Cliff Burdick
Cliff Burdick
``` cuda::std::complex a{1,0}; std::cout
**Describe the bug** After using `add_subdirectory` on CUTLASS in a CMake project, I'd expect CUTLASS's transitive target(s) to be exported for use in other projects. I have tried the following...
Unit tests take a very long time to compile on some systems. Parallelism helps, but not as much as it could given that many files have dozens of tests. This...
A lot of existing code already has column-major layout. Many existing libraries take column-major layout. We should give the option to declare a tensor with that layout to allow further...
Tensor with a static descriptor have out of bounds accesses when doing copies,
Currently when a view is created from a tensor, or when temporary tensors are created, they aren't necessarily using the same types of storage and descriptors as the original tensors....
The IIR filter appear to not work on signals that are not multiples of 8192. Fix this and add tests
**Is your feature request related to a problem? Please describe.** MatX currently takes raw non-owned pointers, smart unowned pointers, and self-allocates owned pointers otherwise. While this allows for many different...
Right now it looks like benchmark names must be the full name of the benchmark, but it would be useful to provide a regex syntax as gbench allows.
When using nvbench::main in a target, nvbench adds an include path for nvbench using `-I` instead of `-isystem`. This causes tools like clang-tidy to pick up nvbench as outside of...