Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode

Abstract

The Internet-of-Things requires end-nodes with ultra-low-power always-on capability for a long battery lifetime, as well as high performance, energy efficiency, and extreme flexibility to deal with complex and fast-evolving near-sensor analytics algorithms (NSAAs). We present Vega, an IoT end-node SoC capable of scaling from a 1.7 $\mu$W fully retentive cognitive sleep mode up to 32.2 GOPS (@ 49.4 mW) peak performance on NSAAs, including mobile DNN inference, exploiting 1.6 MB of state-retentive SRAM, and 4 MB of non-volatile MRAM. To meet the performance and flexibility requirements of NSAAs, the SoC features 10 RISC-V cores: one core for SoC and IO management and a 9-cores cluster supporting multi-precision SIMD integer and floating-point computation. Vega achieves SoA-leading efficiency of 615 GOPS/W on 8-bit INT computation (boosted to 1.3TOPS/W for 8-bit DNN inference with hardware acceleration). On floating-point (FP) compuation, it achieves SoA-leading efficiency of 79 and 129 GFLOPS/W on 32- and 16-bit FP, respectively. Two programmable machine-learning (ML) accelerators boost energy efficiency in cognitive sleep and active states, respectively.

13 pages, 11 figures, 8 tables, journal paper

References in corpus (1)

• DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs

Cited by in corpus (14)

• A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms
• TinyVers: A Tiny Versatile System-on-chip with State-Retentive eMRAM for ML Inference at the Extreme Edge
• An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
• DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training
• Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasing
• Dustin: A 16-Cores Parallel Ultra-Low-Power Cluster with 2b-to-32b Fully Flexible Bit-Precision and Vector Lockstep Execution Mode
• NanoSLAM: Enabling Fully Onboard SLAM for Tiny Robots
• Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
• HULK-V: a Heterogeneous Ultra-low-power Linux capable RISC-V SoC
• A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference
• SPEED: A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference
• Parallelizing Optical Flow Estimation on an Ultra-Low Power RISC-V Cluster for Nano-UAV Navigation
• CVA6 RISC-V Virtualization: Architecture, Microarchitecture, and Design Space Exploration
• HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones