[SparseBlas]Initial design of Sparse Coo data

[abhilash1910]

Description

Motivation

Currently from one of the priority app CUDA - SYCL migration perspective (CUDA-SYCL Task Force) (bitsandbytes) , there is a requirement to support COO format. Since currently the scope is through CSR, the code migration is routed through CSR pathway. However for an efficient migration of CUDA applications invoking COO, I propose a design for COO format. I have taken reference from the existing CSR implementation as most of the function args are similar. The current application requires cusparseCreateCoo api, and I had taken reference from this api invokation:

cusparseCreateCoo(cusparseSpMatDescr_t* spMatDescr, int64_t rows, int64_t cols, int64_t nnz, void* cooRowInd, void* cooColInd, void* cooValues, cusparseIndexType_t cooIdxType, cusparseIndexBase_t idxBase, cudaDataType valueType)

It would entail development of some COO auxiliary methods , getters ,aos and const variants in general. Since currently COO is not supported on iGPU yet , it would be nice to have this feature for future application migrations.
Tagging @Rbiessy from discussion.

[Rbiessy]

Hello @abhilash1910, we have updated the specification for the sparse domain recently: uxlfoundation/oneAPI-spec#522. Among other changes this adds support for the COO format.
I am already working on updating the MKL backends to match the new API. I expect the PR will be in review sometime next week so I would rather not change the existing implementation. FYI I will start working on adding support for cuSPARSE after that.

[Rbiessy]

I think this PR can be closed in favor of #500. Let me know @abhilash1910 whether this would work for you.

[abhilash1910]

Thanks @Rbiessy , I will review shortly , in the meantime closing this.