imaging vision IP
Filter
Compare
11
IP
from 6 vendors
(1
-
10)
-
General Purpose Neural Processing Unit (NPU)
- Hybrid Von Neuman + 2D SIMD matrix architecture
- 64b Instruction word, single instruction issue per clock
- 7-stage, in-order pipeline
-
Digital Signal Processor IP
- • High performance vector signal processing
- and efficient control code processing
- • 256 8-bit macs, 128 16-bit macs, or 64 32-bit macs per cycle
- • Flexible vector permute operations
-
Digital Signal Processor IP
- • High performance vector signal processing
- and efficient control code processing
- • 32 8-bit macs, 16 16-bit macs, or 8 32-bit macs per cycle
- • Flexible vector permute operations
-
Digital Signal Processor IP
- • High performance vector signal processing
- and efficient control code processing
- • 128 8-bit macs, 64 16-bit macs, or 32 32-bit macs per cycle
- • Flexible vector permute operations
-
Imaging and Computer Vision Processor
- Superior performance
- Low power consumption
- Flexible and scalable
-
Intelligent Vision Processor
- Fully programmable in high level languages
- Scalar and Vector units to handle a mix of control and parallel code efficiently
-
High Performance Scalable Sensor Hub DSP Architecture
- Self contained, specialized sensor hub on-device processor
- Unifies multi-sensor processing with AI and sensor fusion
- Highy-configurable 8-way VLIW architecture
-
ISP, Image Signal Processing, Real-time Pixel Processor for Automotive
- Very low latency
- no frame-buffer
-
Unified Deep Learning Processor
- Unified deep learning/vision/video architecture enables flexibility
- Low power extends battery life and prevents overheating
- Single scalable architecture
-
Image Signal Procesing, Real-time Pixel Processor Automotive
- Very low latency
- no frame-buffer