NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manjunath, Varun, Ramesh, Pranav, Srinivasan, Gopalakrishnan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908635928461312
author Manjunath, Varun
Ramesh, Pranav
Srinivasan, Gopalakrishnan
author_facet Manjunath, Varun
Ramesh, Pranav
Srinivasan, Gopalakrishnan
contents NeuroFlex is a column-level accelerator that co-executes artificial and spiking neural networks to minimize energy-delay product on sparse edge workloads with competitive accuracy. The design extends integer-exact QCFS ANN-SNN conversion from layers to independent columns. It unifies INT8 storage with on-the-fly spike generation using an offline cost model to assign columns to ANN or SNN cores and pack work across processing elements with deterministic runtime. Our cost-guided scheduling algorithm improves throughput by 16-19% over random mapping and lowers EDP by 57-67% versus a strong ANN-only baseline across VGG-16, ResNet-34, GoogLeNet, and BERT models. NeuroFlex also delivers up to 2.5x speedup over LoAS and 2.51x energy reduction over SparTen. These results indicate that fine-grained and integer-exact hybridization outperforms single-mode designs on energy and latency without sacrificing accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05215
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling
Manjunath, Varun
Ramesh, Pranav
Srinivasan, Gopalakrishnan
Neural and Evolutionary Computing
Hardware Architecture
NeuroFlex is a column-level accelerator that co-executes artificial and spiking neural networks to minimize energy-delay product on sparse edge workloads with competitive accuracy. The design extends integer-exact QCFS ANN-SNN conversion from layers to independent columns. It unifies INT8 storage with on-the-fly spike generation using an offline cost model to assign columns to ANN or SNN cores and pack work across processing elements with deterministic runtime. Our cost-guided scheduling algorithm improves throughput by 16-19% over random mapping and lowers EDP by 57-67% versus a strong ANN-only baseline across VGG-16, ResNet-34, GoogLeNet, and BERT models. NeuroFlex also delivers up to 2.5x speedup over LoAS and 2.51x energy reduction over SparTen. These results indicate that fine-grained and integer-exact hybridization outperforms single-mode designs on energy and latency without sacrificing accuracy.
title NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling
topic Neural and Evolutionary Computing
Hardware Architecture
url https://arxiv.org/abs/2511.05215