Is Private