Tachyum processor with Julia

[Palli]

@elrod [are you only working on dense?]
This (likely) “sparsity 133/8 = 16.625” got got me thinking, how would you design hardware (or software, maybe we can do better for Julia) for sparse matrices? What I had written here, since off-topic here(?) moved elsewhere:

A flexible sparse matrix data format and parallel algorithms for the assembly of sparse matrices in general finite element applications using atomic synchronisation primitives

Unlike the above, below is just my speculation (that I moved from other thread, since maybe a bit off-topic there): @elrod [are you only working on dense?] This (likely) “sparsity 133/8 = 16.625” got got me thinking, how would you design hardware (or software, maybe we can do better for Julia) for sparse matrices. I’m guessing matrices are split up into 4x4=16-sized blocks/submatrices (would 1x16 for one matrix and 16x1 be better for the other you are multiplying, or maybe 2x8 etc.?). If yo…