Based on the AI-specific APiM framework, a modular deep neural network learning accelerator without any external
caching can be used for high-performance edge computing, as a vision-based deep learning computing and AI algorithm
acceleration. NCC S1 is small in shape, extremely low in power consumption and best peak performance. Equipped with
complete and easy-to-use model training tools, network training model instances, and professional hardware platform, it
can be quickly applied in the artificial intelligence industry.
5.6Tops Best Peak Performance
Based on the AI-embedded Neural Network Processor (NPU), the NCC S1 possesses 28,000 parallel neural computing cores
and supports on-chip parallel and in-situ calculations. Its peak up to 5.6Tops, dozens of times higher than other
solutions on the market. It can afford complex high-density calculations for high-performance edge computing field.
AI Processing Framework APiM
Based on AI-specific MPE matrix engine and APiM (AI processing in Memory) framework, it deals with AI in a
revolutionary way. Without any instructions, bus and external DDR cache, plenty of data can be directly input or output
to the silicon chip by upgrading the network preloading once, which greatly lifts the processing speed of AI and
reduces the processing energy consumption.
9.3Tops/W High Energy Efficiency
The NPU of NCC S1 neural network computing card uses the 28nm process technology. The power is only 300mW when
throughput is 2.8 Tops, while the energy efficiency is up to 9.3 Tops/W. It maintains strong computing ability while
owning extremely low energy consumption, endowed with great advantages in the edge computing field of terminal
High-performance Hardware Platform
NCC S1 neural network computing card can be equipped with ROC-RK3399-PC open source main board. On condition that it is
stocked with high-performance RK3399 six-core processor and abundant hardware interface, it can rapidly integrate
hardware platform for edge computing, set up product prototype, and thus accelerate AI product project process.
Supporting Model Training Tools
Provide the complete and easy-to-use model training tool PLAI (People Learn AI) which based on PyTorch, it can be
developed on Windows 10 and Ubuntu 16.04 systems to add custom network models more easily and quickly, which greatly
reduces the technical difficulties to applying AI and makes AI technology accessible to more people.
Provide Network Training Model
Support the following three network training model examples such as GNet1, GNet18 and GNetfc with more network
instances continuing to emerge subsequently, making it possible to easily test a large number of deep learning
applications on the device.
Lightspeeur SPR2801S (28nm process, unique MPE and APiM architecture)
Applicable ROC-RK3399-PC platform
Support Pytorch, Caffe framework, follow-up support TensorFlow
PLAI model training tool(Support for GG1, GNet18 and GNetfc network models based on VGG-16)