Open source is a buzzword.
A few years ago, the open-source architecture RISC-V emerged, creating significant waves in the chip design field due to its open characteristics..
Earlier this year, the open-source large model DeepSeek made a grand debut, igniting further interest in AI.
Now, this wave has reached the FPGA .
01The World’s First Open Source FPGA Officially Released
Recently, the American semiconductor startup Zero ASIC announced the launch of the world’s first open standard eFPGA IP product, Platypus.
According to the company, Platypus is the first and currently the only commercial eFPGA IP product, featuring three major characteristics:100% open and standardized FPGA architecture; providing 100% open-source FPGA bitstream format and equipped with 100% open-source FPGA development tools.
Zero ASIC traces its origins back to 2008, when Adapteva was established, focusing on parallel processor development. In 2020, the original Adapteva founder Andreas Olofsson reassembled the team, renamed the company to Zero ASIC, and received funding support from the U.S. government to focus on the development of composable chip platforms.
Previously, Olofsson led DARPA‘s CHIPS project (General Heterogeneous Integration and IP Reuse Strategy), laying the foundation for subsequent technology routes.
It is reported that Zero ASIC is building the world’s first composable chip platform, enabling billions of unique silicon systems to be assembled from a ready-made chip catalog within hours.
So, what is an open-source FPGA? What significance does open-source FPGA hold?
Open-source FPGA refers to FPGA technology whose hardware design, toolchain, or related ecosystem is released in open-source form. Unlike traditional FPGA (closed-source commercial products dominated by companies like Xilinx, Intel, etc.), open-source FPGA code, architecture, or development tools are open to the public, allowing users to freely modify, customize, and share.
Typical forms of open-source FPGA include open-source toolchains, open-source hardware architectures, and fully open-source FPGA designs, etc.
Discussing the advantages of open-source FPGA:
First, in terms of cost: open-source FPGA can help developers avoid the high licensing fees and tool subscription costs associated with commercial companies.
In terms of customization: developers can modify FPGA architectures or toolchains to meet specific needs (such as custom instruction sets, optimizing power consumption), and the speed of development can also be significantly accelerated.
In terms of security: traditional FPGA relies on a single vendor’s toolchain and chips, while the open-source ecosystem supports multi-platform compatibility.
In terms of lifecycle, commercial FPGA may be phased out due to vendor discontinuation, while open-source projects can be maintained by the community, extending hardware lifespan.
Special announcement for the May Day fan event: Celebrate May Day with challenges and rewards!
👏🏻 Memory challenge: Successfully match characters to cards within a specified time to win a prize! Each person has 2 chances to challenge daily! 🎟 Game prizes ✅ MiJia Lite Eye Protection Desk Lamp *1 ✅ 2.8-inch LCD TFT LCD *5 ✅ Summer Cool Package *10 (including small fan, glass coffee cup, towel, cooling patch) Long press to scan the QR code in the image to participate in the challenge, and wish everyone a happy holiday in advance! Have fun~
02Open Source FPGA: A Long Journey
For the past 25 years, there have been multiple attempts to open-source FPGA.
Osaka University in Japan is an important participant in the open-source FPGA project.
In May 1997, the open-source FPGA research platform (VPR) was launched, helping to lower the barrier for high-quality, reproducible FPGA research.
Osaka University LNIS team developed an open-source, comprehensive FPGA design and implementation framework—OpenFPGA. It is open-sourced on GitHub, supporting highly customizable FPGA architectures, providing a one-stop solution from Verilog to bitstream, making it very suitable for chip designers and researchers. It is distributed under the MIT license, with some submodules outside the core codebase (such as VTR, Yosys and Yosys plugins) following their respective licensing terms.
OpenFPGA core is the VPR tool, which is responsible for FPGA placement and routing. VPR uses advanced algorithms to optimize the layout of logic blocks, routing resource allocation, and power control. By open-sourcing, developers can directly participate in improving VPR, driving continuous performance and efficiency improvements.
The core functionalities of the project include:
-
Verilog to Bitstream generation: allowing users to compile designs directly into configuration bitstreams for specific FPGA devices.
-
Custom FPGA architecture: supporting the creation and validation of personalized FPGA structures, pushing the boundaries of FPGA design innovation.
-
Self-testing and verification: integrated verification tools ensure design correctness, reducing error risks.
-
Agile prototyping: providing a rapid prototyping environment to accelerate research and development cycles.
It is worth noting that VPR is still just a research tool, and commercial FPGA still lacks a fully open RTL to place-and-route process.
To address the lack of fully open FPGA devices, DARPA funded the OpenFPGA and PRGA FPGA generator research projects in 2018.
Although these open-source generators have facilitated the tape-out of several academic chips, the final designs have neither been standardized nor commercialized.
There has also never been a commercially available open, standardized FPGA product on the market.
With the launch of the Platypus eFPGA series, Zero ASIC has taken an important step towards standardizing FPGA by publicly releasing the complete architectural description and bitstream format of its commercial Z1000 eFPGA IP under the open-source Apache license, aiming to make it an open standard.
Additionally, many organizations are extending their reach into other aspects of open-source FPGA development. For example: FINN (Fast INtegration of Neural Networks) is an open-source project developed by Xilinx that focuses on implementing efficient neural network inference on FPGA (Field Programmable Gate Arrays). FINN leverages the parallel processing capabilities of FPGA to significantly accelerate neural network inference, making it particularly suitable for edge computing and real-time application scenarios.
SymbiFlow is also an open-source Verilog to bitstream FPGA synthesis flow, currently targeting Xilinx 7 series, Lattice iCE40 and Lattice ECP5 FPGA. The goal of this project is to design highly scalable and multi-platform tools. The open-source project SymbiFlow has supported multiple FPGA open-source toolchains through community collaboration, breaking the monopoly of traditional EDA tools.
Microsemi started offering RISC-V soft cores in its FPGA in 2017, Lattice began offering them in 2020, and Intel (Altera) started in 2021, making Xilinx the last major supplier to do so, with plans to offer it in May 2024.
Point out to follow and star with non-network eefocus
Scan to reply with “FPGAA, RISC-V, MCU” and other keywords for industry groups and to receive reports
03Open Source MCU: Paving a Path
In addition to FPGA, the open-source trend is penetrating more types of chip fields.
In October 2019, at the Wuzhen Internet Conference, Alibaba’s chip company Tsinghua Unigroup announced the open-source low-power microcontroller chip ( MCU) design platform. Since then, Tsinghua Unigroup has become the first company in China to achieve open-source chip platforms.
Similar to the advantages of open-source FPGA, open-source MCU offers greater flexibility and openness, lowering the barrier to entry into embedded development, allowing small teams or individual developers to access and utilize advanced MCU technology, while also helping to better adapt to different market demands and application scenarios.
MCUs can be divided into 4-bit, 8-bit, 16-bit, and 32-bit. Different bit-width MCUs are suitable for different fields, with higher bit-width MCUs having stronger data processing capabilities, making them more suitable for complex application scenarios. Since the advent of MCUs in the 1970s, 8-bit MCUs have dominated the market. With the development of smart technologies such as the Internet of Things and the cost competitiveness of 32-bit MCUs, the demand for 32-bit MCUs has rapidly increased, surpassing the total shipments of 4-bit, 8-bit, and 16-bit MCUs since 2015.
Today, with the rapid development of technologies such as the Internet of Things, cloud computing, 5G, and artificial intelligence, most IoT devices need to be equipped with next-generation MCU chips to perform complex tasks such as sensing, communication, information processing, computing, and issuing control commands. Having AI capabilities and cloud access capabilities is the biggest difference between next-generation MCU chips and traditional MCU chips.
MCUs based on RISC-V instruction set architecture represent a brand new market.
In recent years, RISC-V MCUs have developed rapidly. Due to their openness and flexibility, they have found extensive applications in the Internet of Things, smart devices, automotive electronics, industrial control, and other compact, low-power, and cost-sensitive embedded systems. In particular, automotive electronics are considered the most promising market for future RISC-V MCUs.
According to statistics from the SHD Group, in 2023, the global shipment of SoC products based on RISC-V cores is expected to reach 1.26 billion units, and is projected to reach 2 billion units by 2024, and will exceed 20 billion units by 2031. Among them, the largest share of shipments will be MCUs, with shipments of RISC-V MCUs expected to reach 617 million units in 2023, and is projected to reach 7.3 billion units by 2030, with a compound annual growth rate of 42.4%..
Domestic and foreign suppliers and products of RISC-V MCUs have also seen significant development in recent years, with many companies launching RISC-V core-based MCU products. For example, GigaDevice launched and mass-produced a 32-bit general-purpose MCU product based on RISC-V core in 2019; Renesas Electronics also introduced RISC-V MCUs, such as the R9A02G021; Espressif Technology launched several AI-capable MCU products through its self-developed RISC-V 32-bit processor. Additionally, companies like Qualcomm, NVIDIA, and Infineon are actively developing RISC-V-based solutions.
Recently, Infineon announced that it will launch a new series of automotive MCUs based on RISC-V in the coming years, leading the application of RISC-V in the automotive industry.
04What Benefits Does Open Source FPGA Bring to Domestic Companies?
Compared to MCU, the open-source path for FPGA is still in its early stages. However, from the development path of MCU, we can glimpse the future direction of FPGA.
First, let’s look at the similarities and differences between FPGA and MCU.
From a product feature perspective: FPGA and MCU are both programmable chips, but they achieve functionality differently. MCUs implement functions through software programming, suitable for executing fixed tasks (such as sensor control, simple algorithms); FPGA implements functions through hardware logic reconstruction, supporting parallel computing and complex algorithm acceleration, offering greater flexibility.
From an application scenario perspective: MCUs are characterized by low power consumption and low cost, widely used in simple control scenarios such as home appliances and consumer electronics; FPGA is suitable for high-performance computing (such as 5G signal processing, AI inference), hardware acceleration, and prototype verification in complex scenarios.
From a development threshold perspective: MCU development relies onC/C++ programming, with mature toolchains and low entry barriers. FPGA requires mastery of hardware description languages ( HDL), with complex design processes and higher requirements for engineers.
Now, looking at the future direction of open-source FPGA: currently FPGA is in the early exploration stage, with platforms like GitHub emerging with a large number of open-source IP cores, and corresponding toolchains are gradually maturing. In response to the demands of AI, the Internet of Things, and other fields, open-source FPGA can accelerate the implementation of customized solutions.
Will open-source FPGA become a future trend? What benefits does it bring to domestic FPGA companies?
For domestic companies, as analyzed above, open-source reduces technical barriers, attracts global developers to participate, and accelerates technological iteration, and open-source FPGA can also reduce dependence on international vendors’ IP.
In detailed analysis:
In terms of technological innovation: open-source community contributions IP cores can be quickly integrated by domestic manufacturers, shortening product launch cycles; open-source toolchains also support hardware trimming, allowing domestic FPGA to optimize power consumption and performance for specific scenarios (such as edge computing).
In terms of cost reduction: open-source EDA tools can replace expensive commercial tools, reducing R&D costs. Reusing open-source IP reduces redundant development, focusing on core technological innovation.
Therefore, open-source FPGA provides a differentiated competitive route for domestic FPGA manufacturers. Writing this, some may wonder why the development of open-source FPGA is much slower than that of MCU?
It is well known that developing FPGA is challenging, with high hardware design thresholds, performance bottlenecks in open-source toolchains, fragmented ecosystems, and the impact of mainstream FPGA vendors’ profit models hindering the progress of open-source FPGA. It is certain that open-source FPGA may become a key infrastructure for hardware innovation, but more efforts are needed from all sectors of the industry.
END
Welcome to leave comments and exchange ideas in the comment section!
Industry Community
