Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 8 years ago.
Improve this question
In our application we have FFT part. We would like to port that part onto GPU. We have Tesla K20m GPU. Which version of cuFFT is optimized for K20m card.
There is not a specific version of the cufft library that is optimized for a specific card. Just use the standard cufft library that ships with cuda 5.0 (or cuda 5.5 RC, if you like).
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 1 year ago.
Improve this question
I am looking for obtaining number of cycles of accessing memory type in CUDA. I want to analyze difference of memory types' and cache types' speed on GPU among the each specific architecture. Is there any source where I can find the number of clock cycles of accessing memory relating to its architecture or is there any method to measure them?
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 3 years ago.
Improve this question
I am trying to use onnx-trt but that requires TENSORRT_LIBRARY_MYELIN.
TENSORRT_LIBRARY_MYELIN requires trt 7. trt 7 requires cuda 10.2. cuda 10.2 can only be updated through the jetpack sdk manager. But I only see cuda 10.0 on there. How do I update to cuda 10.2?
TensorRT 7 hasn't been released for Jetson yet, stay tuned.
Closed. This question is off-topic. It is not currently accepting answers.
Want to improve this question? Update the question so it's on-topic for Stack Overflow.
Closed 10 years ago.
Improve this question
What do I have to do, to be able to do Cuda programming on a Macbook Air with Intel HD 4000 graphics?
Setup a virtual machine? Buy an external Nvidia card? Is it possible at all?
If you have a new(-ish) Macbook Air you could perhaps use an external (NVidia) graphics device like this:
external Thunderbolt PCIe case
Otherwise it will not be possible to run Cuda programms on non NVidia Hardware (since it is a proprietary framework)
You may also be able to run Cuda code through converting it to OpenCL first (for example with this framework: Swan Framwork )
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 8 years ago.
Improve this question
CUDA advertises itself as a parallel computing platform. However, I'm having trouble seeing how it's any different from a software framework (a collection of libraries used for some functionality). I am using CUDA in class and all I'm seeing is that it provides libraries in C for - functions that help in parallel computing on the GPU - which fits my definition of a framework. So tell me, how is a platform like CUDA different from a framework? Thank you.
CUDA the hardware platform, is the actual GPU and its scheduler ("CUDA architecture"). However CUDA is also a programming language, which is very close to C. To work with the software written in CUDA you also need an API for calling these functions, allocating memory etc. from your host language. So CUDA is a platform, a language and a set of APIs.
If the latter (a set of APIs) matches your definition of a software framework, then the answer is simply yes, as both options are true.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 9 years ago.
Improve this question
Can I use nVidia CUDA on QNX(x86_64 or other) and what driver do I need for this?
I found nothing about this by link, and in #46 answer sound like "I don't know"
http://www.qnx.com/news/web_seminars/faq_multicore.html
But, QNX thinks to Include Support for NVIDIA Tegra Processor Family:
http://www.qnx.com/news/pr_5306_1.html
And nVidia thinks to add support CUDA and OpenCL to the nVidia Tegra5(Logan) ARM+GK1xx in next year:
http://en.wikipedia.org/wiki/Tegra#Logan
http://www.ubergizmo.com/2013/07/nvidia-tegra-5-release-date-specs-news/
And then can we use CUDA on nVidia Tegra5(ARM+GK1xx) on QNX(ARM), and what about QNX(x86)?
At this time, there's no support for CUDA on QNX.
The supported operating systems for CUDA are listed on the cuda download page as well as in section 1.4 of the release notes
Regarding Tegra, at this time there are no Tegra devices that support CUDA. The list of CUDA-enabled GPUs is here. Whether using an x86/x86_64 CPU or an ARM CPU, one of these CUDA GPUs is required for CUDA support.
Update: There are now tegra devices that support CUDA, including the widely available Tegra TK1 and recently announced TX1.