» Current | 2020 | 2019 | 2018 | Subscribe

Linley Newsletter

DSP-IP Vendors Target 3D Navigation

June 11, 2019

Author: Mike Demler

Technologies that capture and create 3D environmental models are critical to augmented reality (AR), autonomous vehicles, drones, industrial robots, and other systems. But these systems must also navigate through the real or virtual worlds. Simultaneous localization and mapping (SLAM) addresses this problem by fusing camera and sensor data to create a 3D map, establishing the user’s (or machine’s) point of view, and precisely tracking its trajectory through the photorealistic space. SLAM software traditionally runs on CPUs and GPUs, but intellectual-property (IP) vendors Cadence and Ceva have recently introduced more-efficient solutions that employ their DSP cores.

For its SLAM solution, Cadence developed the new Vision Q7 DSP, which implements hardware and instruction-set features designed specifically to accelerate the complex linear algebra and matrix-math operations that SLAM algorithms employ. Despite adding new hardware, the Q7 consumes roughly the same area as its predecessor, the Vision Q6. The company says that by reoptimizing the Xtensa-processor pipeline it introduced in the Q6, it saved enough area to compensate for the additional MAC units and FPUs.

Ceva says its DSP cores already have those capabilities, so it’s offering a new SLAM SDK that programmers can use with the DSP cores in its XM-series and NeuPro deep-learning accelerators (DLAs). Production RTL for the Cadence Vision Q7 is available for general licensing, as are the XM and NeuPro cores and the Ceva SLAM SDK.

Subscribers can view the full article in the Microprocessor Report.

Subscribe to the Microprocessor Report and always get the full story!

Purchase the full article


Linley Spring Processor Conference 2020
Coming April 7-8, 2020
Hyatt Regency, Santa Clara, CA
Register Now!
Linley Fall Processor Conference 2020
Coming October 28-29, 2020
Hyatt Regency, Santa Clara, CA
More Events »


Linley Newsletter
Analysis of new developments in microprocessors and other semiconductor products
Subscribe to our Newsletter »