On the SPEC-CPU 2017 opportunities for dynamic vectorization possibilities on PIM architectures
Rodrigo Machniewicz Sokulski, Sairo R. dos Santos, Marco A. Z. Alves · 2022
Processing-In-Memory (PIM) devices usually implement vector instructions to efficiently utilize the large main memory bandwidth. One possible way to vectorize applications for such PIM systems is to convert CPU instructions into PIM vector instructions dynamically. In this work, we present a study on the feasibility of the dynamic conversion between these instructions for the Vector-In-Memory Architecture (VIMA). Our results show that 24 % of the loops from some SPEC-CPU 2017 applications are suitable for this conversion. Furthermore, we conclude that dynamic conversion mechanisms must to be able to efficiently deal with memory access conflicts, a problem present in 99 % of all possible conversions to VIMA.