MODEL OF AUTOMATED SYNTHESIS TOOL FOR HARDWARE ACCELERATORS OF CONVOLUTIONAL NEURAL NETWORKS FORPROGRAMMABLE LOGIC DEVICES
Annotation
Currently, more and more tasks on image processing and analysis are being solved using convolutional neural networks. Neural networks implemented using high-level programming languages, libraries and frameworks cannot be used in real-time systems, for example, for processing streaming video in cars, due to the low speed and energy efficiency of such implementations. The application of specialized hardware accelerators of neural networks is necessary for these tasks. The design of such accelerators is a complex iterative process requiring highly specialized knowledge and qualification. This consideration makes the creation of automation tools for high-level synthesis of such computers a relevant issue. The purpose of this research is a tool development for the automated synthesis of neural network accelerators from a high-level specification for programmable logic devices (FPGAs), which reduces the development time. A description of networks is used as a high-level specification, which can be obtained using the TensorFlow framework. The several strategies have been researched for optimizing the structure of convolutional networks, methods for organizing the computational process and formats for representing data in neural networks and their effect on the characteristics of the resulting computer. It was shown that structure optimization of neural network fully connected layers on the example of solving the handwritten digit recognition problem from the MNIST set reduces the number of network parameters by 95 % with a loss of accuracy equal to 0.43 %, pipelining of calculations speeds up the calculation by 1.7 times, and parallelization of the computing process individual parts provides the acceleration by almost 20 times, although it requires 4-6 times more FPGA resources. Applying of fixed-point numbers instead of floating-point numbers in calculations reduces the used FPGA resources by 1.7–2.8 times. The analysis of the obtained results is carried out and a model of an automated synthesis tool is proposed, which performs the indicated optimizations in automatic mode in order to meet the requirements for speed and resources used in the implementation of neural network accelerators on FPGA.
Keywords
Постоянный URL
Articles in current issue
- READER’S NOTE
- BLOCKCHAIN TECHNOLOGY IN 5G NETWORKS
- LASER HEATING NUMERICAL SIMULATION OF TITANIUM-CONTAINING OPTOTHERMAL FIBER CONVERTER AND VEIN WALL DURING ENDOVASALLASER COAGULATION
- EXPERIMENTAL STUDY OF OPTICAL POWER EFFECT ON THE STRUCTURE OF FIBER-OPTICAL DIFFUSER OBTAINED BY FIBER CORE MELTING
- METHODS OF HOT WIRE CREATION FOR FIBER-OPTICAL THERMAL ANEMOMETER
- EFFECT OF EXTERNAL RELATIVE PRESSURE ON PHASE SHIFT IN SAGNAC INTERFEROMETER
- ABSORPTION CHARACTERISTICS OF SILVER ION-EXCHANGED LAYERS IN CHLORIDE PHOTO-THERMO-REFRACTIVE GLASS
- ERBIUM SPECTRAL-LUMINESCENT CHARACTERISTICS IN BROMIDE-FLUORIDE PHOTO-THERMO-REFRACTIVE GLASSES
- AUTOMATED HANDDETECTION METHOD FOR TASKS OF GESTURE RECOGNITION IN HUMAN-MACHINE INTERFACES
- MODERN APPROACHES TO MULTICLASS INTENT CLASSIFICATION BASED ON PRE-TRAINED TRANSFORMERS
- EFFECTIVE IMPLEMENTATION OF MODERN MCELIECE CRYPTOSYSTEM ON GENERALIZED (L,G)-CODES
- NORMALIZATION OF KAZAKH LANGUAGE WORDS
- IMAGE-BASED DEFECT ANALYSIS FOR 3D-PRINTED ITEM SURFACE USING MACHINE LEARNING METHODS
- PACKET RESERVATIONS IN REAL-TIME MULTIPATH TRANSMISSIONS
- MODULAR APPROACH APPLICATION IN DEVELOPMENT OF COMPUTER NUMERICAL CONTROL SOFTWARE
- PARAMETRIC IDENTIFICATION OF DIFFERENTIAL-DIFFERENCE MODELS OF HEAT TRANSFER IN ONE-DIMENSIONAL BODIES BASED ON KALMAN FILTER ALGORITHMS
- SELECTION OF COMPOSITE MATERIAL IN ELECTROMAGNETIC LOG SENSOR
- MODELING OF LIQUEFIED NATURAL GAS EVAPORATION IN MOBILE RESERVOIRS
- MATHEMATICAL MODEL OF LIQUEFIED NATURAL GAS EVAPORATION AND ANALYSIS OF ORIGINAL COMPOSITION EFFECT ON EVAPORATION SPEED
- MESHLESS MODELING OF ELASTIC DEFORMATIONS OF POLYMERIC COMPOSITE MATERIALS UNDER STATIC LOADING
ACCURACY INCREASE OF SOFTWARE AND HARDWARE APPLIANCE FOR MUSCLE ACTIVITY MEASURING AND MONITORING BY FILTRATION OF CARRIER COMPONENT AND FREQUENCIES HIGHER THAN MEASURED SIGNAL RANGE