Add bfloat16 to sparse_to_dense and dense_to_sparse routines

[jsandham]

Summary of proposed changes:

• Adds bfloat16 uniform precision to rocsparse_sparse_to_dense and rocsparse_dense_to_sparse routines

[codecov]

Codecov Report

Attention: Patch coverage is 68.62745% with 16 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
library/include/rocsparse_bfloat16.h	57.89%	8 Missing ⚠️
library/src/conversion/rocsparse_convert_array.cpp	0.00%	4 Missing ⚠️
library/src/auxiliary/rocsparse_auxiliary.cpp	0.00%	3 Missing ⚠️
library/src/common/rocsparse_datatype_utils.cpp	0.00%	1 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop     #488      +/-   ##
===========================================
- Coverage    79.52%   79.50%   -0.02%     
===========================================
  Files          342      343       +1     
  Lines        30539    30590      +51     
===========================================
+ Hits         24284    24319      +35     
- Misses        6255     6271      +16     

Files with missing lines	Coverage Δ
library/src/common/rocsparse_blas_rocblas.cpp	0.00% <ø> (ø)
library/src/common/rocsparse_common.cpp	67.24% <ø> (ø)
library/src/conversion/rocsparse_coo2dense.cpp	100.00% <ø> (ø)
library/src/conversion/rocsparse_dense2coo.cpp	100.00% <ø> (ø)
...brary/src/conversion/rocsparse_dense_to_sparse.cpp	95.59% <100.00%> (+0.43%)	⬆️
library/src/conversion/rocsparse_nnz.cpp	94.00% <ø> (ø)
...brary/src/conversion/rocsparse_sparse_to_dense.cpp	90.43% <100.00%> (+1.11%)	⬆️
library/src/extra/rocsparse_spgemm.cpp	80.69% <ø> (ø)
library/src/level2/rocsparse_spitsv.cpp	80.65% <ø> (ø)
...econd/itilu0/rocsparse_csritilu0_async_inplace.cpp	71.21% <ø> (ø)
... and 10 more

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.