ITK/Release 4/GPU Acceleration/Tcon-2010-11-22: Difference between revisions
From KitwarePublic
< ITK | Release 4 | GPU Acceleration
Jump to navigationJump to search
(Created page with "= Attendees = * Won Ki - Harvard University * Joe Stem - NVIDIA * Kimberly Powell - NVIDIA * Dennis Sessanna - NVIDIA * Luis Ibanez - Kitware Inc. = Topics = * Quick summary o...") |
Daviddoria (talk | contribs) m (moved ITK Release 4/GPU Acceleration/Tcon-2010-11-22 to ITK/Release 4/GPU Acceleration/Tcon-2010-11-22) |
||
| (28 intermediate revisions by one other user not shown) | |||
| Line 9: | Line 9: | ||
= Topics = | = Topics = | ||
* Quick summary of ITKv4 effort | == Overview == | ||
* Quick summary of ITKv4 effort (Luis Ibanez) | |||
* Summary of ITK-GPU approach (Won Ki) | |||
== Questions == | |||
* Level of abstraction ? | |||
** Joe suggests to look at OpenCV | |||
*** Expose the interactions with the GPU | |||
*** Most GPU programmers do things synchronously (so they unfortunately do too many data transfers, and don't get full benefit from the GPU). | |||
* Joe asked for typical Use Cases | |||
** We listed: | |||
*** Radiology : 100Mb per image (512x512x200) | |||
*** Microscopy : 10Gb | |||
*** Video : 10Mb images, 30~100 frames per second. | |||
* CUDA vs OpenCL ? | |||
** Joe answers | |||
** OpenCL is better for asynchronous multi-GPU programming. | |||
** Reasons for using CUDA over OpenCL | |||
*** Tedious API in OpenCL | |||
*** Large collection of CUDA existing libraries | |||
*** Performance optimization may be harder in OpenCL | |||
** Luis asked about vendor's commitment to OpenCL (for next 5 ~ 10 years) | |||
*** Joe answers | |||
**** NVIDIA supports the OpenCL standard (so, what is in OpenCL will be supported in NVidia cards) | |||
**** Some third party vendors are doing CUDA for NVidia platforms and OpenCL for other platforms (splitting the effort) | |||
**** Translation from CUDA to OpenCL is straight forward. (having a dual implementation may be lower than twice the effort) | |||
**** Other options CUDA x86 compiler coming up (commercial product) | |||
**** Translator from CUDA to OpenCL (need to find links to it) | |||
* Won: OpenCV & CUDA who did it ? | |||
** Joe : The OpenCV developers (Willow Garage)(code is in current SVN) | |||
* Won: How distribution happens (NVidia mpp libs) | |||
** Joe : binary (pre-build) downloads are available, and source code is also available. | |||
* Won: GPU code Testing ? | |||
** Joe : existing regression test framework (we - itkv4 devs - should look at it) | |||
*** Nvidia can suggest the sub-set of card families that should be tested. (e.g. major versions of drivers) | |||
**** There will also be families of OS (Windows 7 / Vista / XP ) to test (whild MacOSX / Linux should behave very similar). | |||
Latest revision as of 16:01, 9 December 2011
Attendees
- Won Ki - Harvard University
- Joe Stem - NVIDIA
- Kimberly Powell - NVIDIA
- Dennis Sessanna - NVIDIA
- Luis Ibanez - Kitware Inc.
Topics
Overview
- Quick summary of ITKv4 effort (Luis Ibanez)
- Summary of ITK-GPU approach (Won Ki)
Questions
- Level of abstraction ?
- Joe suggests to look at OpenCV
- Expose the interactions with the GPU
- Most GPU programmers do things synchronously (so they unfortunately do too many data transfers, and don't get full benefit from the GPU).
- Joe suggests to look at OpenCV
- Joe asked for typical Use Cases
- We listed:
- Radiology : 100Mb per image (512x512x200)
- Microscopy : 10Gb
- Video : 10Mb images, 30~100 frames per second.
- We listed:
- CUDA vs OpenCL ?
- Joe answers
- OpenCL is better for asynchronous multi-GPU programming.
- Reasons for using CUDA over OpenCL
- Tedious API in OpenCL
- Large collection of CUDA existing libraries
- Performance optimization may be harder in OpenCL
- Luis asked about vendor's commitment to OpenCL (for next 5 ~ 10 years)
- Joe answers
- NVIDIA supports the OpenCL standard (so, what is in OpenCL will be supported in NVidia cards)
- Some third party vendors are doing CUDA for NVidia platforms and OpenCL for other platforms (splitting the effort)
- Translation from CUDA to OpenCL is straight forward. (having a dual implementation may be lower than twice the effort)
- Other options CUDA x86 compiler coming up (commercial product)
- Translator from CUDA to OpenCL (need to find links to it)
- Joe answers
- Won: OpenCV & CUDA who did it ?
- Joe : The OpenCV developers (Willow Garage)(code is in current SVN)
- Won: How distribution happens (NVidia mpp libs)
- Joe : binary (pre-build) downloads are available, and source code is also available.
- Won: GPU code Testing ?
- Joe : existing regression test framework (we - itkv4 devs - should look at it)
- Nvidia can suggest the sub-set of card families that should be tested. (e.g. major versions of drivers)
- There will also be families of OS (Windows 7 / Vista / XP ) to test (whild MacOSX / Linux should behave very similar).
- Nvidia can suggest the sub-set of card families that should be tested. (e.g. major versions of drivers)
- Joe : existing regression test framework (we - itkv4 devs - should look at it)
