cuda integer of 16 bits

is there any 16 bits long variable in CUDA? I need an unsigned integer of 16 bits. I've tried:

uint16
uint16_t

But no one is recognized by nvcc.

Solution

May be you should try ordinary c unsigned short?

ModuleNotFoundError: No module named 'nvcc_plugin'
Comparing performance among custom cuda kernel, cublas and cutensor
How can I check the progress of matrix multiplication?
cudafe++ died with status 0xc0000409 when switching to c++20 for nvcc
How to use 128bit float and complex numbers in OpenCL/CUDA?
Docker container with CUDA does not see my GPU | WSL2 / Ubuntu / Win10 | nvcc & nvidia-smi work
Cupy copy numpy array to existing device array
Why use MPS, Time Slicing or MIG if Nvidia's defaults have better performance?
Linker error: /usr/bin/ld: cannot find -lcudart_static while trying to compile CUDA code with clang
Paralelizing FFT (using CUDA)
Nvidia NVML Driver/library version mismatch
Does it matter if the version of cuda on docker is different from the version of cuda on the PC?
CUDA compile problems on Windows, Cmake error: No CUDA toolset found
CUDA compatibility with Visual Studio 2022 version 17.10
What is the relationship between GPU thread occupancy and sychronization stalls?
PyTorch problem with a specific version of CUDA
CUDA incompatible with my gcc version
How can I debug code 700 "illegal memory access" aka `CUDA_EXCEPTION_14, Warp Illegal Address`?
Replacement for deprecated cuDNN functions - official NVIDIA migration path?
Weird behavior from CUDA (Libtorch) and OpenGL interop
What is the canonical way to check for errors using the CUDA runtime API?
Convergence barrier for branchless CUDA conditional select
CUDA: Using grid-strided loop with reduction in shared memory
Conda CUDA12 incompatibility
Initialize constant global array CUDA C
nvrtc is not limiting register usage
Cannot get CUDA device count, GPU metrics will not be available , Nvidia triton server issue in docker
Running more than one CUDA applications on one GPU
Is it possible to read from usb webcam to gpu memory directly
Multiple CUDA versions on machine nvcc -V confusion