Publication | Closed Access
BRein memory: A 13-layer 4.2 K neuron/0.8 M synapse binary/ternary reconfigurable in-memory deep neural network accelerator in 65 nm CMOS
82
Citations
0
References
2017
Year
Unknown Venue
EngineeringNeural Networks (Machine Learning)Nm CmosComputer ArchitectureNeurochipSocial Sciences13-Layer 4.2Computing SystemsNeuromorphic EngineeringParallel ComputingNeurocomputersVersatile Reconfigurable AcceleratorBinary/ternary DnnsComputer EngineeringNeural Networks (Computational Neuroscience)Computer ScienceReconfigurable ArchitectureDeep LearningTops ChipHardware AccelerationDomain-specific AcceleratorBrein MemoryBrain-like Computing
A versatile reconfigurable accelerator for binary/ternary deep neural networks (DNNs) is presented. It features a massively parallel in-memory processing architecture and stores varieties of binary/ternary DNNs with a maximum of 13 layers, 4.2 K neurons, and 0.8 M synapses on chip. The 0.6 W, 1.4 TOPS chip achieves performance and energy efficiency that is 10–10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> –10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> times better than a CPU/GPU/FPGA.