Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory

This paper presents a programmable and scalable digital neuromorphic architecture based on 3D high-density memory integrated with logic tier for efficient neural computing. The proposed architecture consists of clusters of processing engines, connected by 2D mesh network as a processing tier, which is integrated in 3D with multiple tiers of DRAM. The PE clusters access multiple memory channels (vaults) in parallel. The operating principle, referred to as the memory centric computing, embeds specialized state-machines within the vault controllers of HMC to drive data into the PE clusters. The paper presents the basic architecture of the Neurocube and an analysis of the logic tier synthesized in 28nm and 15nm process technologies. The performance of the Neurocube is evaluated and illustrated through the mapping of a Convolutional Neural Network and estimating the subsequent power and performance for both training and inference.

[1]  Sudhakar Yalamanchili,et al.  Energy Introspector: A parallel, composable framework for integrated power-reliability-thermal modeling for multicore architectures , 2014, 2014 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

[2]  Yann LeCun,et al.  CNP: An FPGA-based processor for Convolutional Networks , 2009, 2009 International Conference on Field Programmable Logic and Applications.

[3]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[4]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[5]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[6]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[7]  Zheng Guo,et al.  17.1 A 0.6V 1.5GHz 84Mb SRAM design in 14nm FinFET CMOS technology , 2015, 2015 IEEE International Solid-State Circuits Conference - (ISSCC) Digest of Technical Papers.

[8]  Berin Martini,et al.  NeuFlow: A runtime reconfigurable dataflow processor for vision , 2011, CVPR 2011 WORKSHOPS.

[9]  Berin Martini,et al.  A 240 G-ops/s Mobile Coprocessor for Deep Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Umut Arslan,et al.  13.1 A 1Gb 2GHz embedded DRAM in 22nm tri-gate CMOS technology , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[11]  Jia Wang,et al.  DaDianNao: A Machine-Learning Supercomputer , 2014, 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture.

[12]  Kiyoung Choi,et al.  A scalable processing-in-memory accelerator for parallel graph processing , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[13]  Michele Magno,et al.  Accelerating real-time embedded scene labeling with convolutional networks , 2015, 2015 52nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[14]  Ivo D. Dinov,et al.  Deep learning for neural networks , 2018 .

[15]  L.O. Chua,et al.  Cellular neural networks , 1993, 1988., IEEE International Symposium on Circuits and Systems.

[16]  J. Jeddeloh,et al.  Hybrid memory cube new DRAM architecture increases density and performance , 2012, 2012 Symposium on VLSI Technology (VLSIT).

[17]  Jaejin Lee,et al.  25.2 A 1.2V 8Gb 8-channel 128GB/s high-bandwidth memory (HBM) stacked DRAM with effective microbump I/O test methods using 29nm process and TSV , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[18]  Yuan Xie,et al.  Optimizing GPU energy efficiency with 3D die-stacking graphics memory and reconfigurable memory interface , 2013, TACO.

[19]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[20]  Paul Rosenfeld,et al.  Performance Exploration of the Hybrid Memory Cube , 2014 .

[21]  David Atienza,et al.  3D-ICE: A Compact Thermal Model for Early-Stage Design of Liquid-Cooled ICs , 2014, IEEE Transactions on Computers.

[22]  Kiyoung Choi,et al.  PIM-enabled instructions: A low-overhead, locality-aware processing-in-memory architecture , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[23]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[24]  Christoforos E. Kozyrakis,et al.  Towards energy-proportional datacenter memory with mobile DRAM , 2012, 2012 39th Annual International Symposium on Computer Architecture (ISCA).

[25]  Stephen Gould,et al.  Decomposing a scene into geometric and semantically consistent regions , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[26]  Luca Benini,et al.  Origami: A Convolutional Network Accelerator , 2015, ACM Great Lakes Symposium on VLSI.

[27]  Luca Benini,et al.  High performance AXI-4.0 based interconnect for extensible smart memory cubes , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[28]  Luca Benini,et al.  A ultra-low-energy convolution engine for fast brain-inspired vision in multicore clusters , 2015, 2015 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[29]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[30]  G. Miller.  Learning to Forget , 2004, Science.