[jira] [Commented] (LUCENE-7745) Explore GPU acceleration

Previous Topic Next Topic
classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view

[jira] [Commented] (LUCENE-7745) Explore GPU acceleration

JIRA jira@apache.org

    [ https://issues.apache.org/jira/browse/LUCENE-7745?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15932604#comment-15932604 ]

Ishan Chattopadhyaya commented on LUCENE-7745:

[~dsmiley], that is a very important question. Afaik, there is no Apache compatible GPGPU framework. Both OpenCL and CUDA are likely incompatible with Apache (I am not fully sure). I see that jCUDA is MIT license, which is a wrapper around the native libraries.

If there are benefits to using GPGPU processing, my thought is that we can ensure all necessary plumbing in our codebase in order to offload processing to some plugin, whereby the user can plugin the exact GPU kernels from outside the Lucene distribution (if those kernels also violate any licensing restrictions we have). If there are clear benefits in speeding things up using a GPU, it would not be, *for the end-user*, the end of the world if the code comes outside Apache distribution.

bq.  If (a) is a "no", we need to be honest up front with the contributor.
That is a good point, and we can document this clearly.

> Explore GPU acceleration
> ------------------------
>                 Key: LUCENE-7745
>                 URL: https://issues.apache.org/jira/browse/LUCENE-7745
>             Project: Lucene - Core
>          Issue Type: Improvement
>            Reporter: Ishan Chattopadhyaya
>              Labels: gsoc2017, mentor
> There are parts of Lucene that can potentially be speeded up if computations were to be offloaded from CPU to the GPU(s). With commodity GPUs having as high as 12GB of high bandwidth RAM, we might be able to leverage GPUs to speed parts of Lucene (indexing, search).
> First that comes to mind is spatial filtering, which is traditionally known to be a good candidate for GPU based speedup (esp. when complex polygons are involved). In the past, Mike McCandless has mentioned that "both initial indexing and merging are CPU/IO intensive, but they are very amenable to soaking up the hardware's concurrency."
> I'm opening this issue as an exploratory task, suitable for a GSoC project. I volunteer to mentor any GSoC student willing to work on this this summer.

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]