Develop stream 20220711

[nolmoonen]

• Improve the configuration generation script, it now supports all benchmarks that have config autotuning.
• Added support for large indices in device_reduce_by_key, device_partition, and device_unique.
• Improved block sort test by covering a wider range of input sizes.
• Small improvement to performance of device radix sort.
• Added workaround for benchmarks that showed poor performance due to a compiler problem.
• Added clarification for disfunctional method in block sort.
• Performance improvement for device merge sort with custom types.
• Improved the large indices test for device adjacent difference by verifying output locations.
• Removed workaround for ROCM_SYMLINK_LIBS.
• Fixed bug in device merge sort that could result in incorrect results for structure types.