fpsmt_gpu
fpsmt_gpu copied to clipboard
Solving floating point SMT constraints on a GPU
Hi, I am not familar with `nvcc` commands, but after docker pulling is complete, I am getting the following error from MakeFile.  I do have nvcc...
Removes aes random block generation in favor of [curand](https://docs.nvidia.com/cuda/curand/device-api-overview.html)
On some SMT files, the fuzzer reports success with an all zero input vector. This may be correct (haven't checked), but it should be astronomically unlikely that we ever see...