PANTHER - DSP Digital Signal Processor Platform

Parallel & versatile processing for greater Energy-Efficiency
& SoC flexibility

Technology for better future

The solution to deal with data deluge, while preventing the increase of power consumed by data centers, is known as Edge AI. This solution consists in transferring most of the processing intelligence from the cloud to the sensor. It translates into an unprecedented need to increase performances of «smart devices» by a factor of 1,000 at constant energy consumption.

With our SPEED IP platform, we are positioned as THE provider of solutions for Edge AI System-on-Chip designers. We enable our customers to do much more with less energy resulting in major benefits on environment.

PANTHER DSP Platform

PANTHER is scalable multi-core Digital Signal Processor IP Platform capable to efficiently run typical signal processing tasks as well as Artificial Intelligence and Machine Learning algorithms.

PANTHER relies on popular RISC-V instruction set and leverages a rich software ecosystem. Configurable from 4 to 16 parallel cores that rely on an advanced memory interconnect, PANTHER combines ultimate throughput efficiency with optimal silicon area to fit ideally with each SoC requirement.

Software execution on its parallel architecture is streamlined through the delivery of dedicated libraries together with a complete software development kit.

Applications

  • Vision: image classification, person detection, gesture recognition
  • Audio: keyword spotting, audio scene classification
  • Industry: preventive maintenance
  • Smart home/city: metering, counting, detection

Key figures

  • Up to 64MAC/Cycle (Configuration 16c – 8b Integer)​
  • 2TOPs/W running mobilenet V1 @200 Frames/s​
  • KWS @ 3x less power than state-of-the art competition​
  • Small footprint: 0.63mm2 for 4 cores​ @ 500 GOPS.
  • >80% parallelism achieved​ ​

PANTHER is a highly parallelizable multicore architecture for Digital Signal Processing

PARALLEL TASKS HANDLING
Its parallel architecture makes it very efficient to handle multi-threaded algorithms such as the ones used in modern DSP and AI/ML applications.

PARALLEL EFFICIENCY
Thanks to the Sync Unit and its highly parallel multicore architecture, PANTHER helps solving the software flexibility and energy efficiency quandary.

MACHINE LEARNING
Additionally to typical floating point and scalar operations, PANTHER has been enhanced with dedicated AI instructions to handle efficiently ML tasks and algorithms.

COMPLETE SDK
PANTHER comes with a complete toolchain running the most popular AI environments as well as a SDK with Dolphin Design’s specific HAL drivers and documentation package.

Key benefits

  • Hardware scalability ​
  • Highly parallelized for best power efficiency​
  • Power optimization based on runtime workload​
  • DSP software versatility and specialized accelerator energy efficiency at once​
  • Software API for seamless programming​
  • AI Toolchain for NN model deployment​
  • Established RISC V architecture​ ecosystem

Key features

  • Configurable RISC V multicore platform from 4 to 16 cores​
  • Embedded DMA for background data transfer​
  • Inter-core synchronization unit
  • ​Individual core power management​
  • SIMD and floating point instruction support​
  • Proprietary AI/ML instruction extension​
  • Efficient programming framework with tools and libraries​​ ​

pdf

Download our white paper “At the edge of data processing”

In order to implement efficient data processing solutions at the edge, MCU architectures need to be modified.
Firstly, an efficient fine-grained data power network needs to be implemented, optimizing not only leakage, but also dynamic power.
Then a new sensor-centric approach must be implemented, to avoid involving the CPU in all events in the case of large data collection.

  1. The need for more and more edge processing capability
  2. Limitations of current MCU solutions
  3. What needs to be changed
  4. Dolphin Design SPEED MCU subsystem and computing platform offer
  5. Benchmarks
  6. Example of audio applications
  7. Take-away

Looking for an AIoT systems to address energy efficiency challenges

Need to discuss about your project?