SEMIFIVE Concluded Mass Production Contract for AI Chip with HyperAccel
Collaboration on design and development using 4nm process technology, with mass production targeted for Q1 2026
SEOUL, South Korea, Oct. 11, 2024 — SEMIFIVE, a leading design solution provider and pioneer of platform-based custom silicon solutions, has announced the conclusion of a contract with HyperAccel to develop a generative AI chip, Bertha, for mass production. Bertha will be developed using 4nm process technology, and the mass production is targeted to commence in the first quarter of 2026.
HyperAccel has developed a LLM Processing Unit (LPU), an AI chip specifically designed for transformer-based Large Language Model (LLM). This is the world’s first semiconductor LPU tailored for LLM inference, offering low cost, low latency, and domain-specific features. It is expected to replace existing high-cost and low-efficiency Graphics Processing Units (GPUs) with performance improvements of up to 2 times and a price/performance ratio that is 19 times better than that of a typical supercomputer.
SEMIFIVE specializes in SoC platforms and ASIC design solutions. The company focuses on developing expert SoC design platforms for AI chips these days with plans to expand its roadmap to respond to customer demand for AI custom silicon. To achieve this goal, SEMIFIVE is actively developing its SoC chiplet platform in collaboration with industry-leading partners.
“We are delighted to work with SEMIFIVE, a leading provider of SoC platforms and comprehensive ASIC design solutions, for the development of Bertha to be mass-produced,” said Joo-Young Kim, CEO of HyperAccel. “By collaborating with SEMIFIVE , we are excited to offer customers AI semiconductors that provide more cost-effective and power-efficient LLM features than GPU platforms. This advancement will significantly reduce the operational expenses of data centers and expand our business scope to other industries that require LLMs.”
“HyperAccel is a company with the most efficient and scalable LPU technology for LLMs. As the demand for LLM computation is skyrocketing, HyperAccel has the potential to become a new powerhouse in the global processor infrastructure,” said Brandon Cho, CEO and co-founder of SEMIFIVE. “We are extremely excited to be the production partner for HyperAccel’s groundbreaking Bertha chip, and we are thrilled to contribute to yet another innovative success story built on the SEMIFIVE platform.”
Learn more about SEMIFIVE
SEMIFIVE is the pioneer of platform-based SoC design, working with customers to implement innovative ideas into custom silicon in the most efficient way. Our SoC platforms offer a powerful springboard for new chip designs, and leverage configurable domain-specific architectures and pre-validated key IP pools. We offer comprehensive spec-to-system capabilities with end-to-end solutions so that custom SoCs can be realized faster, with reduced cost and risks for key applications such as data center or AI-enabled IoT. With a strong partnership with Samsung Foundry as a leading SAFETM DSP partner, as well as the larger ecosystem, SEMIFIVE provides a one-stop shop solution for any SoC design needs.
Related Semiconductor IP
- MACsec Engine optimized for 10Base-T1S/T1L applications
- Dual Port, Voltage Scaling Register File Compiler on GF22FDX+
- Single Port, Voltage Scaling, High Speed SRAM Memory Compiler on GF22FDX+
- I3C Full Controller / Target
- I3C HCI Host Controller
Related News
- SEMIFIVE Signs Turnkey Contract with Mobilint to Develop Robotics AI Chip Under 'K-On-Device AI Semiconductor' Program
- SEMIFIVE Commences Mass Production of HyperAccel’s LLM AI Inference Accelerator ‘Bertha’ on Samsung 4nm, Spurring Growth Momentum
- FotoNation and SEMIFIVE Announce Strategic Collaboration for Turnkey Development of TriSilica Perceptual AI Chip Family Using Samsung Foundry
- Kandou AI to Open India Chip Design Headquarters in Hyderabad
Latest News
- Cyient Semiconductors Secures Strategic Investment from GlobalFoundries
- JEDEC® Previews Next-Generation DDR6 DRAM: Higher Performance, Greater Capacity, Improved Power Efficiency and Data-Center-Class Reliability
- INTELPRO Adopts Andes AX46MPV Flagship Multicore Vector Processor and AndesAIRE™ AnDLA™ I370 to Power Next-Generation Heterogeneous AI and Robotics Solutions
- VeriSilicon Introduces Low-Power, High-Performance Wearable Subsystem Solution for Next-Generation AI/AR Glasses
- IC Manage Announces MCP Server for GDP-AI Design and IP Management System