# SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategy

arXiv: https://arxiv.org/abs/2508.12906 · HTML: https://mlsanity.com/paper/2508.12906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 56 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Learning by Playing - Solving Sparse Reward Tasks from Scratch](https://mlsanity.com/paper/1802.10567/) (2018)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [SpArch: Efficient Architecture for Sparse Matrix Multiplication](https://mlsanity.com/paper/2002.08947/) (2020)
- [Dealing with Sparse Rewards in Reinforcement Learning](https://mlsanity.com/paper/1910.09281/) (2019)
- [ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning](https://mlsanity.com/paper/2009.02010/) (2020)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [Natural Evolutionary Strategies for Variational Quantum Computation](https://mlsanity.com/paper/2012.00101/) (2020)
- [Extending Sparse Tensor Accelerators to Support Multiple Compression Formats](https://mlsanity.com/paper/2103.10452/) (2021)

## Abstract (arXiv)

The growing demand for sparse tensor algebra (SpTA) in machine learning and big data has driven the development of various sparse tensor accelerators. However, most existing manually designed accelerators are limited to specific scenarios, and it's time-consuming and challenging to adjust a large number of design factors when scenarios change. Therefore, automating the design of SpTA accelerators is crucial. Nevertheless, previous works focus solely on either mapping (i.e., tiling communication and computation in space and time) or sparse strategy (i.e., bypassing zero elements for efficiency), leading to suboptimal designs due to the lack of comprehensive consideration of both. A unified framework that jointly optimizes both is urgently needed. However, integrating mapping and sparse strategies leads to a combinatorial explosion in the design space(e.g., as large as O(1041) for the workload P32 × 64 × Q64 × 48 = Z32 × 48). This vast search space renders most conventional optimization methods (e.g., particle swarm optimization, reinforcement learning and Monte Carlo tree search) inefficient. To address this challenge, we propose an evolution strategy-based sparse tensor accelerator optimization framework, called SparseMap. SparseMap constructing a more comprehensive design space with the consideration of both mapping and sparse strategy. We introduce a series of enhancements to genetic encoding and evolutionary operators, enabling SparseMap to efficiently explore the vast and diverse design space. We quantitatively compare SparseMap with prior works and classical optimization methods, demonstrating that SparseMap consistently finds superior solutions.