Built on our latest Xtensa NX architecture and offers up to 2.18TOPS of performance
The Cadence® Tensilica® Vision Q7 DSP delivers up to 2.18 tera operations per second (TOPS), 2.6X higher total TOPS compared to the Vision P6 DSP. To address the increasing computational requirements for embedded vision and AI applications, the sixth-generation Vision Q7 DSP provides up to 2X greater AI and floating-point performance compared to the Vision P6 DSP. The Vision Q7 DSP is specifically optimized for simultaneous localization and mapping (SLAM), a technique commonly used in the robotics, drone, mobile, and automotive markets to automatically construct or update a map of an unknown environment, and in the AR/VR market for inside-out tracking.
Tensilica Vision Q7 DSP
Overview
Key Features
- 1024/512b Load/Store capabilities
- 512 8-bit MAC: 2X MAC capability versus Vision P6 DSPs
- 8/16/32-bit fixed-point processing
- Double-precision (FP64), single-precision (FP32), and half-precision (FP16) floating-point processing
- Acceleration for simultaneous localization and mapping (SLAM)
- 4-channel iDMA
- User-defined instructions support
- Built on Xtensa® NX processor offering up to 1.5X frequency compared to Vision P6 DSP
- ISO 26262 ready for automotive market
Block Diagram
Applications
- Automotive,
- Communications,
- Consumer Electronics,
- Data Processing,
- Industrial and Medical,
- Military/Civil Aerospace,
- Others
Technical Specifications
Maturity
Available on request