GitLab

Implemented a kernel that does a distributed reshuffle on the virtual block level when possible.

Deprecated C interface for cyclopstf.hpp. Added support for element-wise custom operations. Got rid of buffer and buffer_len parameters that were never used.  Added a test for weight
which uses a custom divide operaiton.

folded dimensions were set to edge length 1. Fixed by changing symmmetry of
folded dimensions symmetry to NS in the lower level kernel.

 Added compare_tensors function to print two tensors side-by-side and changed print_tensor to only print non-zero elements.

Wrote code that explicitly zeros out the padding. Made CTF_World be object reference rather than pointer everywhere.
Having issues with FFT tests due to diagonal rescaling in SY and possibly other problems.

2. Switched ctf.hpp to be templated and instantiated complex and double
3. Made diagonal rescaling work for SY and FFT test passes

TODO: Make diagonal rescaling require less dumb redistributions

Changed sizes from int64_t to int.  SY FFT test gets the wrong answer in parallel however, which is worrying

Added a new interface which is not fully complete nor tested