Gemmini: Berkeley's Open-Source AI Accelerator Is Reshaping Custom Chip Design

GitHub July 2026
⭐ 1384
Source: GitHubArchive: July 2026
UC Berkeley's Gemmini is an open-source hardware generator that accelerates matrix multiplication and convolution using a flexible systolic array architecture. Built for the RISC-V ecosystem, it enables rapid prototyping of custom AI accelerators for edge inference, but requires fluency in the Chisel hardware construction language.

Gemmini, developed by the Berkeley Architecture Research group, is not just another academic project—it is a strategic enabler for the open-source hardware movement. At its core, Gemmini is a parameterized systolic array generator that can be configured for different data types (INT8, FP16, FP32), array dimensions, and memory hierarchies. It is designed to plug into a RISC-V SoC as a tightly coupled accelerator, handling the dense linear algebra operations that dominate modern AI workloads. The project has garnered over 1,384 stars on GitHub, reflecting strong interest from both academia and industry. Its significance lies in lowering the barrier to entry for custom AI chip design: startups and research groups can now generate a synthesizable accelerator without starting from scratch. However, the learning curve is steep—Gemmini is written in Chisel, a Scala-based hardware construction language, and requires understanding of both digital design and the RISC-V ecosystem. This article provides an in-depth analysis of Gemmini's architecture, its competitive positioning against proprietary accelerators like NVIDIA's NVDLA and Google's TPU, and the broader implications for the AI hardware market.

Technical Deep Dive

Gemmini's architecture is built around a systolic array—a grid of processing elements (PEs) that perform multiply-accumulate (MAC) operations in a pipelined, data-flow fashion. This design is ideal for matrix multiplication and convolution because it maximizes data reuse and minimizes memory bandwidth requirements. The generator allows users to specify the array dimensions (e.g., 16x16, 32x32, 64x64), the data type for each PE (INT8, FP16, FP32), and the depth of local scratchpads and global buffers.

Memory Hierarchy: Gemmini employs a multi-level memory system: a global DRAM interface, a shared scratchpad (typically SRAM), and local PE registers. The scratchpad is partitioned into banks to enable parallel access. The generator also supports tiling—breaking large matrices into blocks that fit in the scratchpad—which is critical for real-world performance.

Chisel and the RTL Generation: Gemmini is written in Chisel, which compiles to Verilog. This allows designers to parametrize the accelerator at a high level (e.g., `val gemmini = GemminiConfig(rows=32, cols=32, dataType=INT8)`) and generate optimized RTL. The repository includes a full test suite, a cycle-accurate simulator, and integration scripts for the Rocket Chip SoC generator.

Performance Benchmarks: The following table compares Gemmini's performance against other open-source accelerators on common edge inference tasks (data from published papers and GitHub documentation):

| Accelerator | Array Size | Data Type | Throughput (GOPS) @ 1GHz | Power (mW) | Area (mm² @ 28nm) |
|---|---|---|---|---|---|
| Gemmini (default) | 16x16 | INT8 | 512 | 250 | 1.2 |
| Gemmini (large) | 64x64 | INT8 | 8192 | 1800 | 8.5 |
| NVIDIA NVDLA (small) | — | INT8 | 1024 | 500 | 2.5 |
| Google Edge TPU (simulated) | 64x64 | INT8 | 4096 | 2000 | 12.0 |

Data Takeaway: Gemmini's small configuration achieves competitive throughput per area and power, but the large configuration scales linearly—a key advantage of the systolic array design. However, NVDLA's dedicated hardware for convolutions can outperform Gemmini on certain layer types (e.g., depthwise convolutions) due to specialized dataflows.

Key Open-Source Repositories:
- ucb-bar/gemmini (⭐1,384): The main repository, including Chisel source, testbenches, and integration with Rocket Chip.
- ucb-bar/chisel3 (⭐3,800+): The hardware construction language used to build Gemmini.
- ucb-bar/rocket-chip (⭐3,200+): The RISC-V SoC generator that Gemmini is designed to plug into.

Key Players & Case Studies

UC Berkeley ASPIRE Lab: Led by Professor Krste Asanović (also a RISC-V co-founder), the lab has a long track record of open-source hardware projects. Gemmini is the latest in a lineage that includes the Rocket Chip generator and the BOOM out-of-order core. The lab's strategy is to provide a complete, open-source AI accelerator that can be used for both research and commercial prototyping.

SiFive and Esperanto Technologies: These RISC-V chip startups have publicly referenced Gemmini as a reference design for their AI accelerators. SiFive's Intelligence series of processors includes optional AI acceleration blocks that share architectural concepts with Gemmini. Esperanto's ET-SoC-1, a 1,000-core RISC-V chip for AI inference, uses a similar systolic array approach, though their implementation is proprietary.

Comparison with Proprietary Accelerators:

| Feature | Gemmini | NVIDIA NVDLA | Google TPUv4i |
|---|---|---|---|
| License | Open-source (BSD) | Open-source (NVIDIA) | Proprietary |
| Programmability | Custom software stack (C++/Python) | NVIDIA's compiler toolchain | TensorFlow/PyTorch via XLA |
| Flexibility | Parametric (size, data type, memory) | Fixed dataflow (convolution-optimized) | Fixed systolic array |
| Ecosystem | RISC-V + Chisel | ARM/x86 + Verilog | Google Cloud |
| Maturity | Academic (pre-silicon) | Production (used in Xavier, Orin) | Production (cloud) |

Data Takeaway: While NVDLA and TPU offer production-ready performance and software ecosystems, Gemmini's open-source nature and parametric flexibility make it the go-to choice for researchers and startups that need to customize the accelerator for novel architectures (e.g., sparsity, mixed-precision, or non-traditional dataflows).

Industry Impact & Market Dynamics

Gemmini is part of a broader trend toward open-source AI hardware, which is challenging the dominance of proprietary vendors like NVIDIA, Intel, and Google. The global AI accelerator market is projected to grow from $10.2 billion in 2023 to $71.3 billion by 2030 (CAGR 32%), according to industry reports. Open-source accelerators like Gemmini are capturing a small but growing share of the edge inference segment, which is expected to reach $15 billion by 2027.

Adoption Drivers:
1. RISC-V Ecosystem Growth: The RISC-V ISA is gaining traction in IoT, automotive, and edge devices. Gemmini provides a natural AI acceleration path for RISC-V SoCs.
2. Startup Cost Reduction: A startup can use Gemmini to generate a custom accelerator without paying millions in licensing fees or hiring a large hardware team.
3. Academic Research: Universities use Gemmini to explore novel architectures (e.g., analog computing, in-memory computing) without building a full chip from scratch.

Market Data Table:

| Year | Open-Source AI Accelerator Market Share (est.) | Gemmini GitHub Stars | Number of RISC-V AI Chip Startups |
|---|---|---|---|
| 2021 | 2% | 450 | 12 |
| 2023 | 5% | 1,100 | 25 |
| 2025 (projected) | 10% | 2,500 | 40 |

Data Takeaway: The correlation between Gemmini's GitHub popularity and the growth of RISC-V AI startups suggests that the open-source accelerator is acting as a catalyst for the ecosystem. However, the 5% market share indicates that proprietary solutions still dominate, especially in high-performance cloud inference.

Risks, Limitations & Open Questions

Chisel Learning Curve: Gemmini's reliance on Chisel is a double-edged sword. While Chisel enables powerful parameterization, it is unfamiliar to most hardware engineers who are trained in Verilog or VHDL. This limits the pool of developers who can contribute or customize Gemmini.

Software Stack Immaturity: Unlike NVIDIA's CUDA or Google's TensorFlow, Gemmini's software stack is rudimentary. It includes a C++ library and a Python wrapper, but lacks a full compiler that can optimize arbitrary neural network graphs. Users must manually tile operations and manage data movement.

Silicon Provenness: Gemmini has been synthesized and tested on FPGAs, but as of mid-2025, no commercial chip has been taped out using Gemmini as the primary accelerator. The risk of bugs or performance bottlenecks in silicon remains.

Scalability to Large Models: Gemmini is designed for edge inference (models up to tens of millions of parameters). For large language models (LLMs) with billions of parameters, the memory hierarchy and bandwidth are insufficient without significant modifications.

Ethical Concerns: Open-source AI accelerators could lower the barrier for malicious actors to build custom hardware for surveillance or autonomous weapons. However, this is a general concern for all open-source hardware, not specific to Gemmini.

AINews Verdict & Predictions

Gemmini is a critical piece of infrastructure for the open-source AI hardware movement, but it is not yet a commercial product. Our editorial judgment is that Gemmini will follow a trajectory similar to Linux in the 1990s: initially dismissed as an academic toy, it will gradually gain adoption in niche markets (edge IoT, automotive, aerospace) where customization and cost are more important than peak performance.

Predictions:
1. By 2027, at least three startups will tape out chips using Gemmini-derived accelerators, targeting applications like smart cameras, drone navigation, and industrial robotics.
2. By 2028, the Gemmini project will merge with the RISC-V Vector Extension (RVV) to provide a unified programming model, reducing the software stack gap.
3. By 2030, open-source AI accelerators (including Gemmini and its derivatives) will capture 15-20% of the edge inference market, driven by the proliferation of RISC-V in IoT devices.

What to Watch: The next major milestone is a successful tape-out of a Gemmini-based chip in a commercial process (e.g., TSMC 28nm or 12nm). If that happens, expect a surge in venture capital interest and a wave of new startups. Until then, Gemmini remains a powerful research tool with immense potential—but it is not yet a threat to NVIDIA's dominance.

More from GitHub

UntitledSvelte-Cubed is not just another wrapper around Three.js; it is a fundamental rethinking of how 3D scenes are authored oUntitledSvelte, created by Rich Harris and now stewarded by the Vercel ecosystem, has grown from a niche experiment into a serioUntitledThe Model Context Protocol (MCP) is gaining traction as a standard for AI models to access external tools and data. HoweOpen source hub3359 indexed articles from GitHub

Archive

July 2026599 published articles

Further Reading

RISC-V's Foundational Toolchain: How riscv-gnu-toolchain Powers the Open Hardware RevolutionThe riscv-gnu-toolchain is not merely another GitHub repository; it is the bedrock upon which the entire RISC-V softwareAlibaba's OpenC906: How an Open-Source RISC-V Core Disrupts the Silicon Status QuoAlibaba's chip design arm, T-Head Semiconductor, has open-sourced a production-proven, 64-bit RISC-V CPU core, the OpenCChisel AsyncFIFO: The Unsung Hero of Clock Domain Crossing in Silicon DesignA new open-source asynchronous FIFO implementation written in Chisel has emerged, directly reusing the battle-tested AsyChipyard's Baremetal-IDE: A Low-Level RISC-V Development Game ChangerA new submodule within the Chipyard framework, baremetal-ide, promises to streamline low-level RISC-V development by pro

常见问题

GitHub 热点“Gemmini: Berkeley's Open-Source AI Accelerator Is Reshaping Custom Chip Design”主要讲了什么?

Gemmini, developed by the Berkeley Architecture Research group, is not just another academic project—it is a strategic enabler for the open-source hardware movement. At its core, G…

这个 GitHub 项目在“How to set up Gemmini for RISC-V AI inference on FPGA”上为什么会引发关注?

Gemmini's architecture is built around a systolic array—a grid of processing elements (PEs) that perform multiply-accumulate (MAC) operations in a pipelined, data-flow fashion. This design is ideal for matrix multiplicat…

从“Gemmini vs NVDLA: which open-source accelerator is better for edge AI”看,这个 GitHub 项目的热度表现如何?

当前相关 GitHub 项目总星标约为 1384,近一日增长约为 0,这说明它在开源社区具有较强讨论度和扩散能力。