Weighing the Pros and Cons of Enclosure Materials

- By Hammond Manufacturing Enclosures come in many styles,...

All About O-RAN in 2024!

O-RAN has gained significant popularity thanks to...

Differential and Floating Voltage Measurements

Fundamentally, all oscilloscopes measure voltage (in the...

Trending

SEMIFIVE, HyperAccel Create Cost-Effective Gen AI Chip Named Bertha

SEMIFIVE declared that it has reached an agreement with HyperAccel to create Bertha, a Gen AI Chip, for mass manufacturing. Bertha is expected to be developed with 4nm process technology, with mass production expected to start in 2026’s first quarter.SEMIFIVE, HyperAccel Create Cost-Effective Gen AI Chip Named Bertha

An AI device called the LLM Processing Unit (LPU) was created by HyperAccel especially for use with transformer-based Large Language Models (LLM). This is the first semiconductor LPU in the world designed with LLM inference in mind, providing low latency, cheap cost, and features unique to this domain.

The anticipated outcome is a price/performance ratio that is 19 times better than that of a conventional supercomputer, together with performance gains of up to two times, replacing the current high-cost and low-efficiency Graphics Processing Units (GPUs).

SEMIFIVE is an expert in ASIC design solutions and SoC platforms. These days, the company’s main focus is on creating sophisticated SoC design platforms for AI chips, but it still has plans to broaden its roadmap in order to meet client demand for custom AI silicon. In order to do this, SEMIFIVE is actively working with top industry partners to develop its SoC chiplet platform.

Key Comments

“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.”SEMIFIVE, HyperAccel Create Cost-Effective Gen AI Chip Named Bertha

“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.”

For Further Info, CLICK HERE

Don't Miss