Axelera AI Platform Accelerates Edge Application Deployment
By Maurizio Di Paolo Emilio, EETimes (November 21, 2023)
Conventional AI applications frequently require local devices to transmit data to a centralized cloud server for analysis and processing. Although this methodology exhibits efficacy across various scenarios, it’s not without its constraints, encompassing latency, bandwidth consumption, and privacy and security considerations. Relocating AI processing near the location where the data is generated—otherwise known as the “bringing AI to the edge” approach—resolves these concerns through the execution of computations locally on the device or in close proximity to the data source.
In an interview with EE Times, Axelera AI co-founder and CEO Fabrizio Del Maffeo noted recent industry milestones the company achieved, as well as the appointment of a former Arm executive to Axelera’s board of directors.
To read the full article, click here
Related Semiconductor IP
- Bluetooth Low Energy 6.0 Digital IP
- Flash Memory LDPC Decoder IP Core
- SLM Signal Integrity Monitor
- Bluetooth Low Energy 6.0 Scalable RF IP
- All Digital Fractional-N RF Frequency Synthesizer PLL in GlobalFoundries 22FDX
Related News
- Arm Accelerates Edge AI with Latest Generation Ethos-U NPU and New IoT Reference Design Platform
- Secure, Efficient and Trusted: Axelera AI and Kudelski IoT Partner for Next-Generation Edge Intelligent Ecosystem
- Elliptic Labs’ AI Platform Now Optimized for Ceva’s NeuPro-Nano NPU – Enabling Smarter Edge Devices
- Launch of BrainChip Developer Hub Accelerates Event-Based AI Innovation on Akida™ Platform with Release of MetaTF 2.13
Latest News
- Perceptia Devices Release pPLL08W, best-in-class RF PLL IP in GF22FDX
- Axiomise Partners With Bluespec to Verify Its RISC-V Cores
- Rapidus Achieves Significant Milestone at its State-of-the-Art Foundry with Prototyping of Leading-Edge 2nm GAA Transistors
- SEMIFIVE Files for Pre-IPO Review on KRX
- Innosilicon Scales LPDDR5X/5/4X/4 and DDR5/4 Combo IPs to 28nm and 22nm, Cementing Its Position as the ‘One Stop’ for Memory Interface Solutions