Does the library provide the SpMM operation (sparse matrix times skinny dense matrix)?

PASSIONLab / CombBLAS

The Combinatorial BLAS (CombBLAS) is an extensible distributed-memory parallel graph library offering a small but powerful set of linear algebra primitives specifically targeting graph analytics.

Other

64 stars 22 forks source link

Does the library provide the SpMM operation (sparse matrix times skinny dense matrix)? #17

Open prenc opened 2 years ago

prenc commented 2 years ago

In the paper describing the state of the library in version 2.0, you say that you've introduced the SpMM operation. However, I can not find the mentioned function in the code. Do you expect a user to craft it on their own using SpMV? If so, could you please provide some hints on how to do it quickly and efficiently, or am I overlooking something?

aydinbuluc commented 1 year ago

One way to do it quickly is to use SpMV with the vector elements being std::array of length k