English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The rise of data-intensive applications exposed the limitations ofconventional processor-centric von-Neumann architectures that struggle to meetthe off-chip memory bandwidth demand. Therefore, recent innovations in computerarchitecture advocate compute-in-memory (CIM) and compute-near-memory (CNM),non-von- Neumann paradigms achieving orders-of-magnitude improvements inperformance and energy consumption. Despite significant technologicalbreakthroughs in the last few years, the programmability of these systems isstill a serious challenge. Their programming models are too low-level andspecific to particular system implementations. Since such future architecturesare predicted to be highly heterogenous, developing novel compiler abstractionsand frameworks become necessary. To this end, we present CINM (Cinnamon), afirst end-to-end compilation flow that leverages the hierarchal abstractions togeneralize over different CIM and CNM devices and enable device-agnostic anddevice-aware optimizations. Cinnamon progressively lowers input programs andperforms optimizations at each level in the lowering pipeline. To show itsefficacy, we evaluate CINM on a set of benchmarks for the well-known UPMEM CNMsystem and the memristors-based CIM accelerators. We show that Cinnamon,supporting multiple hardware targets, generates high-performance codecomparable to or better than state-of-the-art implementations.

CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms