A bug of 4_CUDA_Libraries/cudaNvSciNvMedia/cuda_consumer.cu
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 9.6k
- Forks
- 2.4k
- Avg merge
- 53m
- Merged PRs (30d)
- 1
Description
Get the wrong result when referring to the sample for setting the cudaExtent.width.
Because of the change in NvSciBuf's padding size, on Drive OS 6.0.5.0 Linux.
the cudaExtent.width should be set to the value of NvSciBufImageAttrKey_PlanePitch/(NvSciBufImageAttrKey_PlaneBitsPerPixel/8) ;
// https://docs.nvidia.com/cuda/cuda-runtime-api/structcudaExtent.html#structcudaExtent
// Width in elements when referring to array memory, in bytes when referring to linear memory
// NvSciBufImageAttrKey_PlanePitch: Outputs the pitch (aka width in bytes) for every plane.
// You can find the information on NvOnline Bug 3880762
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in 4_CUDA_Libraries/cudaNvSciNvMedia/cuda_consumer.cu, focusing on how cudaExtent.width is set for NvSciBuf images. Compare it with the reported PlanePitch/(PlaneBitsPerPixel/8) calculation and validate the sample on Drive OS 6.0.5.0 Linux; done when it no longer produces the reported wrong result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- hpc
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 48/100