One of the most challenging problems in high-level synthesis is how to quickly explore a wide range of design options to achieve high-quality designs. This paper presents an Integrated Framework for Design Optimizatio...
详细信息
One of the most challenging problems in high-level synthesis is how to quickly explore a wide range of design options to achieve high-quality designs. This paper presents an Integrated Framework for Design Optimization and Space Minimization (IDOM) towards finding the minimum configuration satisfying timing and code size constraints. We show an effective way to reduce the design space to be explored through the study of the fundamental properties and relations among multiple design parameters, such as retiming value, unfolding factor, timing, and code size. Theories are presented to produce a small set of feasible design choices with provable quality. IDOM algorithm is proposed to generate high-quality design by integrating performance and code size optimization techniques. The experimental results on a set of DSP benchmarks show the efficiency and effectiveness of the IDOM algorithm. It constantly generates the minimal configuration for all the benchmarks. The cost of design space exploration using IDOM is only 3% of that using the standard method.
This paper presents an investigation into the possibility of using a regular concurrent programming language for modeling and implementing digital circuits. Some of the reasons for using an existing language include t...
详细信息
This paper presents an investigation into the possibility of using a regular concurrent programming language for modeling and implementing digital circuits. Some of the reasons for using an existing language include the ability to use existing compilers and analysis tools for circuit design and verification. Another important reason is the ever increasing need to model complete systems that comprise interacting software and hardware in a single framework which facilitates easier migration of sub-components between hardware and software implementations compared to multi-model approaches. To this end we present the design of the Kiwi system which models digital circuits with concurrent programs using a standard library in C# for multi-threaded programming. Kiwi models can be executed using a regular C# compiler. Also, the compiled bytecode can be automatically converted into circuits using our Kiwi hardwaresynthesissystem.
It is a challenging task to resist adversarial attacks due to the imperceptibility of adversarial examples. The passive defense method is developed based on a series of input transformations and has achieved a promisi...
详细信息
ISBN:
(数字)9781728191980
ISBN:
(纸本)9781728191997
It is a challenging task to resist adversarial attacks due to the imperceptibility of adversarial examples. The passive defense method is developed based on a series of input transformations and has achieved a promising result, which however suffers from a high computation cost. In this paper, we design a new heatmap-aware method to defend adversarial attacks, leading to a significant decrease in the time cost. To be specific, we compute the classification importance from each part of the input to obtain the heatmap of the data, and the key areas of classification are extracted according to the heatmap. A series of transformations are applied to the key areas of the classification, which reduces the amount of data to be processed and thus reduces the time cost. A set of preliminary experiments are conducted to testify the effectiveness of the proposed approach.
A software model of hardware estimator is developed. The behavioral description is transformed into an intermediate format called control flow graph (CFG). The graph is partitioned into hardware and software. The unop...
详细信息
A software model of hardware estimator is developed. The behavioral description is transformed into an intermediate format called control flow graph (CFG). The graph is partitioned into hardware and software. The unoptimized hardware in intermediate graph is estimated by transforming the graph into matrix format. The partitioned hardware of control flow graph is translated as behavioral network graph. The high level synthesis and logic synthesis are performed using the BNG with simple logical transformation. The final RTL obtained from the conventional synthesis method and BNG method for resource and timing constraint were presented. The cost estimation for the various control construction is being tabulated
With increasing applications of Deep Neural Networks (DNNs) to edge computing systems, security issues have received more attentions. Particularly, model stealing attack is one of the biggest challenge to the privacy ...
详细信息
ISBN:
(数字)9781728191980
ISBN:
(纸本)9781728191997
With increasing applications of Deep Neural Networks (DNNs) to edge computing systems, security issues have received more attentions. Particularly, model stealing attack is one of the biggest challenge to the privacy of models. To defend against model stealing attack, we propose a novel protection architecture with fuzzy models. Each fuzzy model is designed to generate wrong predictions corresponding to a particular category. In addition' we design a special voting strategy to eliminate the systemic errors, which can destroy the dark knowledge in predictions at the same time. Preliminary experiments show that our method substantially decreases the clone model's accuracy (up to 20%) without loss of inference accuracy for benign users.
NAND flash memory can provide cost-effective secondary storage in mobile embedded systems, but its lack of a random access capability means that code shadowing is generally required, taking up extra RAM space. Demand ...
详细信息
NAND flash memory can provide cost-effective secondary storage in mobile embedded systems, but its lack of a random access capability means that code shadowing is generally required, taking up extra RAM space. Demand paging with NAND flash memory has recently been proposed as an alternative which requires less RAM. This scheme is even more attractive for OneNAND flash, which consists of a NAND flash array with SRAM buffers, and supports eXecute-ln-Place (XIP), which allows limited random access to data on the SRAM buffers. We introduce a novel demand paging method for OneNAND flash memory with XIP feature. The proposed on-line demand paging method with XIP adopts finite size sliding window to capture the paging history and thus predict future page demands. We particularly focus on non-critical code accesses which can disturb real-time code. Experimental results show that our method outperforms conventional LRU-based demand paging by 57% in terms of execution time and by 63% in terms of energy consumption. It even beats the optimal solution obtained from MIN, which is a conventional off-line demand paging technique by 30% and 40% respectively.
The AcubeSAT space mission, a collaborative effort within the Fly Your Satellite! 3 program of the European Space Agency (ESA) Education Office and SpaceDot, features unique payload requirements aimed at exploring the...
详细信息
暂无评论