CHAMELEON - µLP SoC chassis IP platform
Open, user-configurable IP platform
supporting CPUs from any vendor
Scalable AMBA-based chassis enabling maximum
energy-efficiency for SoCs in days
Technology for better future
Moving data and decision to the cloud led the whole industry to a new power and time-consuming challenge: the data deluge.
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.
Benefits are multiples:
- Faster response time
- No need for constant connectivity
- Higher data privacy
- Longer battery lifetime
The stake is to select cost-effective solutions enabling to reduce drastically the power consumption of such local decisions.
HERE COMES CHAMELEON MCU SUB-SYSTEM
Event-Based MCU Sub-system
CHAMELEON is a flexible & pre-verified event-based MCU sub-system platform embedding several standard peripherals, an autonomous DMA, a fined-grained power management unit, a tiny ML accelerator, a low latency interconnect, and an event manager.
It allows fast and efficient CPU-less data collection & filtering, enabling extremely low power consumption in both deep sleep and active modes.
CHAMELEON is preinstanciated for Cortex M and can be configured for other cores.
It is fully interoperable with our SPIDER power management platform.
The platform comes with an RTL configurator tool and all necessary drivers.
BRING DIFFERENTIATION TO YOUR CHIP ON YOUR TARGETED MARKET
ULTIMATE ENERGY EFFICIENCY
- Autonomous ULP data collection for IoT devices
- Highly energy efficient data processing for endpoint AI devices
Download our white paper “At the heart 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.
- The need for more and more edge processing capability
- Limitations of current MCU solutions
- What needs to be changed
- Dolphin Design SPEED MCU subsystem and computing platform offer
- Example of audio applications
BRAIN CONFIGURATION OF CHAMELEON
SECURE YOUR SILICON
Specific configuration for your application
Chameleon is designed to fit your application requirements. Each configuration are created by our expert SoC architects to provide you with the main features to optimize the energy efficiency of your MCU sub-system to reach your performance targets.
- Preinstanciated CortexM
- Flexible interconnect
- Debug architecture
- Event & IRQ management
- Choice of peripherals, with specific optimizations: timers, watchdog, SPI, UART, I2C, GPIO
BE EFFICIENT, ADOPT CHAMELEON
EXAMPLE: SMART CONFIGURATION
Event-based, ultra-low Power MCU fabric, dedicated to:
- Smart Sensors
- Smart TWS – Speakers
- Wearables & low-power intelligent IoT devices
PLUG & PLAY SUBSYSTEM
AI TOOL CHAIN - TensorFlowLite
- RTL design views
- RTL design FPGA views
- UPF description backbone
- Acceptance testbench
- Top level integration tests
- User manual
- Release note
- CMSIS Low Level HW Drivers
- Dolphin Design specific HAL drivers
- Reference to compilation toolchain
- Reference to Debug and Programming tools
Virtual Platform (On demand)
TLM design view to enable early eSW development and integration
SINGLE & DUAL CORE CORTEX M4F & M0+