ICE-IP-338 High-speed XTS-GCM Multi Stream Inline Cipher Engine
FuriosaAI and GUC Partner on RNGD, the Most Efficient AI Accelerator for LLMs
Santa Clara, CA – July 31, 2024 – FuriosaAI Inc. is pleased to announce its collaboration with GUC (Global Unichip Corporation) as a key partner on the second-gen AI accelerator, RNGD (pronounced “Renegade”), the most efficient data center accelerator for high-performance large language and multimodal models.
GUC has been crucial in helping FuriosaAI to achieve an aggressive timeline for RNGD. Developing a new AI accelerator – especially one like RNGD, which utilizes advanced technology like HBM3 and a large-scale 653mm2 SoC with 40 billion transistors – is only possible with excellent partners like GUC, which brings deep expertise in designing system-on-chip (SoC) solutions.
“RNGD offers the unprecedented combination of performance, power efficiency, and programmability for running large language models and multimodal models. GUC's expertise in areas such as SoC design, backend implementation, and silicon interposer (CoWoS®) packaging has ensured that the RNGD project stayed on schedule to launch this year,” said June Paik, FuriosaAI CEO.
Complementing FuriosaAI's cutting-edge technology is GUC's expertise in turnkey semiconductor design services. As a trusted partner, GUC meticulously executed the project starting from spec-in, seamlessly integrating complex HBM memory subsystems, implementing the physical design, designing the package utilizing TSMC’s industry leading CoWoS® technology, followed by comprehensive testing services and manufacturing logistics management, successfully enabling FuriosaAI RNGD’s 1st time success. GUC played a pivotal role in enabling FuriosaAI RNGD's flawless execution, significantly accelerating its time-to-market.
“We are excited to partner with FuriosaAI to bring their revolutionary AI accelerator to market," said Dr. Sean Tai, president of GUC. "GUC is highly experienced with large-scale chip design. Our turnkey design services provide end-to-end support, enabling FuriosaAI to rapidly scale their innovation and meet the growing demand for AI acceleration solutions. We look forward to further supporting FuriosaAI as they continue to design innovative products for the AI market."
Together, FuriosaAI and GUC are poised to drive AI innovation to new heights, empowering organizations worldwide to harness the full potential of artificial intelligence.
For more information about FuriosaAI and the RNGD AI accelerator, visit https://furiosa.ai
For inquiries about GUC’s turnkey design services, visit https://www.guc-asic.com
|
Related News
- BrainChip Unveils Edge AI Box Partner Ecosystem for Gestures, Cybersecurity, Image Recognition, and Computer Vision
- BOS and Tenstorrent Unveil Eagle-N, Industry's First Automotive AI Accelerator Chiplet SoC
- Synopsys Announces Industry's First Ultra Ethernet and UALink IP Solutions to Connect Massive AI Accelerator Clusters
- Arteris and MIPS Partner on High-Performance RISC-V SoCs for Automotive, Datacenter and Edge AI
- DMP Released Next-Generation AI Accelerator IP "ZIA A3000 V2" - Industry-leading PPA efficiency to propel the future of edge AI
Breaking News
- Cadence to Acquire Secure-IC, a Leader in Embedded Security IP
- Blue Cheetah Tapes Out Its High-Performance Chiplet Interconnect IP on Samsung Foundry SF4X
- Alphawave Semi to Lead Chiplet Innovation, Showcase Advanced Technologies at Chiplet Summit
- YorChip announces patent-pending Universal PHY for Open Chiplets
- PQShield announces participation in NEDO program to implement post-quantum cryptography across Japan
Most Popular
- Qualitas Semiconductor Signs IP Licensing Agreement with Edge AI Leader Ambarella
- BrainChip Provides Low-Power Neuromorphic Processing for Quantum Ventura's Cyberthreat Intelligence Tool
- Altera Launches New Partner Program to Accelerate FPGA Solutions Development
- Alchip Opens 3DIC ASIC Design Services
- Electronic System Design Industry Posts $5.1 Billion in Revenue in Q3 2024, ESD Alliance Reports
E-mail This Article | Printer-Friendly Page |