The proceedings contain 52 papers. The topics discussed include: tumor detection using convolutional neural network on a lightweight multicore device;a STDM (static time division multiplexing) switch on a multi-FPGA s...
ISBN:
(纸本)9781728148823
The proceedings contain 52 papers. The topics discussed include: tumor detection using convolutional neural network on a lightweight multicore device;a STDM (static time division multiplexing) switch on a multi-FPGA system;modular memory system for RISC-V based MPSoCs on Xilinx FPGAs;low-cost congestion detection mechanism for networks-on-chip;implementation of content-based anonymization edge router on NetFPGA;and towards an efficient hardware architecture for odd-even based merge sorter.
The proceedings contain 49 papers. The topics discussed include: acceleration of full-PIC simulation on a CPU-FPGA tightly coupled environment;data and commands communication protocol for neuromorphic platform configu...
ISBN:
(纸本)9781509035304
The proceedings contain 49 papers. The topics discussed include: acceleration of full-PIC simulation on a CPU-FPGA tightly coupled environment;data and commands communication protocol for neuromorphic platform configuration;heuristic based routing algorithm for network on chip;2-step power scheduling with adaptive control interval for network intrusion detection systems on multicores;a data locality and memory contention analysis method in embedded NUMA multi-coresystems;time-triggered and rate-constrained on-chip communication in mixed-criticality systems;a Benes based NoC switching architecture for mixed criticality embeddedsystems;cReComp: automated design tool for ROS-compliant FPGA component;dynamic ring-based multicast with wavelength reuse for optical network on chips;a task allocation method for the DTTR scheme based on the parallelism of tasks;accelerating multicore architecture simulation using application profile;full-system simulation of *** multicore architecture for performance and energy exploration;communication-based power modelling for heterogeneous multiprocessor architectures;optimizing latencies and customizing NoC of time-predictable heterogeneous multi-core processor;dual-engine cross-ISA DBTO technique utilising multithreaded support for multicore processor system;and pushing the limits of online auto-tuning: machine code optimization in short-running kernels.
The proceedings contain 34 papers. The topics discussed include: an efficient parallel hardware scheme for solving the N-queens problem;simplified quadcopter simulation model for spike-based hardware PID controller us...
ISBN:
(纸本)9781538666890
The proceedings contain 34 papers. The topics discussed include: an efficient parallel hardware scheme for solving the N-queens problem;simplified quadcopter simulation model for spike-based hardware PID controller using systemC-AMS;unifying wire and time scheduling for high-level synthesis;on-chip lifetime prediction for dependable many-processor SoCs based on data fusion;design features of analog-to-digital solutions for the tracking detector readout electronics;Bluetooth low energy based indoor positioning on iOS platform;a practical high efficiency video coding solution for visual sensor network using raspberry Pi platform;adaptive long-term reference selection for efficient scalable surveillance video coding;light field image coding for efficient refocusing;and adaptive genetic algorithm for improving prediction accuracy of a multi-criteria recommender system.
The proceedings contain 58 papers. The topics discussed include: FPGA-based implementation of the stereo matching algorithm using high-level synthesis;accelerated on-chip algorithm based on semantic region-based parti...
ISBN:
(纸本)9781665438605
The proceedings contain 58 papers. The topics discussed include: FPGA-based implementation of the stereo matching algorithm using high-level synthesis;accelerated on-chip algorithm based on semantic region-based partial difference detection for LiDAR-vision depth data transmission reduction in lightweight controller systems of autonomous vehicle;acceleration of gravitation field analysis for asteroids by GPU computation;host bypassing: direct data piping from the network to the hardware accelerator;a function-rich FPGA system of camera image processing for video meeting;execution right delegation scheduling algorithm for multiprocessor;performance estimation of high-level dataflow program on heterogeneous platforms;multi-objective reinforcement learning for energy harvesting wireless sensor nodes;parasitic-aware modelling for neural networks implemented with memristor crossbar array;and surface type classification for autonomous robots using temporal, statistical and spectral feature extraction and selection.
The proceedings contain 86 papers. The topics discussed include: a scalable JPEG encoder on a many-core array;understanding the performance impact of queue-based resource allocation in scalable disaggregated memory sy...
ISBN:
(纸本)9798350393613
The proceedings contain 86 papers. The topics discussed include: a scalable JPEG encoder on a many-core array;understanding the performance impact of queue-based resource allocation in scalable disaggregated memory systems;a low-stall methodology for an interleaved processor state replication;low-cost low-power implementation of binary Edwards curve for secure passive RFID tags;IODnet: indoor/outdoor telecommunication signal detection through deep neural network;modelling and impact analysis of push back attack in 3D bufferless network on chip;patient similarity using electronic health records and self-supervised learning;and convolutional neural networks inference accelerator design using selective convolutional layer.
The proceedings contain 27 papers. The topics discussed include: improving memory access efficiency for heterogeneous multiprocessor systems;orthogonal instruction processing: an alternative to lightweight VLIW proces...
ISBN:
(纸本)9781538634417
The proceedings contain 27 papers. The topics discussed include: improving memory access efficiency for heterogeneous multiprocessor systems;orthogonal instruction processing: an alternative to lightweight VLIW processors;the design and implementation of scalable deep neural network accelerator cores;an efficient deadlock-free adaptive routing algorithm for 3D network-on-chips;thermal management in 3d homogeneous NOC systems using optimized placement of liquid microchannels;comparing synchronous, mesochronous and asynchronous NOCs for GALS based MPSOCs;a study of conflicting pairs of compiler optimizations;hypervisor-induced negative interference in virtualized multi-core platforms: the P4080 case;comparative study on edge detection algorithms using OpenACC and OpenMPI on multicoresystems;reliability and power optimization in 3d-stacked cache using a run-time reconfiguration procedure;enhanced long edge first routing algorithm and evaluation in large-scale networks-on-chip;run-time scalable NOC for FPGA based virtualized IPs;temporal partitioning in mixed-criticality NOCs using timely blocking;performance evaluation of tsunami simulation using OpenCL on GPU and FPGA;a computational model for improving the accuracy of multi-criteria recommender systems;real-time audio processing on the t-crest multicore platform;designing efficient parallel processing in 3d standard-chip stacking system with standard bus;and real-time UAV attitude heading reference system using extended Kalman filter for programmable soc.
The proceedings contain 85 papers. The topics discussed include: taxonomy of proactive detection methods of drunk driving for enhancing traffic safety;road surface extraction and object elimination for autonomous driv...
ISBN:
(纸本)9798331530471
The proceedings contain 85 papers. The topics discussed include: taxonomy of proactive detection methods of drunk driving for enhancing traffic safety;road surface extraction and object elimination for autonomous driving simulators based on neural radiance field;sustainable transportation solutions: advancements in compressed air vehicle technology;improving long text classification based on selective state space model (Mamba);times higher education rankings analysis for enhancing university performance using multi-criteria decision making;text self-supervision enhances visual-language learning for person re-identification;and theoretical analysis of the memory-efficient matrix storage method for quantum emulation accelerators with gate fusion on FPGAs.
The proceedings contain 58 papers. The topics discussed include: evaluating the optimal self-checking carry propagate adder for cryptographic processor;buffer allocation for exposed Datapath architectures;movie orient...
ISBN:
(纸本)9781665464994
The proceedings contain 58 papers. The topics discussed include: evaluating the optimal self-checking carry propagate adder for cryptographic processor;buffer allocation for exposed Datapath architectures;movie oriented positive negative emotion classification from EEG signal using wavelet transformation and machine learning approaches;design of reward functions for RL-based high-speed autonomous driving;a lightweight end-to-end network for wearing mask recognition on low-resolution images;automatic endometrial segmentation in ultrasound images using deep learning;fake image detection using an ensemble of CNN models specialized for individual face parts;exploring the potential of error-permissive communication in multi-FPGA-based edge computing;cluster based smart random walk for data aggregation in wireless sensor network;radar and camera fusion for object forecasting in driving scenarios;online image sensor fault detection for autonomous vehicles;and systolic array based convolutional neural network inference on FPGA.
The 2022 ieee 15 th internationalsymposium on embeddedmulticore/many-coresystemson-chip (MCSoC-2022) is an annual internationalsymposium favored by the Universiti Sains Malaysia (USM) and the Technical Committee ...
The 2022 ieee 15 th internationalsymposium on embeddedmulticore/many-coresystemson-chip (MCSoC-2022) is an annual internationalsymposium favored by the Universiti Sains Malaysia (USM) and the Technical Committee on Microprocessors and Micro-computers of the ieee Computer Society in cooperation with the ieee Singapore Section. MCSoC 2022 is hosted in Penang - a charming island in Malaysia - at Universiti Sains Malaysia (USM). There is growing confidence that future massively-parallel computer systems will be based on connectionist models and the innovative design of interconnection networks, processor architecture, applications, and software tools for embedded multi-coresystems-on-chip will play a crucial role in our understanding the future systems. Along with Industry 4.0, the Internet of Things, cloud computing, data-centric computing through the Internet along with artificial intelligence become more and more popular. Therefore, the required computing power is incredibly increasing every moment. The rise of artificial intelligence innovation in recent years is encountering efficiency of power, online adaptation, and architectural and design issues. This edition of MCSoC offers new tracks on artificial intelligence on-chip learning and neuromorphic computing together with nine tracks on SoC design and application to bring new and potent methods for design from devices to applications.
暂无评论