San Jose, CA – August 10, 2023 – Andes Technology, a leading supplier of high-performance, low-power 32/64-bit RISC-V processor cores and founding Premier member of RISC-V International, and TetraMem Inc, a pioneer in analog memristor technology and in-memory computing, is proud to announce a strategic partnership aimed at delivering a fast, high-performance AI inference chip that will revolutionize the artificial intelligence and edge computing landscape.
The convergence of artificial intelligence and edge computing has become a driving force behind the advancement of numerous industries, including autonomous vehicles, smart cities, healthcare, cybersecurity, and entertainment. Recognizing the enormous potential of this market, TetraMem has licensed the powerful Andes RISC-V NX27V vector CPU, combined with ACE (Andes Custom Extension)TM) to create a breakthrough solution that addresses the challenges of AI processing in power-constrained environments.
The centerpiece of this collaboration is the fusion of Andes’ high-performance RISC-V Vector CPU with TetraMem’s revolutionary computer memory – an analog RRAM – in-memory computer architecture through ACE to enable tight coupling for the best performance. This unprecedented combination amplifies the strengths of both companies, resulting in lightning-fast, energy-efficient AI inference that surpasses the limitations of traditional computing approaches – transcending the “memory wall” and “end of Moore’s Law” limitations.
Features of AI Accelerator Chip:
- RISC-V Vector CPU Excellence: Andes RISC-V Vector CPU cores are known for their exceptional performance, efficiency and configurability, making them ideal for a wide range of AI and edge computing applications. The addition of Andes’ powerful vector processor brings unmatched performance to the accelerator chip.
- Analog In-Memory Computing Prowess: TetraMem’s unique analog in-memory computing technology gives the chip massively parallel VMM computation without data movement, reducing the energy overhead of conventional architectures as confirmed in TetraMem’s first commercially manufactured demonstration chip.
- Energy efficient AI acceleration: The joint effort aims to create a chip that is not only powerful but improves energy efficiency by at least an order of magnitude. By optimizing calculations and eliminating the transfer of weight data, the planned chip will significantly extend the battery life of edge devices and impose an almost zero impact on thermal budgets.
- Flexible and scalable: The AI accelerator chip will be designed from 22nm and above, to 7nm and below in the future, with versatility and scalability in mind for easy integration into various AI-powered products and applications. This adaptability ensures broad industry application. The TetraMem founding team has demonstrated scalability of the computing meristor to 2nm and below, ensuring a roadmap for future-proof solutions.
Mr. Frankwell Lin, Chairman and CEO of Andes Technology, expressed his excitement about the partnership, saying, “Our collaboration with TetraMem represents a significant milestone in the development of AI accelerators. By combining Andes’ world-class RISC-V vector processing technology with TetraMem’s cutting-edge analog in-memory computing, we are poised to deliver a revolutionary solution that will power the next generation of AI applications.”
Dr. Glenn Ning Ge, CEO of TetraMem Technologies, echoed this sentiment, stating, “TetraMem’s analog-RRAM-based in-memory computing technology changes the physics of how AI computations are performed, launching a new era of computing. Working hand hand in hand with the Andes, we are confident that our joint AI accelerator chip will set a new standard for AI processing in terms of speed and energy efficiency.”
Tetramem expects to unveil the AI accelerator chip and make technical samples and development kits for the new 22nm “TetraMem MX Series” chip available to the public in the second half of 2024. The partnership between Andes and TetraMem marks a major leap forward in AI hardware that promises to unlock unprecedented possibilities for AI innovations.
For more information about Andes Technology and TetraMem Technologies, please visit their respective websites at www.andestech.com and www.tetramem.com.
About Andes technology
Eighteen years in business and a founding Premier member of RISC-V International, Andes is a publicly traded company (TWSE: 6533; SIN: US03420C2089; ISIN: US03420C1099) and a leading supplier of high-performance/low-power 32/64-bit embedded processor IP solutions and the driving force in taking RISC-V mainstream. Its V5 RISC-V CPU families range from tiny 32-bit cores to advanced 64-bit Out-of-Order processors with DSP, FPU, Vector, Linux, superscalar and/or multi/many-core capabilities. By the end of 2022, the cumulative volume of Andes-Embedded™ SoCs has exceeded 12 billion. For more information, please visit https://www.andestech.com.
About TetraMem Inc
Founded in 2018 by a team of world-class experts, TetraMem is poised to deliver the industry’s most disruptive in-memory computing (IMC) technology for edge applications. The TetraMem team brings together complementary skills and technological know-how with 34 patents issued to date spanning materials science, device, circuit design, architecture and application, as well as a patented six-dimensional co-design methodology. TetraMem is the only company in the world to produce a high-bit-density multi-level memristor-based accelerator in a commercial foundry, with the technology featured in the March 30, 2023 issue of the journal, Nature. This breakthrough technology enables memory-based computing, eliminates weight data movement, significantly improves energy efficiency and performance of AI and machine learning workloads compared to digital technologies, with scalability far beyond the limits of competing analog technologies. For more information, please visit https://www.tetramem.com. Follow TetraMem on LinkedIn.
#Andes #Technology #TetraMem #Collaborate #Build #Groundbreaking #Accelerator #Chip #Analog #InMemory #Computing