René Widera

please update https://github.com/alpaka-group/alpaka/blob/8dbe7c42c647e4b67f22c10a39c36b160f654ecf/docs/source/dev/backends.rst?plain=1#L366 too ```c++ alpaka::allocMappedBuf(host, platform, extents) 1D, 2D, 3D supported! ```

@alpaka-group/alpaka-maintainers Since @SimeonEhrig asked for help I changed some points which IMO are important. My goal is not to have the perfect description because what @SimeonEhrig did is already a...

@alpaka-group/alpaka-maintainers ping

We added `-frelaxed-template-template-args` to alpaka with https://github.com/alpaka-group/alpaka/pull/2267 The provided godbolt example works fine when adding `-frelaxed-template-template-args`, therefor I will close this issue.

offline discussed in the developer meeting: https://docs.nvidia.com/cuda/cuda-runtime-api/structcudaFuncAttributes.html#structcudaFuncAttributes provides more properties than the maximum number of threads per block. We should at least design the API so that we can get...

I check our current code. All implementations of `TaskKernel*` using a tuple to store the arguments internally therefore using the "kernelBoundle" object which is unifying this approche will reduce the...

please rebase against dev to get the fix from #2294 in and remove draft from the PR if it is ready

@SimeonEhrig please update the description of this PR, `isTuple`,... is not valid anymore.

Please rebase against the dev branch to pull https://github.com/alpaka-group/alpaka/pull/2293 and update this example too.

@mehmetyusufoglu the CI says, looks like a missing include ``` /builds/hzdr/crp/alpaka/example/convolution2D/src/convolution2D.cpp:308:30: error: use of undeclared identifier 'KernelBundle' const auto &bundeledKernel = KernelBundle(convolutionKernel2D, alpaka::getPtrNative(bufInputAcc), alpaka::getPtrNative(outputDeviceMemory), matrixWidth, matrixHeight, alpaka::getPtrNative(bufFilterAcc), filterWidth, intputWidthAllocated, filterWidthAllocated);...