singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "wangwei (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SINGA-423) Deep learning over AMD GPUs
Date Thu, 31 Jan 2019 01:57:00 GMT

     [ https://issues.apache.org/jira/browse/SINGA-423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

wangwei updated SINGA-423:
--------------------------
    Description: 
GPU is a fueling factor for deep learning. Most deep learning libraries (including Singa)
are using Nvidia GPUs because [cuDNN|https://developer.nvidia.com/cudnn] from Nvida provides
almost all deep learning operations, which are also highly optimized.

 

This ticket is to provide support for AMD GPUs in Singa. AMD has provided a similar [library
|https://rocm.github.io/dl.html] as cuDNN. The task is then to integrate this library with
Singa's programming model, write the documentation and conduct the corresponding test.

 

Programming language: C++, CMake, OpenCL or [HIP|https://gpuopen.com/compute-product/hip-convert-cuda-to-portable-c-code/]

OS: Linux (Ubuntu or CentOS)

Tools: Github, JIRA,

Machine learning (ML) background: basics of ML and DL (deep learning)

 

  was:
GPU is a fueling factor for deep learning. Most deep learning libraries (including Singa)
are using Nvidia GPUs because cuDNN from Nviida provides almost all deep learning operations,
which are also highly optimized.

 

This ticket is to provide support for AMD GPUs in Singa. AMD has provided a similar [library
|https://rocm.github.io/dl.html] as cuDNN. The task is then to integrate this library with
Singa's programming model, write the documentation and conduct the corresponding test.

 

Programming language: C++, CMake, OpenCL or [HIP|https://gpuopen.com/compute-product/hip-convert-cuda-to-portable-c-code/]

OS: Linux (Ubuntu or CentOS)

Tools: Github, JIRA,

Machine learning (ML) background: basics of ML and DL (deep learning)

 

        Summary: Deep learning over AMD GPUs  (was: Implement deep learning operations over
AMD GPUs)

> Deep learning over AMD GPUs
> ---------------------------
>
>                 Key: SINGA-423
>                 URL: https://issues.apache.org/jira/browse/SINGA-423
>             Project: Singa
>          Issue Type: New Feature
>            Reporter: wangwei
>            Priority: Major
>              Labels: gsoc2019
>
> GPU is a fueling factor for deep learning. Most deep learning libraries (including Singa)
are using Nvidia GPUs because [cuDNN|https://developer.nvidia.com/cudnn] from Nvida provides
almost all deep learning operations, which are also highly optimized.
>  
> This ticket is to provide support for AMD GPUs in Singa. AMD has provided a similar [library
|https://rocm.github.io/dl.html] as cuDNN. The task is then to integrate this library with
Singa's programming model, write the documentation and conduct the corresponding test.
>  
> Programming language: C++, CMake, OpenCL or [HIP|https://gpuopen.com/compute-product/hip-convert-cuda-to-portable-c-code/]
> OS: Linux (Ubuntu or CentOS)
> Tools: Github, JIRA,
> Machine learning (ML) background: basics of ML and DL (deep learning)
>  



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Mime
View raw message