This header, with C-style comments, is included in various Fortran files.
The IBM XL compiler doesn't seem to like this (at least by default).

This commit is a modificatio of the commit 4792a5a8 by Victor Yu, who
discovered the problem first

* Removed redundant malloc, memset and memcpy
* Use pinned host memory
* Implemented blocking for GPU code path in step5
* Removed unused code

* cudaMallocHost
* cudaFreeHost
* cudaHostRegister
* cudaHostUnregister

* Switch to a simple non-WY algorithm
* Unify real and complex cases
* Update reduction kernel
* Use __shfl_xor_sync for warp reduce (CUDA 9+)
* Support 2^n block size, n = 1,2,...,10
* Use templates when possible
* Clean up unused CUDA functions
* Increase default stripe width when using GPU

Skew

See merge request !26