In this paper we present the second stage of a two-phase strategy for reducing the required background memory sizes for a large class of data-intensive multimedia applications. This strategy is particularly useful in ...
详细信息
In this paper we present the second stage of a two-phase strategy for reducing the required background memory sizes for a large class of data-intensive multimedia applications. This strategy is particularly useful in an embedded application context, where memory size and the corresponding power consumption are the main cost factors together with data transfers. Our strategy optimizes the storage order of arrays in memory by trying to improve the reuse of memory locations, as well for elements of the same array as for elements of different arrays. Although size reduction is the main objective, an added benefit is a reduced power consumption due to the decreased capacitive load of the memories. The memory size reduction task is part of an overall memory size and power reduction methodology called ATOMIUM, in which other tasks can increase its effectiveness (e.g. loop transformations), but it can also be used on a stand-alone base. The effectiveness of our approach is demonstrated by experimental results for some real-life multimedia applications, for which a considerable memory size reduction was obtained.
A method is presented for mapping conditional affine resources equations (CAREs) into systolic-type architectures. The tasks of localization and of space-time reindexing are formulated as a single branch and broad sea...
详细信息
Data-driven arrays provide high levels of parallelism and pipelining for algorithms with no internal regularity. Most of the methods previously developed for mapping algorithms onto processor arrays assumed an unbound...
详细信息
We present a novel technique to study the behavior of liquids in microfluidics. For this, an array of capacitive sensor realized in CMOS circuitry is considered to detect the liquid in a channel integrated into CMOS c...
详细信息
The concept of pipelined buses for parallel architectures diverges from the conventional exclusive access buses and offers both possibilities and challenges for significantly improving the efficiency of interprocessor...
详细信息
ISBN:
(纸本)0818690895
The concept of pipelined buses for parallel architectures diverges from the conventional exclusive access buses and offers both possibilities and challenges for significantly improving the efficiency of interprocessor communications in parallel computers. The authors present an efficient embedding of pyramids in arrayprocessors with pipelined buses. The embedding has the property that all the neighboring nodes in the pyramid are mapped to the same bus. Thus, any two neighbors in the embedded pyramid can communicate with each other using a single bus cycle.
This paper presents a novel technique for bacteria detection. The proposed system uses MC-1 magnetotactic bacteria and measures impedance to detect the presence of pathogenic bacteria. An electrode array is connected ...
详细信息
The following topics are dealt with: fault-tolerant computers;associative processors and memories;defect-tolerant components;systolic arrayprocessors;signal processing architectures;emerging architectures;multiproces...
详细信息
The following topics are dealt with: fault-tolerant computers;associative processors and memories;defect-tolerant components;systolic arrayprocessors;signal processing architectures;emerging architectures;multiprocessors;distributed systems;image processing architectures;logic and system simulation;circuit and interconnection simulation;hierarchical design and silicon compilers;logic synthesis and design languages;device modeling and simulation;testing;hardware accelerators;knowledge-based tools;WSI;packaging;physical design;automation and robotics;image processing and graphics;computer networks;parallel/multiprocessing systems;supercomputers;application-specific ICs;intelligent workstations;technology transfer;and reliabiity and maintainability. 251 papers were presented, of which 243 are published in full in the present proceedings, and 8 as abstracts only.
Modular multiplication is a fundamental operation in numerous public-key cryptosystems including the RSA method. Increasing popularity of internet e-commerce and other security applications translate into a demand for...
详细信息
Modular multiplication is a fundamental operation in numerous public-key cryptosystems including the RSA method. Increasing popularity of internet e-commerce and other security applications translate into a demand for a scalable performance hardware design framework. Previous scalable hardware methodologies either were not systolic and thus involved performance-degrading, full-world-length broadcasts or were not scalable beyond linear array size. In this paper, these limitations are overcome with the introduction of three scalable-performance modular multiplication architectures based on systolic arrays. Very high clock rates are feasible, since the cells composing the architectures are of bit-level complexity. Architectural methods based on both binary and high-radix modular multiplication are derived. All techniques are constructed to allow additional flexibility for the impact of interconnect delay within the design environment.
Compiler optimizations play a pivotal role in determining the run-time performance of an application. Performance improvements stem from path length reduction, efficient instruction selection, pipeline scheduling, and...
详细信息
Compiler optimizations play a pivotal role in determining the run-time performance of an application. Performance improvements stem from path length reduction, efficient instruction selection, pipeline scheduling, and memory penalty minimization. This paper describes typical optimizations and highlights the mechanisms by which they improve performance. We categorize the described optimizations as basic, architecture specific, interprocedural, and source level. To accurately make trade-offs in the hardware design process, compiler/hardware interaction is essential in the early design stages.
The PAPRICA project started in 1988 as an experimental VLSI architecture devoted to the efficient computation of data with two-dimensional structure. The main goal of the project is to develop a subsystem that could o...
详细信息
暂无评论