Exclusive | Former Graphcore President Lu Tao Joins MemSilicon, Aims to Turn LPU into a "High-Speed Rail"
Former Graphcore President Lu Tao joins MemSilicon as CEO; the company completes a Series A funding round of over RMB 400 million, focusing on LPU (AI processor) R&D.
Key Takeaways
- Key Highlight：Former Graphcore President Lu Tao joins MemSilicon as CEO; the company completes a Series A funding round of over RMB 400 million, focusing on LPU (AI processor) R&D.
- Innovation & Tech：Highlights advancements in Exclusive, Former, Graphcore, demonstrating rapid progress in model capabilities.
- Industry Impact：Reported via 雷峰网 (CN), offering actionable signals for developers and technology leaders.
MemSilicon announced the completion of a Series A funding round of over RMB 400 million, led by Boyuan Capital, with participation from Bosch Ventures, Chuangling Capital, miHoYo, GigaDevice, Xiaomi Strategic Investment, and other institutions. Former Graphcore President and Greater China General Manager Lu Tao has joined the company as CEO and co-founder.
Lu Tao has over two decades of experience in the semiconductor industry, having previously served as General Manager of Cavium China and Vice President of Lightelligence. His career spans Arm server CPUs, large-SRAM-architecture AI processors (IPUs), and silicon photonics. Graphcore is a globally recognized AI processor company whose IPU products were once seen as a GPU alternative. Lu Tao's joining brings MemSilicon deep expertise in AI chip architecture design.
The company's core focus is the development of the LPU (Learning Processing Unit). The "high-speed rail" metaphor in the title suggests its pursuit of high-throughput, low-latency AI inference and training capabilities. Against the backdrop of continuously rising compute demands for large model training and inference, competition in the domestic AI chip space is intensifying, and MemSilicon is attempting to enter the market with a differentiated architecture.
Looking at the investor lineup, it includes both industrial capital such as Bosch Ventures, GigaDevice, and Xiaomi Strategic Investment, as well as consumer internet company miHoYo, reflecting expectations for AI chip applications across multiple downstream scenarios including autonomous driving, consumer electronics, and game rendering. However, the cycle from tape-out to mass production to ecosystem building for AI chips is long, and MemSilicon still faces multiple challenges in technology implementation and market competition.
This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.
Industry Insights & Analysis
As artificial intelligence rapidly evolves, breakthroughs surrounding Exclusive, Former, Graphcore, President are shifting toward scalable, robust real-world implementations.
Driven by both open-source ecosystems and proprietary model architectures, the integration between compute optimization, data engineering, and agentic workflows is accelerating. This development provides a strategic benchmark for upcoming AI tooling and developer workflows.