Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators
- URL: http://arxiv.org/abs/2404.05368v1
- Date: Mon, 8 Apr 2024 10:10:30 GMT
- Title: Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators
- Authors: Jan Klhufek, Miroslav Safar, Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina,
- Abstract summary: Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors.
We show that enabling rich mixed quantization schemes during the implementation can open a previously hidden space of mappings.
CNNs utilizing quantized weights and activations and suitable mappings can significantly improve trade-offs among the accuracy, energy, and memory requirements.
- Score: 0.20971479389679332
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e., placement and scheduling of DNN elementary operations on hardware units of the accelerator). We show that enabling rich mixed quantization schemes during the implementation can open a previously hidden space of mappings that utilize the hardware resources more effectively. CNNs utilizing quantized weights and activations and suitable mappings can significantly improve trade-offs among the accuracy, energy, and memory requirements compared to less carefully optimized CNN implementations. To find, analyze, and exploit these mappings, we: (i) extend a general-purpose state-of-the-art mapping tool (Timeloop) to support mixed quantization, which is not currently available; (ii) propose an efficient multi-objective optimization algorithm to find the most suitable bit-widths and mapping for each DNN layer executed on the accelerator; and (iii) conduct a detailed experimental evaluation to validate the proposed method. On two CNNs (MobileNetV1 and MobileNetV2) and two accelerators (Eyeriss and Simba) we show that for a given quality metric (such as the accuracy on ImageNet), energy savings are up to 37% without any accuracy drop.
Related papers
- EPIM: Efficient Processing-In-Memory Accelerators based on Epitome [78.79382890789607]
We introduce the Epitome, a lightweight neural operator offering convolution-like functionality.
On the software side, we evaluate epitomes' latency and energy on PIM accelerators.
We introduce a PIM-aware layer-wise design method to enhance their hardware efficiency.
arXiv Detail & Related papers (2023-11-12T17:56:39Z) - Precision-aware Latency and Energy Balancing on Multi-Accelerator
Platforms for DNN Inference [22.9834921448069]
We propose ODiMO, a hardware-aware tool that performs a fine-grain mapping across different accelerators on-chip.
We show that ODiMO reduces energy/latency by up to 33%/31% with limited accuracy drop (-0.53%/-0.32%) compared to manual mappings.
arXiv Detail & Related papers (2023-06-08T09:23:46Z) - Energy Efficient Hardware Acceleration of Neural Networks with
Power-of-Two Quantisation [0.0]
We show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 FPGA can be at least $1.4x$ more energy efficient than the uniform quantisation version.
arXiv Detail & Related papers (2022-09-30T06:33:40Z) - Edge Inference with Fully Differentiable Quantized Mixed Precision
Neural Networks [1.131071436917293]
Quantizing parameters and operations to lower bit-precision offers substantial memory and energy savings for neural network inference.
This paper proposes a new quantization approach for mixed precision convolutional neural networks (CNNs) targeting edge-computing.
arXiv Detail & Related papers (2022-06-15T18:11:37Z) - FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task.
The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources.
It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
arXiv Detail & Related papers (2022-01-18T13:59:22Z) - Quantized Neural Networks via {-1, +1} Encoding Decomposition and
Acceleration [83.84684675841167]
We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks.
We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
arXiv Detail & Related papers (2021-06-18T03:11:15Z) - Binary Graph Neural Networks [69.51765073772226]
Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data.
In this paper, we present and evaluate different strategies for the binarization of graph neural networks.
We show that through careful design of the models, and control of the training process, binary graph neural networks can be trained at only a moderate cost in accuracy on challenging benchmarks.
arXiv Detail & Related papers (2020-12-31T18:48:58Z) - Optimisation of a Siamese Neural Network for Real-Time Energy Efficient
Object Tracking [0.0]
optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented.
It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream.
arXiv Detail & Related papers (2020-07-01T13:49:56Z) - APQ: Joint Search for Network Architecture, Pruning and Quantization
Policy [49.3037538647714]
We present APQ for efficient deep learning inference on resource-constrained hardware.
Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner.
With the same accuracy, APQ reduces the latency/energy by 2x/1.3x over MobileNetV2+HAQ.
arXiv Detail & Related papers (2020-06-15T16:09:17Z) - Switchable Precision Neural Networks [35.2752928147013]
Switchable Precision neural Networks (SP-Nets) are proposed to train a shared network capable of operating at multiple quantization levels.
At runtime, the network can adjust its precision on the fly according to instant memory, latency, power consumption and accuracy demands.
arXiv Detail & Related papers (2020-02-07T14:43:44Z) - Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques.
We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
arXiv Detail & Related papers (2020-02-03T04:11:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.