Energy-Efficient Convolutional Neural Networks via Recurrent Data Reuse

Mocerino, Luca; Tenace, Valerio; Calimera, Andrea

doi:10.23919/date.2019.8714880

Cited by 8 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in [21] we proposed a hardware-software co-design flow to implement a fully-CMOS processing element that integrates an SRAM-based CAM into a standard FPU. The design is enabled by a clustering procedure aimed at boosting the intrinsic reuse opportunity.…”

Section: Convnets Approximation Via Arithmetic Approximation and Data-reusementioning

confidence: 99%

“…Experimental results have shown that achieving high accuracy may call for large memory configurations, because of the high number of centroids needed and/or the high number of input activations to be stored, reducing the energy savings achievable. Borrowing the original idea proposed in [21], this work makes a step further introducing the use of approximate matching for associative-based ConvNet processing.…”

Section: Convnets Approximation Via Arithmetic Approximation and Data-reusementioning

confidence: 99%

“…Concerning prior arts, the first analysis we conducted aims at showing the improvements brought by our new framework when compared to our preliminary work [21] (gray dashed line in Figure 11). The energy efficiency increases up to 37.06% for OR, 9.42% for IC, and 32.79% for KS for FP32 data path, while for FP16 data path it is possible to save up to 13.37% for OR, 17.92% for IC, and 14.42 for KS from a strict to more relaxed accuracy constraint.…”

Section: Energy-accuracy Trade-off and Comparison With Previous Workmentioning

confidence: 99%

“…This work does focus on these aspects introducing a practical alternative to enhance data reuse via approximate associative matching and standard CMOS circuits. Specifically, we propose a hardware-software co-design pipeline consisting of a suite of automatic tools that implement a multi-stage approximation and generate ConvNet models able to maximize the reuse mechanism implemented through a memory-enhanced processing element (PE) borrowed from our preliminary work [21]. Similar input patterns are merged via clustering at first, then a bit-wise approximate matching is implemented in such a way that the associative memory utilization is maximized.…”

Section: Introductionmentioning

confidence: 99%

“…Each column (and color) represents a different benchmark, from left to right: OR, IC and KS. The current approach is compared to our preliminary work[21] (grey dashed lines). (a) OR; (b) IC; (c) KS.…”

mentioning

confidence: 99%

See 4 more Smart Citations

AxP: A HW-SW Co-Design Pipeline for Energy-Efficient Approximated ConvNets via Associative Matching

Mocerino

Calimera

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The reduction in energy consumption is key for deep neural networks (DNNs) to ensure usability and reliability, whether they are deployed on low-power end-nodes with limited resources or high-performance platforms that serve large pools of users. Leveraging the over-parametrization shown by many DNN models, convolutional neural networks (ConvNets) in particular, energy efficiency can be improved substantially preserving the model accuracy. The solution proposed in this work exploits the intrinsic redundancy of ConvNets to maximize the reuse of partial arithmetic results during the inference stages. Specifically, the weight-set of a given ConvNet is discretized through a clustering procedure such that the largest possible number of inner multiplications fall into predefined bins; this allows an off-line computation of the most frequent results, which in turn can be stored locally and retrieved when needed during the forward pass. Such a reuse mechanism leads to remarkable energy savings with the aid of a custom processing element (PE) that integrates an associative memory with a standard floating-point unit (FPU). Moreover, the adoption of an approximate associative rule based on a partial bit-match increases the hit rate over the pre-computed results, maximizing the energy reduction even further. Results collected on a set of ConvNets trained for computer vision and speech processing tasks reveal that the proposed associative-based hw-sw co-design achieves up to 77% in energy savings with less than 1% in accuracy loss.

show abstract

Section: Convnets Approximation Via Arithmetic Approximation and Data-reusementioning

confidence: 99%

Section: Convnets Approximation Via Arithmetic Approximation and Data-reusementioning

confidence: 99%

Section: Energy-accuracy Trade-off and Comparison With Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

AxP: A HW-SW Co-Design Pipeline for Energy-Efficient Approximated ConvNets via Associative Matching

Mocerino

Calimera

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks

Mocerino

Calimera

2020

2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

Self Cite

View full text Add to dashboard Cite

Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a new template designed to improve the predictive performance of binarized CNNs via parallelization. Inspired by the ensemble learning theory, it consists of a compact topology that is end-to-end trainable and organized to minimize memory utilization. Experimental results collected over three realistic benchmarks show TentacleNet fills the gap left by classical binary models, ensuring substantial memory savings w.r.t. state-of-the-art binary ensemble methods.

show abstract

ADC-PIM: Accelerating Convolution on the GPU via In-Memory Approximate Data Comparison

Choi

Lee

Rhee

2022

IEEE J. Emerg. Sel. Topics Circuits Syst.

View full text Add to dashboard Cite

Energy-Efficient Convolutional Neural Networks via Recurrent Data Reuse

Cited by 8 publications

References 14 publications

AxP: A HW-SW Co-Design Pipeline for Energy-Efficient Approximated ConvNets via Associative Matching

AxP: A HW-SW Co-Design Pipeline for Energy-Efficient Approximated ConvNets via Associative Matching

TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks

ADC-PIM: Accelerating Convolution on the GPU via In-Memory Approximate Data Comparison

Contact Info

Product

Resources

About