LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

OpenCL for Labview is now Open Source

That is a huge improvement!  The OpenCL FFT gives the option to run in single precision which Labview doesn't and is even better if you don't need the extra precision.  

0 Kudos
Message 11 of 20
(2,166 Views)

Lets just say that trying to force a bigger difference by changing to 2048 width didn't work out well. 🙂

(Graphics driver reset and VI hang)

/Y

G# - Award winning reference based OOP for LV, for free! - Qestit VIPM GitHub

Qestit Systems
Certified-LabVIEW-Developer
0 Kudos
Message 12 of 20
(2,165 Views)

Yeah, OpenCL on the GPU depends on how much memory the card can allocate.  If you scroll down on the device properties it will give you a heads up but it doesn't enforce it anywhere in the VIs.

0 Kudos
Message 13 of 20
(2,160 Views)

/double post, sorry

0 Kudos
Message 14 of 20
(2,159 Views)

New run gave 32ms and 44ms resp.

Very nice improvement, and i'm in no way accusing you, i just thought the massive parallellism would yield more. 🙂

This will be fun to play with. 😄

/Y

 

G# - Award winning reference based OOP for LV, for free! - Qestit VIPM GitHub

Qestit Systems
Certified-LabVIEW-Developer
0 Kudos
Message 15 of 20
(2,149 Views)

The more you can put into the OpenCL kernel to avoid data transfers between device and host and even global memory on the device, the better off you are.  Check the OpenCL cheatsheet if you are interesting in writing kernels, and there is a write-up in the manual.

Message 16 of 20
(2,142 Views)

Why did you use Write/Read buffer instead Map/Unmap? Map/Unmap will speed up transfer, because used DMA.

Can you correct you source for use Map/Unmap?

0 Kudos
Message 17 of 20
(1,633 Views)

Hey, thanks for using OpenCL for Labview. I don't have the time to support this any more, but it is free on Github if you'd like to modify it. I would be happy to add you to the Github project so your changes can be merged into the main project.

0 Kudos
Message 18 of 20
(1,599 Views)

OK. I changed to Map/Unmap. The speed up to 100x.

https://github.com/CyberRSR/OpenCLV

Message 19 of 20
(1,576 Views)

Thanks so much! Merged your changes into the main branch, glad to see some folks using this!

Message 20 of 20
(1,568 Views)