Cuda implementation of Normalize() function
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 119
- Forks
- 88
- PR merge metrics
- No merged PRs in 30d
Description
We have CPU implementation of **Normalize**() function in `src/image_function.h` and `src/image_function.cpp` files. We want to add Cuda implementation of the same function. Please put new code in `src/cuda/image_function_cuda.cuh` and `src/cuda/image_function_cuda.cu` files. Things which we need to do:
1. Copy 4 function declaration from `src/image_function.h` to `src/cuda/image_function_cuda.cuh`
2. Copy first 3 function implementation from `src/image_function.cpp` to `src/cuda/image_function_cuda.cu`
3. Add Cuda kernel called `normalizeCuda` into unnamed namespace at the top of `src/cuda/image_function_cuda.cu` file
4. Add forth function implementation by following **LookupTable()** code logic
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
Compare the Normalize declarations in src/image_function.h with the implementations in src/image_function.cpp, then read the LookupTable() logic in src/cuda/image_function_cuda.cu. Work in src/cuda/image_function_cuda.cuh and src/cuda/image_function_cuda.cu, adding the requested declarations, implementations, and normalizeCuda kernel. Done means all four Normalize functions have CUDA counterparts following the specified CPU and LookupTable patterns.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 35/100