# DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators

arXiv: https://arxiv.org/abs/2509.10702 · HTML: https://mlsanity.com/paper/2509.10702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration](https://mlsanity.com/paper/1911.09925/) (2019)
- [Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators](https://mlsanity.com/paper/1809.04070/) (2018)
- [Data-Driven Offline Optimization For Architecting Hardware Accelerators](https://mlsanity.com/paper/2110.11346/) (2021)
- [Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search](https://mlsanity.com/paper/2103.01489/) (2021)
- [NAAS: Neural Accelerator Architecture Search](https://mlsanity.com/paper/2105.13258/) (2021)
- [CoSA: Scheduling by Constrained Optimization for Spatial Accelerators](https://mlsanity.com/paper/2105.01898/) (2021)
- [A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators](https://mlsanity.com/paper/2105.12842/) (2021)
- [Apollo: Transferable Architecture Exploration](https://mlsanity.com/paper/2102.01723/) (2021)
- [Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling](https://mlsanity.com/paper/2205.05826/) (2022)
- [HASCO: Towards Agile HArdware and Software CO-design for Tensor Computation](https://mlsanity.com/paper/2105.01585/) (2021)
- [TENET: A Framework for Modeling Tensor Dataflow Based on Relation-centric Notation](https://mlsanity.com/paper/2105.01892/) (2021)
- [DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators](https://mlsanity.com/paper/2201.11220/) (2022)
- [Demystifying Map Space Exploration for NPUs](https://mlsanity.com/paper/2210.03731/) (2022)

## Built on by (most cited first, 4 of 4)

- [Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions](https://mlsanity.com/paper/2606.02859/) (2026)
- [Mozart: A Chiplet Ecosystem-Accelerator Codesign Framework for Composable Bespoke Application Specific Integrated Circuits](https://mlsanity.com/paper/2510.08873/) (2025)
- [PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI](https://mlsanity.com/paper/2511.03934/) (2025)
- [AgentDSE: Reasoning-Augmented Architectural Design Space Exploration](https://mlsanity.com/paper/2606.21836/) (2026)

## Abstract (arXiv)

In the hardware design space exploration process, it is critical to optimize both hardware parameters and algorithm-to-hardware mappings. Previous work has largely approached this simultaneous optimization problem by separately exploring the hardware design space and the mapspace - both individually large and highly nonconvex spaces - independently. The resulting combinatorial explosion has created significant difficulties for optimizers. In this paper, we introduce DOSA, which consists of differentiable performance models and a gradient descent-based optimization technique to simultaneously explore both spaces and identify high-performing design points. Experimental results demonstrate that DOSA outperforms random search and Bayesian optimization by 2.80x and 12.59x, respectively, in improving DNN model energy-delay product, given a similar number of samples. We also demonstrate the modularity and flexibility of DOSA by augmenting our analytical model with a learned model, allowing us to optimize buffer sizes and mappings of a real DNN accelerator and attain a 1.82x improvement in energy-delay product.