# Agile Autotuning of a Transprecision Tensor Accelerator Overlay for TVM Compiler Stack

arXiv: https://arxiv.org/abs/2004.10854 · HTML: https://mlsanity.com/paper/2004.10854/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

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

- [The Anatomy of a Triton Attention Kernel](https://mlsanity.com/paper/2511.11581/) (2025)
- [Understanding Cache Boundness of ML Operators on ARM Processors](https://mlsanity.com/paper/2102.00932/) (2021)
- [LEAPER: Fast and Accurate FPGA-based System Performance Prediction via Transfer Learning](https://mlsanity.com/paper/2208.10606/) (2022)
- [GPU Performance Portability needs Autotuning](https://mlsanity.com/paper/2505.03780/) (2025)

## Abstract (arXiv)

Specialized accelerators for tensor-operations, such as blocked-matrix operations and multi-dimensional convolutions, have been emerged as powerful architecture choices for high-performance Deep-Learning computing. The rapid development of frameworks, models, and precision options challenges the adaptability of such tensor-accelerators since the adaptation to new requirements incurs significant engineering costs. Programmable tensor accelerators offer a promising alternative by allowing reconfiguration of a virtual architecture that overlays on top of the physical FPGA configurable fabric. We propose an overlay (τ-VTA) and an optimization method guided by agile-inspired auto-tuning techniques. We achieve higher performance and faster convergence than state-of-art.