# Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration

arXiv: https://arxiv.org/abs/1911.09925 · HTML: https://mlsanity.com/paper/1911.09925/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2019.

## Built on by (most cited first, 30 of 63)

- [Full Stack Optimization of Transformer Inference: a Survey](https://mlsanity.com/paper/2302.14017/) (2023)
- [DiffRate : Differentiable Compression Rate for Efficient Vision Transformers](https://mlsanity.com/paper/2305.17997/) (2023)
- [LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale](https://mlsanity.com/paper/2408.05499/) (2024)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms](https://mlsanity.com/paper/2306.15552/) (2023)
- [Allo: A Programming Model for Composable Accelerator Design](https://mlsanity.com/paper/2404.04815/) (2024)
- [A Hardware Evaluation Framework for Large Language Model Inference](https://mlsanity.com/paper/2312.03134/) (2023)
- [HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design](https://mlsanity.com/paper/2412.05393/) (2024)
- [Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators](https://mlsanity.com/paper/2505.18574/) (2025)
- [CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs](https://mlsanity.com/paper/2201.01863/) (2022)
- [LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator](https://mlsanity.com/paper/2501.10658/) (2025)
- [FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables](https://mlsanity.com/paper/2503.06862/) (2025)
- [MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks](https://mlsanity.com/paper/2305.05843/) (2023)
- [LLM-Aided Compilation for Tensor Accelerators](https://mlsanity.com/paper/2408.03408/) (2024)
- [Machine Learning Sensors](https://mlsanity.com/paper/2206.03266/) (2022)
- [MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices](https://mlsanity.com/paper/2410.08855/) (2024)
- [Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions](https://mlsanity.com/paper/2606.02859/) (2026)
- [Iterative Filter Pruning for Concatenation-based CNN Architectures](https://mlsanity.com/paper/2405.03715/) (2024)
- [DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators](https://mlsanity.com/paper/2509.10702/) (2025)
- [GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching](https://mlsanity.com/paper/2105.10554/) (2021)
- [Integration of a systolic array based hardware accelerator into a DNN operator auto-tuning framework](https://mlsanity.com/paper/2212.03034/) (2022)
- [Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs](https://mlsanity.com/paper/2503.00461/) (2025)
- [QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration](https://mlsanity.com/paper/2206.15463/) (2022)
- [An Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators](https://mlsanity.com/paper/2308.12120/) (2023)
- [MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization](https://mlsanity.com/paper/2412.10261/) (2024)
- [TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator](https://mlsanity.com/paper/2503.05951/) (2025)
- [An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems](https://mlsanity.com/paper/2508.14582/) (2025)
- [HighTide: An Agent-Curated Open-Source VLSI Benchmark Suite](https://mlsanity.com/paper/2606.04126/) (2026)
- [Hardware/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs](https://mlsanity.com/paper/2201.09189/) (2022)
- [Tackling the Matrix Multiplication Micro-kernel Generation with Exo](https://mlsanity.com/paper/2310.17408/) (2023)

## Abstract (arXiv)

DNN accelerators are often developed and evaluated in isolation without considering the cross-stack, system-level effects in real-world environments. This makes it difficult to appreciate the impact of System-on-Chip (SoC) resource contention, OS overheads, and programming-stack inefficiencies on overall performance/energy-efficiency. To address this challenge, we present Gemmini, an open-source*, full-stack DNN accelerator generator. Gemmini generates a wide design-space of efficient ASIC accelerators from a flexible architectural template, together with flexible programming stacks and full SoCs with shared resources that capture system-level effects. Gemmini-generated accelerators have also been fabricated, delivering up to three orders-of-magnitude speedups over high-performance CPUs on various DNN benchmarks. * https://github.com/ucb-bar/gemmini