# Bifrost: End-to-End Evaluation and Optimization of Reconfigurable DNN Accelerators

arXiv: https://arxiv.org/abs/2204.12418 · HTML: https://mlsanity.com/paper/2204.12418/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 26 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Learning to Optimize Tensor Programs](https://mlsanity.com/paper/1805.08166/) (2018)
- [Measuring the Algorithmic Efficiency of Neural Networks](https://mlsanity.com/paper/2005.04305/) (2020)
- [Relay: A New IR for Machine Learning Frameworks](https://mlsanity.com/paper/1810.00952/) (2018)
- [SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference](https://mlsanity.com/paper/2110.00478/) (2021)
- [Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1809.07196/) (2018)
- [A Hardware-Software Blueprint for Flexible Deep Learning Specialization](https://mlsanity.com/paper/1807.04188/) (2018)
- [Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture](https://mlsanity.com/paper/1903.07676/) (2019)

## Built on by (most cited first, 1 of 1)

- [DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack](https://mlsanity.com/paper/2311.08909/) (2023)

## Abstract (arXiv)

Reconfigurable accelerators for deep neural networks (DNNs) promise to improve performance such as inference latency. STONNE is the first cycle-accurate simulator for reconfigurable DNN inference accelerators which allows for the exploration of accelerator designs and configuration space. However, preparing models for evaluation and exploring configuration space in STONNE is a manual developer-timeconsuming process, which is a barrier for research. This paper introduces Bifrost, an end-to-end framework for the evaluation and optimization of reconfigurable DNN inference accelerators. Bifrost operates as a frontend for STONNE and leverages the TVM deep learning compiler stack to parse models and automate offloading of accelerated computations. We discuss Bifrost's advantages over STONNE and other tools, and evaluate the MAERI and SIGMA architectures using Bifrost. Additionally, Bifrost introduces a module leveraging AutoTVM to efficiently explore accelerator designs and dataflow mapping space to optimize performance. This is demonstrated by tuning the MAERI architecture and generating efficient dataflow mappings for AlexNet, obtaining an average speedup of 50× for the convolutional layers and 11× for the fully connected layers. Our code is available at www.github.com/gicLAB/bifrost.