Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Chiplets and the Codelet Model (2209.06083v1)

Published 13 Sep 2022 in cs.DC

Abstract: Recently, hardware technology has rapidly evolved pertaining to domain-specific applications/architectures. Soon, processors may be composed of a large collection of vendor-independent IP specialized for application-specific algorithms, resulting in extreme heterogeneity. However, integrating multiple vendors within the same die is difficult. Chiplet technology is a solution that integrates multiple vendor dies within the same chip by breaking each piece into an independent block, each with a common interconnect for fast data transfer. Most prior chiplet research focuses on interconnect technology, but program execution models (PXMs) that enable programmability and performance are missing from the discussion. In chiplet architectures, a cohesive co-designed PXM can further separate the roles of the different actors, while maintaining a common abstraction for program execution. This position paper describes the need for co-designed PXMs and proposes the Codelet PXM and associated architectural features as a candidate to fill this need in extremely heterogeneous chiplet-based architectures.

Summary

We haven't generated a summary for this paper yet.