# Optimizing Tensor Train Decomposition in DNNs for RISC-V Architectures Using Design Space Exploration and Compiler Optimizations

arXiv: https://arxiv.org/abs/2602.01996 · HTML: https://mlsanity.com/paper/2602.01996/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 53 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition](https://mlsanity.com/paper/1412.6553/) (2014)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network](https://mlsanity.com/paper/2008.05441/) (2020)
- [Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization](https://mlsanity.com/paper/1803.09327/) (2018)
- [CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression](https://mlsanity.com/paper/1701.07148/) (2017)
- [TinyIREE: An ML Execution Environment for Embedded Systems from Compilation to Deployment](https://mlsanity.com/paper/2205.14479/) (2022)
- [Model Preserving Compression for Neural Networks](https://mlsanity.com/paper/2108.00065/) (2021)
- [Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition](https://mlsanity.com/paper/2309.12412/) (2023)
- [Rank Selection of CP-decomposed Convolutional Layers with Variational Bayesian Matrix Factorization](https://mlsanity.com/paper/1801.05243/) (2018)
- [Non-Negative Matrix Factorization-Convolutional Neural Network (NMF-CNN) For Sound Event Detection](https://mlsanity.com/paper/2001.07874/) (2020)
- [Canonical Polyadic Decomposition and Deep Learning for Machine Fault Detection](https://mlsanity.com/paper/2107.09519/) (2021)
- [Rate Analysis and Deep Neural Network Detectors for SEFDM FTN Systems](https://mlsanity.com/paper/2103.02306/) (2021)

## Abstract (arXiv)

Deep neural networks (DNNs) have become indispensable in many real-life applications like natural language processing, and autonomous systems. However, deploying DNNs on resource-constrained devices, e.g., in RISC-V platforms, remains challenging due to the high computational and memory demands of fully connected (FC) layers, which dominate resource consumption. Low-rank factorization (LRF) offers an effective approach to compressing FC layers, but the vast design space of LRF solutions involves complex trade-offs among FLOPs, memory size, inference time, and accuracy, making the LRF process complex and time-consuming. This paper introduces an end-to-end LRF design space exploration methodology and a specialized design tool for optimizing FC layers on RISC-V processors. Using Tensor Train Decomposition (TTD) offered by TensorFlow T3F library, the proposed work prunes the LRF design space by excluding first, inefficient decomposition shapes and second, solutions with poor inference performance on RISC-V architectures. Compiler optimizations are then applied to enhance custom T3F layer performance, minimizing inference time and boosting computational efficiency. On average, our TT-decomposed layers run 3x faster than IREE and 8x faster than Pluto on the same compressed model. This work provides an efficient solution for deploying DNNs on edge and embedded devices powered by RISC-V architectures.