Play Video
About AlphaICs
AlphaICs has developed a next-generation processor Real AI Processor (RAPTM), based on a proprietary architecture. The RAPTM architecture uses a specialized Instruction Set Architecture (ISA), designed for accelerating AI workloads. RAPTM is highly scalable and can be scaled for mobile devices to datacenter solutions.
Markets
Automotive
The advancement of automotive technology and the continuous increase in usage of electronics components in vehicles..
Retail
Optimize and accurate planning of workforce in different operations like cash management, in-store replenishment, fulfillment..
Smart Factory
AI has enabled Industrial Robots to advance from doing pre-programmed tasks with high precision and speed to judging the nature of functions..
Surveillance
Artificial Intelligence (AI) technology is bringing starting developments in the surveillance industry. AI surveillance technology is spreading globally..
Health Care
Smart technologies are making healthcare efficient, convenient, and more personalized, by streamlining power consumption, comfort, and data.
Manufacturing
Based on deterministic criteria, factory automation has a set of processing requirements that are different from those provided by a general purpose OS.
Consumer
By dedicating relatively simple sub-processors to handle time-consuming I/O formatting and processing, overall system performance can be improved.
Markets
Products
Gluon AI Co-Processor
Gluon, is a 8 TOPS inference Co-Processor that is taped-out with 16 nm TSMC FF technology. Gluon is optimized for vision applications and provides best performance for image classification, face recognition, object detection and other video analytics applications.
- 8 TOPs
- 3.5 Watt (typical power)
- 4 lane PCIe gen-3
Gluon Evaluation Board
Gluon Evaluation board is a 4-lane gen-3 PCIe card with Gluon AI Co-processor. It can be used to prototype and develop AI hardware.
- PCIe Gen 3 Support: Supports 1, 2 and 4 lanes
- Popular Neural Networks examples available
-
Easy deployment of Deep Neural Networks
One click quantizer
Debugger, profiler support
Technology
Scalable Architecture
Our architecture is scalable and can produce Co-processors from 0.5 tops to 64+ Tops by increasing number of agents.
Architecture Innovation
Our architecture has many advanced architecture innovations such as layer fusion in H/W, intelligent memory access and on-chip memory optimizations that give higher utilization.
Learning Agent or Inference Agent
Each agent can be configured as learning agent or inference agents. Our architecture enables learning at the edge within constrained resources.
Institutional Investors
Testimonials
Tiffany Patrick
Web Creator
Plan, create and code internet sites and web pages.
Ernie Wilks
Web Creator
Plan, create and code internet sites and web pages.
Celeste Munro
Web Creator
Plan, create and code internet sites and web pages.
Jamie Snow
Web Creator
Plan, create and code internet sites and web pages.