AMAIX: A Generic Analytical Model for Deep Learning Accelerators

Jünger, Lukas; Zurstraßen, Niko; Kogel, Tim; Keding, Holger; Leupers, Rainer

doi:10.1007/978-3-030-60939-9_3

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, based on analytical performance models derived from these papers [7,8], we decided 3 × 3 kernel size is the representative kernel for convolution kernels for AlexNet and VGG16 [9][10][11]. Custom instructions for 3 × 3 convolution, MAC, and 2 × 2 max pooling are examined, and high-level descriptions for the proposed experiments are described in the following sections.…”

Section: Configurable Processor Limit Studymentioning

confidence: 99%

Extensible Embedded Processor for Convolutional Neural Networks

Misko

Jadhav

Kim

2021

Scientific Programming

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) require significant computing power during inference. Smart phones, for example, may not run a facial recognition system or search algorithm smoothly due to the lack of resources and supporting hardware. Methods for reducing memory size and increasing execution speed have been explored, but choosing effective techniques for an application requires extensive knowledge of the network architecture. This paper proposes a general approach to preparing a compressed deep neural network processor for inference with minimal additions to existing microprocessor hardware. To show the benefits to the proposed approach, an example CNN for synthetic aperture radar target classification is modified and complimentary custom processor instructions are designed. The modified CNN is examined to show the effects of the modifications and the custom processor instructions are profiled to illustrate the potential performance increase from the new extended instructions.

show abstract

Section: Configurable Processor Limit Studymentioning

confidence: 99%

Extensible Embedded Processor for Convolutional Neural Networks

Misko

Jadhav

Kim

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

Virtual Prototyping of Processor-Based Platforms

Kogel

2022

Handbook of Computer Architecture

View full text Add to dashboard Cite

AMAIX In-Depth: A Generic Analytical Model for Deep Learning Accelerators

Zurstraßen

Jünger

Kogel

et al. 2022

Int J Parallel Prog

View full text Add to dashboard Cite

In recent years the growing popularity of Convolutional Neural Network(CNNs) has driven the development of specialized hardware, so called Deep Learning Accelerator (DLAs). The large market for DLAs and the huge amount of papers published on DLA design show that there is currently no one-size-fits-all solution. Depending on the given optimization goals such as power consumption or performance, there may be several optimal solutions for each scenario. A commonly used method for finding these solutions as early as possible in the design cycle, is the employment of analytical models which try to describe a design by simple yet insightful and sufficiently accurate formulas. The main contribution of this work is the generic Analytical Model for AI accelerators (AMAIX) for the estimation of CNN execution time on DLAs. It is based on the popular Roofline model. To show the validity of our approach, AMAIX was applied to the Nvidia Deep Learning Accelerator (NVDLA) as a case study using the AlexNet and LeNet CNNs as workloads. The resulting performance predictions were verified against an RTL emulation of the NVDLA using a Synopsys ZeBu Server-based hybrid prototype. By refining the model following a divide-and-conquer paradigm, AMAIX predicted the inference time of AlexNet and LeNet on the NVDLA with an accuracy 98%. Furthermore, this work shows how to use the obtained results for root-cause analysis and as a starting point for design space exploration.

show abstract

AMAIX: A Generic Analytical Model for Deep Learning Accelerators

Cited by 4 publications

References 7 publications

Extensible Embedded Processor for Convolutional Neural Networks

Extensible Embedded Processor for Convolutional Neural Networks

Virtual Prototyping of Processor-Based Platforms

AMAIX In-Depth: A Generic Analytical Model for Deep Learning Accelerators

Contact Info

Product

Resources

About