2019 · 11 citations · 6 references
ComputingComputer EngineeringComputer ScienceArtificial IntelligenceAutonomous VehiclesComputer ArchitectureAccelerator ArchitectureAutomotive Embedded SystemsDeep LearningHardware AccelerationPattern RecognitionProcessor Core DesignAcceleratorsDeep Learning AccelerationMany-core ProcessorsMemory ArchitectureProcessor ArchitectureProgrammable AcceleratorsVehicle Control UnitsVoice Recognition
State-of-the-art neural network accelerators consist of arithmetic engines organized in a mesh structure datapath surrounded by memory blocks that provide neural data to the datapath. While server-based accelerators coupled with server-class processors are accommodated with large silicon area and consume large amounts of power, electronic control units in autonomous driving vehicles require power-optimized, ‘AI processors’ with a small footprint. An AI processor for mobile applications that integrates general-purpose processor cores with mesh-structured neural network accelerators and high speed memory while achieving high-performance with low-power and compact area constraints necessitates designing a novel AI processor architecture. We present the design of an AI processor for electronic systems in autonomous driving vehicles targeting not only CNN-based object recognition but also MLP-based in-vehicle voice recognition. The AI processor integrates Super-Thread-Cores (STC) for neural network acceleration with function-safe general purpose cores that satisfy vehicular electronics safety requirements. The STC is composed of 16384 programmable nano-cores organized in a mesh-grid structured datapath network. Designed based on thorough analysis of neural network computations, the nano-core-in-memory architecture enhances computation intensity of STC with efficient feeding of multi-dimensional activation and kernel data into the nano-cores. The quad function-safe general purpose cores ensure functional safety of Super-Thread-Core to comply with road vehicle safety standard ISO 26262. The AI processor exhibits 32 Tera FLOPS, enabling hyper real-time execution of CNN, RNN, and FCN.
6
In-Datacenter Performance Analysis of a Tensor Processing Unit
Norman P. Jouppi, Cliff Young, Nishant Patil et al. · 2017 · 4.4K citations
Angshuman Parashar, Minsoo Rhu, Anurag Mukkara et al. · 2017 · 927 citations
DaDianNao: A Neural Network Supercomputer
Tao Luo, Shaoli Liu, Ling Li et al. · IEEE Transactions on Computers · 2016 · 178 citations
Volta: Performance and Programmability
Jack Choquette, Olivier Giroux, Denis Foley · IEEE Micro · 2018 · 124 citations
Benchmarking SW26010 Many-Core Processor
Zhigeng Xu, James Lin, Satoshi Matsuoka · 2017 · 51 citations