TECHNOLOGY

Core competencies
State-of-the-art
DNN Algorithm
Support
Outstanding
NPU Efficiency for
Smart Mobility
Memory
Bandwidth
Maximization
Scalable
Performance
0.5 ~ 200 TOPS
Advanced DNN model
Compression
Support
PURSUING
TECHNOLOGIES
We saw a fast-growing number of IoT devices and believed the era of
Artificial Intelligence is something inevitable. We embrace the challenges of bringing the most power-efficient and advanced NPU(Neural Processing Unit) for IoT devices.
MLPERF
BENCHMARK RESULT
Learn more
MLPERF
BENCHMARK RESULT
Learn more
INITIAL
PERFORMANCE TESTThis video illustrates how fast 50,000 pictures from the Imagenet 2012 dataset in an FPGA board are processed by the DEEPX NPU. The demo system is composed of a Windows PC and Xilinx Alveo U250 FPGA board.
The FPGA-based implementation runs at 320Mhz and demonstrates 600 IPS (1.6 ms per inference) for the MobileNet Version 1 in the MLPerf AI benchmark category.The ASIC’s implementation will increase threefold without any NPU design change due to simple clock frequency improvement. (Top-ranked in the MLPerf AI benchmark)
Applications
01Consumer
Electronics
Robot
Vacuum
Smart TV
Smart
Air Conditioner
02Smart Mobility
Autonomous Vehicle
Autonomous Drone
AMR
(Autonomous
Mobile Robot)
03Automotive
ADAS
DSM
(Driver Status
Monitoring)
Infotainment
04VR/AR
Entertainment
Device
Enterprise Device
Personal Assistant