GAMMA: Automating the HW Mapping of DNN Models on Accelerators via Genetic Algorithm

DNN layers are multi-dimensional loops that can be ordered, tiled, and scheduled in myriad ways across space and time on DNN accelerators. Each of these choices is called a mapping. It has been shown that the mapping plays an extremely crucial role in overall performance and efficiency, as it direct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design S. 1 - 9
Hauptverfasser: Kao, Sheng-Chun, Krishna, Tushar
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: Association on Computer Machinery 02.11.2020
Schlagworte:
Computational modeling
Computer architecture
DNN accelerators
DNN models
domain-specific genetic algorithm
GAMMA
Genetic Algorithm
genetic algorithms
HW mapping
ML accelerator
multidimensional loops
neural nets
Optimization methods
optimized mapping
Parallel processing
per-layer mappings
Reconfigurable device
search problems
Space exploration
Two dimensional displays
ISSN:1558-2434
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:DNN layers are multi-dimensional loops that can be ordered, tiled, and scheduled in myriad ways across space and time on DNN accelerators. Each of these choices is called a mapping. It has been shown that the mapping plays an extremely crucial role in overall performance and efficiency, as it directly determines the amount of reuse that the accelerator can leverage from the DNN. Moreover, instead of using a fixed mapping for every DNN layer, research has revealed the benefit of optimizing per-layer mappings. However, determining the right mapping, given an accelerator and layer is still an open question. The immense space of mappings (or map-space) makes brute-forced exhaustive search methods unapproachable. In this paper, we propose a domain-specific genetic algorithm-based method, GAMMA, which is specially designed for this HW-mapping problem. In contrast to prior works that either target simple rigid accelerators with a limited map-space or choose from a restricted set of mappings, we construct an extremely flexible map-space and show that GAMMA can explore the space and determine an optimized mapping with high sample efficiency. We quantitatively compare GAMMA with many popular optimization methods and observe GAMMA consistently finds better solutions.
ISSN:1558-2434
DOI:10.1145/3400302.3415639