BrainChip, SiFive partner to bring AI and ML to edge computing

We are excited to bring Transform 2022 back to life on 19th July and virtually 20th July – 3rd August. Join AI and data leaders for sensible conversations and exciting networking opportunities. Learn more about Transform 2022


AI processor maker BrainChip, which makes ultra-low-power neuromorphic chips and supporting software, and RISC-V computing style founder SiFive announced today that they are offering chip designers to offer their optimized artificial intelligence (AI) and machines. Combined related technologies. Learning for the same computing (ML).

BrainChip’s AI engine, Akida, is a state-of-the-art neural networking processor architecture that brings AI functionality to edge and cloud computing in a way that was not previously possible with its high performance and ultra-low power consumption, the company said. Jerome Nadel, CMO of BrainChip, told VentureBeat that Sifive Intelligence Solutions accelerates AI / ML applications with their highly configurable multi-core, multi-cluster enabled design, integrated software and hardware.

The integration of Brainchip’s Akida technology and SiFive’s multi-core RISC-V processors is expected to provide an efficient solution for integrated Edge AI computing, Nadel said.

RISC-V (pronounced “risk-five”) is an open instruction-set computing architecture based on established composite instruction set computing (RISC) principles. It is an open source project available to anyone who wants to use it. RISC-V represents a major step forward in data processing – required for all newer and more “heavy” applications (such as machine learning, AI and high-resolution video) used daily. RISC-V seems to be a natural fit for brainchip architectures for neural networking processors.

RISC-V, with the addition of 5G broadband wireless connectivity, is providing a major impetus for all IT sectors here in 2022. WD has become one of the largest manufacturers of RISC-V processors and other products.

The AI ​​engine mimics the human brain

SiFive Intelligence-based processors have a highly configurable multi-core, multi-cluster-capable design that is optimized for a range of applications requiring high-throughput, single-thread performance under tight power and area limitations, Nade said.

Nadel said the brainchip’s Akida mimics the human brain that analyzes only the sensor inputs required at the time of acquisition, processing data with efficiency, accuracy and energy economy. Keeping AI / ML local on the chip and keeping it cloud-free reduces delays while improving privacy and data security, he said.

BrainChip’s technology is based on its Spiking Neuron Adaptive Processor (SNAP) technology and licenses SNAP with technology partners. SNAP provides a development solution for companies entering the neuromorphic semiconductor chip market. It is a core-enabled technology in neuromorphic semiconductor chips that enables a variety of applications such as gaming, cybersecurity, robotic technology and stock market forecasting.

“As we expand our ecosystem of portfolio partners, we want to ensure that our relationships are built on complementary technologies, capabilities and the breadth of the environment so that we can expand opportunities to as many potential customers as possible,” Nadel said. “Running our technology into a SiFive-based subsystem is a specific type of partnership that accomplishes these goals.”

3 questions for BrainChip

Jack Kang, senior vice president of corporate marketing business development at VentureBeatFive, asked some specific questions about customer experience (CX), news and the relevance of the partnership.

Venturebeat: What’s the number? 1 business takeaway from this announcement?

Jack Kang: For SiFive, this ad demonstrates the continued use of the SiFive Intelligence family of RISC-V-based processor IPs. More companies are choosing RISC-V to be part of their product roadmap strategy and SiFive is the leading provider of commercial RISC-V IP. In the emerging green-field market of AI / ML-enabled platforms, such as the edge processing market targeted by Brainchip, performance per se and performance benefits of the SiFive processor architecture make the SiFive Intelligence family a competitive choice.

VentureBeat: Does BrainChip use any IP arm in its chips? Arm is known for low power and high performance.

Kang: BrainChip has discussed Arm IP for their product line. ARM processors have built a reputation for low power compared to x86-based products. SiFive Intelligence Products compares favorably with ARM products, offering up to 30% better performance-per-field with a single ISA for easy programming, and a modular approach that adjusts well to work with rigid AI IPs such as Developed by BrainChip.

VentureBeat: Can you elaborate on this statement: “(brainchip) mimics the human brain to analyze only the necessary sensor inputs at the time of acquisition.”

Kang: This statement shows the ability of human beings to focus on the important thing. For example, listening to a conversation in a coffee shop while still registering and acknowledging background sounds. The brainchip solution will mimic this ability to reduce power and increase efficiency by focusing on important data being processed. This is similar to adopting mixed and lower precision data types (INT8 vs. FP16) to speed up and improve AI / ML processing efficiency, but is a step further.

Competitors in the market

Alico Viejo competes in the growing intelligent-edge chip market with California-based Branchip, Nvidia Deep Learning GPU, Keras, TFLearn, Clarifai and Microsoft Cognitive Toolkit, AWS Deep Learning AMI and Torch. Nvidia owns about 80 percent of the global GPU (graphics processing unit) market. G2.com has market information here. The availability of new SiFive / BrainChip solutions will be announced at a later date.

Venturebeat’s mission Transformative Enterprise is about to become a digital town square for technology decision makers to gain knowledge about technology and transactions. Learn more about membership.

Similar Posts

Leave a Reply

Your email address will not be published.