skip to main content

Title: IMCE: Energy-efficient bit-wise in-memory convolution engine for deep neural network
In this paper, we pave a novel way towards the concept of bit-wise In-Memory Convolution Engine (IMCE) that could implement the dominant convolution computation of Deep Convolutional Neural Networks (CNN) within memory. IMCE employs parallel computational memory sub-array as a fundamental unit based on our proposed Spin Orbit Torque Magnetic Random Access Memory (SOT-MRAM) design. Then, we propose an accelerator system architecture based on IMCE to efficiently process low bit-width CNNs. This architecture can be leveraged to greatly reduce energy consumption dealing with convolutional layers and also accelerate CNN inference. The device to architecture co-simulation results show that the proposed system architecture can process low bit-width AlexNet on ImageNet data-set favorably with 785.25μJ/img, which consumes ~3× less energy than that of recent RRAM based counterpart. Besides, the chip area is ~4× smaller.
; ; ;
Award ID(s):
Publication Date:
Journal Name:
2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC)
Page Range or eLocation-ID:
111 to 116
Sponsoring Org:
National Science Foundation
More Like this
  1. Deep Convolution Neural Network (CNN) has achieved outstanding performance in image recognition over large scale dataset. However, pursuit of higher inference accuracy leads to CNN architecture with deeper layers and denser connections, which inevitably makes its hardware implementation demand more and more memory and computational resources. It can be interpreted as `CNN power and memory wall'. Recent research efforts have significantly reduced both model size and computational complexity by using low bit-width weights, activations and gradients, while keeping reasonably good accuracy. In this work, we present different emerging nonvolatile Magnetic Random Access Memory (MRAM) designs that could be leveraged to implement `bit-wise in-memory convolution engine', which could simultaneously store network parameters and compute low bit-width convolution. Such new computing model leverages the `in-memory computing' concept to accelerate CNN inference and reduce convolution energy consumption due to intrinsic logic-in-memory design and reduction of data communication.
  2. In this paper, we propose MRIMA, as a novel MRAM-based In-Memory Accelerator for non-volatile, flexible, and efficient in-memory computing. MRIMA transforms current Spin Transfer Torque Magnetic Random Access Memory (STT-MRAM) arrays to massively parallel computational units capable of working as both non-volatile memory and in-memory logic. Instead of integrating complex logic units in cost-sensitive memory, MRIMA exploits hardware-friendly bit-line computing methods to implement complete Boolean logic functions between operands within a memory array in a single clock cycle, overcoming the multi-cycle logic issue in contemporary Processing-In-Memory (PIM) platforms. We present practical case studies to demonstrate MRIMA’s acceleration for binary-weight and low bit-width Convolutional Neural Networks (CNN) as well as data encryption. Our device-to-architecture co-simulation results on CNN acceleration demonstrate that MRIMA can obtain 1.7× better energy-efficiency and 11.2× speed-up compared to ASICs, and, 1.8× better energy-efficiency and 2.4× speed-up over the best DRAM-based PIM solutions. As an AES in-memory encryption engine, MRIMA shows 77% and 21% lower energy consumption compared to CMOS-ASIC and recent domain wall-based design, respectively.
  3. Applications of neural networks have gained significant importance in embedded mobile devices and Internet of Things (IoT) nodes. In particular, convolutional neural networks have emerged as one of the most powerful techniques in computer vision, speech recognition, and AI applications that can improve the mobile user experience. However, satisfying all power and performance requirements of such low power devices is a significant challenge. Recent work has shown that binarizing a neural network can significantly improve the memory requirements of mobile devices at the cost of minor loss in accuracy. This paper proposes MB-CNN, a memristive accelerator for binary convolutional neural networks that perform XNOR convolution in-situ novel 2R memristive data blocks to improve power, performance, and memory requirements of embedded mobile devices. The proposed accelerator achieves at least 13.26 × , 5.91 × , and 3.18 × improvements in the system energy efficiency (computed by energy × delay) over the state-of-the-art software, GPU, and PIM architectures, respectively. The solution architecture which integrates CPU, GPU and MB-CNN outperforms every other configuration in terms of system energy and execution time.
  4. Deep convolutional neural network (DNN) has demonstrated phenomenal success and been widely used in many computer vision tasks. However, its enormous model size and high computing complexity prohibits its wide deployment into resource limited embedded system, such as FPGA and mGPU. As the two most widely adopted model compression techniques, weight pruning and quantization compress DNN model through introducing weight sparsity (i.e., forcing partial weights as zeros) and quantizing weights into limited bit-width values, respectively. Although there are works attempting to combine the weight pruning and quantization, we still observe disharmony between weight pruning and quantization, especially when more aggressive compression schemes (e.g., Structured pruning and low bit-width quantization) are used. In this work, taking FPGA as the test computing platform and Processing Elements (PE) as the basic parallel computing unit, we first propose a PE-wise structured pruning scheme, which introduces weight sparsification with considering of the architecture of PE. In addition, we integrate it with an optimized weight ternarization approach which quantizes weights into ternary values ({-1,0,+1}), thus converting the dominant convolution operations in DNN from multiplication-and-accumulation (MAC) to addition-only, as well as compressing the original model (from 32-bit floating point to 2-bit ternary representation) by at least 16more »times. Then, we investigate and solve the coexistence issue between PE-wise Structured pruning and ternarization, through proposing a Weight Penalty Clipping (WPC) technique with self-adapting threshold. Our experiment shows that the fusion of our proposed techniques can achieve the best state-of-the-art ∼21× PE-wise structured compression rate with merely 1.74%/0.94% (top-1/top-5) accuracy degradation of ResNet-18 on ImageNet dataset.« less
  5. In this paper, we propose a new dynamic reliability technique using an accuracy-reconfigurable stochastic computing (ARSC) framework for deep learning computing. Unlike the conventional stochastic computing that conducts design time accuracy power/energy trade-off, the new ARSC design can adjust the bit-width of the data in run time. Hence, the ARSC can mitigate the long-term aging effects by slowing the system clock frequency, while maintaining the inference throughput by reducing the data bit-width at a small cost of accuracy. We show how to implement the recently proposed counter-based SC multiplication and bit-width reduction on a layer-wise quantization scheme for CNN networks with dynamic fixed-point data. We validate an ARSC-based five-layer convolutional neural network designs for the MNIST dataset based on Vivado HLS with constraints from Xilinx Zynq-7000 family xc7z045 platform. Experimental results show that new ARSC DNN can sufficiently compensate the NBTI induced aging effects in 10 years with marginal classification accuracy loss while maintaining or even exceeding the pre-aging computing throughput. At the same time, the proposed ARSC computing framework also reduces the active power consumption due to the frequency scaling, which can further improve system reliability due to the reduced temperature.