HIGHLIGHTS
SUMMARY
This includes architectures that fit within Wolfe`s P3 machine performance model (CPUs, GPUs, or other accelerators, possibly distributed; Wolfe, 2021) but also those that do not (e_g, Groq`s Tensor Streaming Processor; Abts et_al, 2020). The authors have previously explored the Mathematics of Arrays (MoA) formalism (Mullin, 1988) as a tool to optimize array computations for different hardware architectures, first through their Denotational Normal Form (DNF; Chetioui et_al, 2019) and then through their Operational Forms (OFs; Chetioui et_al, 2021). Research unequivocally shows that productivity increases through reuse (Basili et_al, 1996; Frakes and Succi . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.