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, [email protected] 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 >> <[email protected]> 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
