← Back to Blog
Physical AI

Ruixin High-Beam D35: World's First RISC-V Dataflow Physical AI Chip Enters Mass Production

1. Overview

On September 9, 2026, Suzhou Ruixin Integrated Circuit Technology Co., Ltd. announced that its self-developed High-Beam D35 (Gao Guang D35) dataflow AI chip has entered mass production. It is positioned as the world's first RISC-V dataflow architecture physical AI chip, combining three key innovations:

  • Full dataflow architecture — no program counter, no instruction scheduling; data readiness triggers computation automatically, delivering higher compute-unit utilization, lower data movement, deterministic latency, and superior energy efficiency
  • Self-developed high-performance RISC-V CPU core — recognized by Intel as the only globally approved procurement, demonstrating RISC-V's advancement into high-end computing
  • 128 GB large-capacity memory — supports large-scale AI model deployment at the edge with high-throughput video encode/decode capabilities several times that of comparable edge GPUs

ISCA 2026 Best Paper Nominee: The dataflow computing research behind High-Beam D35 was nominated for best paper at ISCA 2026, the most prestigious and longest-running academic conference in computer architecture. This represents the international top level for Chinese teams in this field.

2. Dataflow Architecture: From MIT to Mass Production

The dataflow architecture concept was first proposed by MIT Professor Jack Dennis in the 1960s. Unlike traditional control-flow architectures, dataflow uses a "data-driven computation" model where data readiness automatically triggers computation, eliminating the need for program counters and instruction scheduling.

Control Flow vs. Dataflow: An Analogy

Control flow is like a cafeteria line: someone directs traffic, everyone queues up, steps forward one at a time, and gets served when called. Dataflow is like a buffet: all dishes are laid out, you take what you want, and when one dish runs low it's naturally replenished — no one needs to direct traffic.

Four Key Advantages of Dataflow

AdvantageExplanationImpact on AI Inference
Higher compute-unit utilizationNo instruction-scheduling overhead; compute units stay busyGPU utilization often <30% in edge inference; dataflow eliminates this bottleneck
Less data movementData flows directly between compute units; no repeated memory read/writeReduces memory bandwidth pressure and energy waste
Deterministic latencyNo branch prediction failures, no cache missesCritical for real-time control in robotics and autonomous systems
Higher energy efficiencyControl-flow overhead eliminated; more work per wattPhysical AI scenarios are power-constrained; efficiency gains are the key metric

These characteristics make dataflow architecture inherently suited for AI inference — especially physical AI, where edge-side power, size, and cost constraints are hard limits.

3. High-Beam D35 Key Specifications

ParameterValue
Chip nameHigh-Beam D35 (Gao Guang D35)
ArchitectureFull dataflow (data-driven, no program counter)
ISARISC-V (64-bit)
CPU coreRuixin self-developed high-performance RISC-V core (Intel globally recognized)
Memory128 GB large-capacity on-board memory
Video encode/decodeSeveral times throughput of comparable edge GPUs
Target deploymentEdge-side and terminal-side physical AI acceleration
Academic recognitionISCA 2026 best paper nominee
StatusMass production (announced 2026-09-09)

Why 128 GB matters: Large memory allows bigger AI models to run locally at the edge — data stays on-device (security), no network round-trip (speed), and works offline (reliability). These three dimensions combined unlock use cases that cloud-dependent architectures cannot serve.

4. Self-Developed RISC-V CPU Core & Intel Recognition

The High-Beam D35 integrates a high-performance RISC-V CPU core fully self-designed by Ruixin. This core received Intel's sole global procurement recognition, validating that RISC-V is no longer synonymous with "low-end embedded" and is advancing into high-end computing territory.

This recognition carries significance beyond the chip itself. It demonstrates that the open RISC-V ISA can produce CPU cores that meet the procurement standards of the world's largest semiconductor company — a powerful signal for the entire RISC-V ecosystem.

The timing aligns with RISC-V's commercial inflection point in 2026: Ubuntu 26.04 LTS became the first enterprise OS with native RISC-V optimization, the RISC-V Server Platform Specification 1.0 was ratified, and SHD Group forecasts RISC-V reaching 33.7% total market share across all hardware segments by 2031.

5. Four Physical AI Application Scenarios

Based on the dataflow architecture's technical characteristics, High-Beam D35 targets four physical AI application domains:

ScenarioDescriptionWhy Dataflow Fits
Industrial IntelligenceAIPC acceleration, video compression & analysis, industrial smart controlHigh compute utilization + video codec throughput handles more channels per unit cost
Embodied AIRobots, autonomous vehicle domain controllers — perception + decision + control integrationLow latency, high energy efficiency, and deterministic timing match hard real-time constraints
Cockpit-Driving IntegrationSmart cockpit + driving-domain perception on a single chipLarge memory + mixed workload processing enables concurrent AI apps and driving compute
Communications5G small cells, mmWave, AI RANArchitecture advantages in power, size, and reliability align with telecom-grade requirements

6. Glorious Community: Ecosystem Strategy

Hardware performance ultimately depends on software ecosystem maturity. Ruixin launched "Glorious Community" (Guang Rong She Qu) alongside the chip — the world's first RISC-V dataflow developer community.

The community is not a simple forum but a complete resource platform integrating:

  • Documentation center
  • SDK toolchain
  • Model library
  • Online training
  • Technical support

Ruixin also established the Ruixin Glorious Fund to support ecosystem innovation, providing a global testing ground for RISC-V and dataflow developers.

7. Industry Context: Global Dataflow Investment Wave

Global tech giants have been aggressively investing in dataflow technology, validating its strategic value for the inference era:

CompanyActionSignificance
NVIDIA$20B acquisition of Groq dataflow technology license + core team absorptionLargest dataflow IP deal in history
AMDAcquired Canadian dataflow inference chip company TaalasExpands AI inference portfolio beyond GPU
IntelDataflow investment and in-house developmentStrategic hedge on post-GPU architecture
SamsungDataflow investment and in-house developmentDiversification beyond Arm-based custom silicon
RuixinHigh-Beam D35 mass production (RISC-V + dataflow + physical AI)First to combine all three paradigms in a shipping chip

8. About Ruixin

Suzhou Ruixin Integrated Circuit Technology Co., Ltd. is headquartered at No. 90 Yun Hui Road, Suzhou Industrial Park. Founded in August 2020, the company focuses on RISC-V CPU + dataflow LPU (Language Processing Unit) AI chip design, aiming to provide an efficient, autonomous, and open computing foundation for the physical AI era.

  • Chief Scientist: Sun Ninghui, academician of the Chinese Academy of Engineering and national strategic scientist
  • Core Team: Veterans from IBM, Intel, and top research institutions
  • Academic output: 100+ published papers, dozens of patents
  • Focus: RISC-V CPU + dataflow LPU AI chips for physical AI

9. Official Sources

物理 AI

睿芯高光 D35:全球首款 RISC-V 数据流物理 AI 芯片量产

2026 年 9 月 9 日,苏州睿芯宣布自主研发的「高光 D35」数据流 AI 芯片实现量产。这是全球首款基于 RISC-V 指令集的数据流架构物理 AI 芯片。

三大核心技术优势

  • 全数据流架构:无程序计数器、无指令调度,数据就绪即自动触发计算,能效比提升数倍
  • 全自研高性能 RISC-V CPU 内核:获 Intel 全球唯一采购认可
  • 128 GB 大显存:支持大规模 AI 模型边缘侧本地部署,视频编解码能力数倍于同级边缘 GPU

数据流架构原理

数据流架构由 MIT Jack Dennis 教授于 1960 年代提出。与传统控制流不同,数据流采用「数据驱动计算」模式:数据就绪后自动触发计算,无需程序计数器调度。

四大优势:计算单元利用率更高、数据搬运更少、延迟更确定、能效比更高。这使数据流架构天生适合 AI 推理,尤其是物理 AI 场景。

四大应用场景

  • 行业智能计算(AIPC 加速、视频分析、工业控制)
  • 具身智能(机器人、无人车域控)
  • 舱驾一体(智能座舱 + 驾驶域融合)
  • 通信领域(5G 小基站、毫米波、AI RAN)

光荣社区

睿芯启动「光荣社区」——全球首个 RISC-V 数据流开发者社区,提供文档中心、SDK 工具链、模型库、在线实训和技术支持,并设立睿芯光荣基金支持生态创新。

产业背景

英伟达以 200 亿美元获取 Groq 数据流技术授权;AMD 收购 Taalas;英特尔、三星同步布局数据流。全球科技巨头用真金白银投下了对数据流架构的战略信任票。

高光 D35 相关技术成果获 ISCA 2026 国际计算机体系结构顶会最佳论文提名。

Physical AI

Ruixin High-Beam D35: Первый в мире RISC-V датафлоу-чип для физического ИИ

Suzhou Ruixin объявила о массовом производстве чипа High-Beam D35 — первого в мире RISC-V чипа с датафлоу-архитектурой для физического ИИ. Три ключевых инновации: полная датафлоу-архитектура (без счётчика программ), собственное RISC-V ядро (признано Intel), 128 ГБ памяти. Технология номинирована на лучшую статью ISCA 2026.

Physical AI

Ruixin High-Beam D35: Primer chip de IA fisica RISC-V con arquitectura dataflow del mundo

Suzhou Ruixin anuncia la produccion en masa del High-Beam D35, el primer chip del mundo con arquitectura dataflow RISC-V para IA fisica. Tres innovaciones clave: arquitectura dataflow completa (sin contador de programa), nucleo CPU RISC-V autodesarrollado (reconocido por Intel), 128 GB de memoria. La tecnologia fue nominada a mejor articulo en ISCA 2026.