The proceedings contain 21 papers. The topics discussed include: SWARAM: portable energy and cost efficient embedded system for genomic processing;authcropper: authenticated image cropper for privacy preserving survei...
ISBN:
(纸本)9781450369237
The proceedings contain 21 papers. The topics discussed include: SWARAM: portable energy and cost efficient embedded system for genomic processing;authcropper: authenticated image cropper for privacy preserving surveillance systems;optode design space exploration for clinically-robust non-invasive fetal oximetry;PredictNcool: leakage aware thermal management for 3D memories using a lightweight temperature predictor;enabling sequential-write-constrained b+-tree index scheme to upgrade shingled magnetic recording storage performance;achieving super-linear speedup across multi-FPGA for real-time DNN inference;and achieving lossless accuracy with lossy programming for efficient neural-network training on NVM-based systems.
The proceedings contain 11 papers. The topics discussed include: work-in-progress: what to expect of early training statistics? an investigation on hardware-aware neural architecture search;work-in-progress: high-perf...
ISBN:
(纸本)9781665472944
The proceedings contain 11 papers. The topics discussed include: work-in-progress: what to expect of early training statistics? an investigation on hardware-aware neural architecture search;work-in-progress: high-performance systolic hardware accelerator for RBLWE-based post-quantum cryptography;work-in-progress: BloCirNN: an efficient software/hardwarecodesign approach for neural network accelerators with block-circulant matrix;work-in-progress: HeteroRW: a generalized and efficient framework for random walks in graph analysis;work-in-progress: lark: a learned secondary index toward LSM-tree for resource-constrained embedded storage systems;work-in-progress: toward energy-efficient near STT-MRAM processing architecture for neural networks;work-in-progress: utilizing latency and accuracy predictors for efficient hardware-aware NAS;industry-track: towards agile design of neural processing unit;and industry paper: surrogate models for testing analog designs under limited budget – a bandgap case study.
The proceedings contain 16 papers. The topics discussed include: meta-chain: user-aware cross-layer space allocation strategy for blockchain storage systems: work-in-progress;heatmap-aware low-cost design to resist ad...
ISBN:
(纸本)9781728191980
The proceedings contain 16 papers. The topics discussed include: meta-chain: user-aware cross-layer space allocation strategy for blockchain storage systems: work-in-progress;heatmap-aware low-cost design to resist adversarial attacks: work-in-progress;layering the monitoring action for improved flexibility and overhead control: work-in-progress;a new hardware Trojan design: distinguishing between trigger inputs and functional inputs is difficult: work-in-progress;techniques for design analysis and modification based on ASAP model : work-in-progress;widerframe: an automatic customization framework for building CNN accelerators on FPGAs: work-in-progress;and an ESL methodology for HW/SW co-design of monitorable embedded systems: the 'design for monitorability' project - work-in-progress.
The proceedings contain 14 papers. The topics discussed include: efficient gait trajectory prediction method based on soft constraint weighted template matching: work-in-progress;introduction to the AMD Versal ACAP ad...
ISBN:
(纸本)9798400702891
The proceedings contain 14 papers. The topics discussed include: efficient gait trajectory prediction method based on soft constraint weighted template matching: work-in-progress;introduction to the AMD Versal ACAP adaptable intelligent engine and to its programming model;MARS: a framework for runtime monitoring, modeling, and management of real-time systems;the synergy of hyperdimensional and in-memory computing;introduction to the AMD Versal ACAP adaptable intelligent engine and to its programming model;challenges and opportunities for sustainable multi-scale computing systems;work-in-progress: a generic non-intrusive parallelization approach for systemC TLM-2.0-based virtual platforms;and work-in-progress: a universal instrumentation platform for non-volatile memories.
The proceedings contain 12 papers. The topics discussed include: neuro-symbolic architecture meets large language models: a memory-centric perspective;work-in-progress: context and noise aware resilience for autonomou...
ISBN:
(纸本)9798350356397
The proceedings contain 12 papers. The topics discussed include: neuro-symbolic architecture meets large language models: a memory-centric perspective;work-in-progress: context and noise aware resilience for autonomous driving applications;tutorial on novel toolkits toward AI for science on resource-constrained computing systems;work-in-progress: worst-case execution-time measurement techniques for nonlinear model predictive controllers;end-to-end carbon footprint assessment and modeling of deep learning;estimation and optimization of DNNs for embedded platforms;emerging architecture design, control, and security challenges in software defined vehicles;***: principles and practices of machine learning systems engineering;AI-driven indoor navigation with mobile embedded systems;sustainable deployment of deep neural networks on non-volatile compute-in-memory accelerators;and reducing smart phone environmental footprints with in-memory processing.
The proceedings contain 11 papers. The topics discussed include: emergent design challenges for embedded systems and paths forward: mixed-criticality, energy, reliability and security perspectives;automated HW/SW co-d...
ISBN:
(纸本)9781450390767
The proceedings contain 11 papers. The topics discussed include: emergent design challenges for embedded systems and paths forward: mixed-criticality, energy, reliability and security perspectives;automated HW/SW co-design for edge AI: state, challenges and steps ahead;work-in-progress: achieving fast lane detection of autonomous driving by CNN based differentiation;work-in-progress: the RISC-V instruction set architecture optimization and fixed-point math library co-design;work-in-progress: learned buffer management: a new frontier;work-in-progress: a physically realizable backdoor attack on 3D point cloud deep learning;work-in-progress: register file management for PRET machines;and work-in-progress: improving security and maintainability in modular embedded systems with hardware support.
The proceedings contain 37 papers. The topics discussed include: a practical methodology to validate the statistical behavior of bloom filters;scalable and realistic benchmark synthesis for efficient NoC performance e...
ISBN:
(纸本)9781450344838
The proceedings contain 37 papers. The topics discussed include: a practical methodology to validate the statistical behavior of bloom filters;scalable and realistic benchmark synthesis for efficient NoC performance evaluation: a complex network analysis approach;an accurate and flexible early memory system power evaluation approach using a microcomponent method;time and timeliness;a design to reduce write amplification in object-based NAND flash devices;enabling the high level synthesis of data analytics accelerators;and going deeper than deep learning for massive data analytics under physical constraints.
暂无评论