libcudacxx
libcudacxx copied to clipboard
NVIDIA
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
``` cuda::std::complex a{1,0}; std::cout
In testing libcu++ for deployment in QUDA, I found that libcu++ atomic fails to compile if address sanitizer is enabled. ```bash $ nvcc bug.cu -o bug -arch=sm_70 -Xcompiler -fsanitize=address -Ilibcudacxx/include...
https://nvidia.github.io/libcudacxx/extended_api/asynchronous_operations/memcpy_async.html https://godbolt.org/z/P3n9xGdxe
Right now, when we build libcu++ as standalone C++ Standard Library (e.g. `std::`) for NVC++, I believe we don't hijack the inline visibility macro to make everything `__host__ __device__`; More...
closes https://github.com/NVIDIA/libcudacxx/issues/72
Apparently it doesn't. I have no idea what the scope of this involves. ``` “/home/sjs/work/pgi/dev4/rte/cuda/libcudacxx/libcxxabi/src/cxa_personality.cpp”, line 533: catastrophic error: #error directive: Unsupported architecture. #error Unsupported architecture. ^ [11:16 PM] static...