systemml-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Niketan Pansare" <npan...@us.ibm.com>
Subject Re: gpu dev environment on windows.
Date Wed, 31 Jan 2018 06:41:53 GMT
Hi Janardhan,

Are you planning to develop a custom kernel? 

If yes, you can use standard text editor to modify the SystemML.cu file. Please use the Makefile
in the same directory for compiling custom kernel. 

If not, you only need to worry about installing cuda 8 n cudnn 5. Here is a link for installing
cudnn: http://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html#installwindows

Thanks,

Niketan.

> On Jan 30, 2018, at 8:14 PM, dusenberrymw@gmail.com wrote:
> 
> Hi Janardhan,
> 
> I don’t use a Windows machine, so I can’t help with this one.  Niketan, would you
have information on this?
> 
> --
> 
> Mike Dusenberry
> GitHub: github.com/dusenberrymw
> LinkedIn: linkedin.com/in/mikedusenberry
> 
> Sent from my iPhone.
> 
> 
>> On Jan 30, 2018, at 7:43 AM, Janardhan Pulivarthi <janardhan.pulivarthi@gmail.com>
wrote:
>> 
>> Hi,
>> 
>> Anybody would volunteer to help me (would like to spare a 15 mins) setup
>> gpu dev environment on my windows.
>> 
>> 1. IDE: intellij, visual studio 2017
>> 2. OS: windows 10
>> 3. cuda: 8.0
>> 4. cudnn: I downloaded the package, but doesn't know how to integrate with
>> cuda.
>> 
>> questions:
>> 1. where to edit the c++ code of gpu kernel
>> 2. how to compile the file with nvvm
>> 3. and so on.
>> 
>> I will be so greatful for the help. please give a hangout request, If you
>> would like to help me.
>> 
>> Thanks,
>> Janardhan


Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message