On Saturday, 5 August 2017 at 01:15:19 UTC, Michael wrote:
On Saturday, 29 July 2017 at 06:54:47 UTC, Prasun Anand wrote:
Hi,

I wrote a Linear Mixed Model tool for Genome Wide Association Studies(GWAS) called [faster_lmm_d](https://github.com/prasunanand/faster_lmm_d). It is built on LDC and is faster than its Python alternative. Also, its the only GWAS tool with a GPU
backend.

I am interested in porting ` faster_lmm_d` to Ruby. Though, it is still a work in progress, I have written a blog about my findings.

Blog: http://www.prasunanand.com/gpu-computing/2017/07/25/gsoc17-calling-d-from-ruby-for-gpu-computing.html

I would love to hear your feedback.

Regards,
Prasun

[Previously posted on LDC thread: http://forum.dlang.org/thread/rzrawenyssbiidsgt...@forum.dlang.org]

I don't know much about your work but it sounds like an interesting application for D. How easy was it interfacing with cuda?

It was easy interfacing CUDA. I used `dstep` to create the bindings and for CUDA and CUBLAS headers. I got interesting results but would be working
on improving the performance.

Was it just cuda you targeted or would it also work with OpenCL?

Yes, OpenCL is supported using ArrayFire. I have targeted CUDA specifically
for better performance.

What made you choose D over going straight to C to work directly with cuda?

`faster_lmm_d`


Reply via email to