Embedded systems based on FPGAs frequently incorporate soft processors. The prevalence of soft processors in embedded systems is due to their flexibility and adaptability to the application. However, soft processors provide moderate performance compared to hard cores and custom logic, hence faster performing soft processors are desirable. Many soft processor architectures have been studied in the past including Vector processors and VLIWs. These architectures focus on regular applications in which it is possible to extract data and/or instruction level parallelism offline. However, applications with irregular parallelism only benefit marginally from such architectures. Targeting such applications, we investigate superscalar, out-of-order, and Runahead execution on FPGAs. Although these architectures have been investigated in the ASIC world, they have not been studied thoroughly for FPGA implementations. We start by investigating the challenges of implementing a typical inorder pipeline on FPGAs and propose effective solutions to shorten the processor critical path. We then show that superscalar processing is undesirable on FPGAs as it leads to low clock frequency and high area cost due to wide datapaths. Accordingly, we focus on investigating and proposing FPGA-friendly OoO and Runahead soft processors. We propose FPGA-friendly alternatives for various mechanisms and components used in OoO execution. We introduce CFC, a novel copy-free checkpointing which exploits FPGA block RAMs for fast and dense storage. Using CFC, we propose an FPGA-friendly register renamer and investigate the design and implementation of instruction schedulers on FPGAs. We then investigate Runahead execution and introduce NCOR, an FPGA-friendly non-blocking cache tailored for FPGAs. NCOR removes CAM-based structures used in conventional designs and achieves the high clock frequency of 278 MHz. Finally, we introduce SPREX, a complete Runahead soft core incorporating CFC and NCOR. Compared to Nios~II, SPREX provides as much as 38% higher performance for applications with irregular data-level parallelism with minimal area overhead.

International Telemetering Conference Proceedings / October 30-November 02, 1995 / Riviera Hotel, Las Vegas, Nevada / The Earth Observing System-AM (EOS-AM) spacecraft, the first in a series of spacecraft for the EOS, is scheduled for launch in June of 1998. This spacecraft will carry high resolution instruments capable of generating large volumes of earth science data at rates up to 150 Mbps. Data will be transmitted in a packet format based upon the Consultative Committee for Space Data Systems (CCSDS) Advanced Orbiting Systems (AOS) recommendations. The Data Systems Technology Division (DSTD) at NASA's Goddard Space Flight Center (GSFC) has developed a set of high performance CCSDS return-link processing systems to support testing and verification of the EOS-AM spacecraft. These CCSDS processing systems use Versa Module Eurocard bus (VMEBus) Very Large Scale Integration (VLSI)-based processing modules developed for the EOS ground segment to acquire and handle the high rate EOS data. Functions performed by these systems include frame synchronization, Reed-Solomon error correction, fill frame removal, virtual channel sorting, packet service processing, and data quality accounting. The first of the systems was delivered in October 1994 to support testing of the onboard formatting equipment. The second and third systems, delivered in April 1995, support spacecraft checkout and verification. This paper will describe the function and implementation of these systems.

No description available.

It was observed, that the RT-PICLS code ran by FWKT on the hypnos cluster was producing an unusual amount of system load, according to Ganglia metrics. Since this may point to an IO-problem in the code, this code was analyzed more closely.

by Tsoi Yeung-pang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1994. / Includes bibliographical references (leaves 105-106). / Chapter I. --- Acknowledgements --- p.i / Chapter II. --- Abstract --- p.ii / Chapter III. --- Table of contents --- p.iv / Chapter IV. --- List of Tables and Figures --- p.v / Chapter Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Modes of chromatography / Chapter 1.2 --- Objective of the present study / References / Chapter Chapter 2. --- Instrumentation and theory --- p.8 / Chapter 2.1 --- Instrumentation of HPLC / Chapter 2.2 --- Theory of liquid chromatography / References / Chapter Chapter 3. --- Determination of citrate in pharmaceutical preparations by HPLC using indirect photometric detection --- p.21 / Chapter 3.1 --- Introduction / Chapter 3.2 --- Review of the analytical methods / Chapter 3.3 --- Theory of detection / Chapter 3.4 --- Experimental / Chapter 3.5 --- Results and discussion / Chapter 3.6 --- Conclusion / References / Chapter Chapter 4. --- Determination of camphor and menthol by HPLC using indirect conductometric detection --- p.74 / Chapter 4.1 --- Introduction / Chapter 4.2 --- Review of the analytical methods / Chapter 4.3 --- Theory of detection / Chapter 4.4 --- Experimental / Chapter 4.5 --- Results and discussion / Chapter 4.6 --- Conclusion / References

Siu Yuen Yu. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 122-139). / Abstracts in English and Chinese. / Abstract (English) --- p.i / Abstract (Chinese) --- p.iii / Acknowledgments --- p.v / Table of Contents --- p.vi / List of Figures --- p.x / List of Tables --- p.xvi / Chapter CHAPTER 1 --- INTRODUCTION --- p.1 / Chapter CHAPTER 2 --- LITERATURE REVIEW --- p.7 / Chapter 2.1 --- Traditional methods for studying zooplankton feeding selectivity --- p.7 / Chapter 2.1.1 --- Cell counting after laboratory feeding experiments --- p.7 / Chapter 2.1.2 --- Direct examination of gut contents --- p.8 / Chapter 2.1.3 --- Use of radioactive tracers --- p.9 / Chapter 2.1.4 --- Gut fluorescence method --- p.9 / Chapter 2.2 --- High Performance Liquid Chromatography analysis of phytoplankton pigments --- p.11 / Chapter 2.2.1 --- Principle --- p.11 / Chapter 2.2.2 --- Pigments as signature markers of phytoplankton --- p.11 / Chapter 2.2.3 --- Development of HPLC analysis of phytoplankton pigments --- p.16 / Chapter 2.2.4 --- Advantages of HPLC analysis of phytoplankton pigments --- p.17 / Chapter 2.2.5 --- Limitation of HPLC analysis of phytoplankton pigments --- p.18 / Chapter 2.3 --- Zooplankton feeding selectivity --- p.19 / Chapter 2.3.1 --- Ecological importance of zooplankton feeding selectivity --- p.19 / Chapter 2.3.2 --- Factors affecting zooplankton feeding selectivity --- p.19 / Chapter 2.3.3 --- Feeding selectivity of zooplankton studied in this study --- p.21 / Chapter 2.3.3.1 --- p. avirostirs --- p.21 / Chapter 2.3.3.2 --- Paracalanus spp --- p.22 / Chapter 2.3.3.3 --- Pseudevadne tergestina --- p.23 / Chapter 2.4 --- Pigment degradation in guts of zooplankton --- p.24 / Chapter 2.4.1 --- Experimental design --- p.24 / Chapter 2.4.2 --- Pigment degradation --- p.24 / Chapter 2.5 --- "Tolo Harbour, Hong Kong" --- p.26 / Chapter 2.5.1 --- Site description --- p.26 / Chapter 2.5.2 --- Phytoplankton and zooplankton in Tolo Harbour --- p.27 / Chapter CHAPTER 3 --- MATERIALS AND METHODS --- p.28 / Chapter 3.1 --- Field sampling --- p.28 / Chapter 3.1.1 --- Study of seasonal patterns in zooplankton feeding selectivity --- p.28 / Chapter 3.1.1.1 --- Collection of phytoplankton and zooplankton for pigment analysis --- p.28 / Chapter 3.1.1.2 --- Collection of phytoplankton and zooplankton for plankton enumeration --- p.30 / Chapter 3.1.2 --- Collection of phytoplankton and zooplankton for laboratory feeding experiments --- p.32 / Chapter 3.2 --- Laboratory experiments and data analysis --- p.33 / Chapter 3.2.1 --- Study of seasonal patterns in zooplankton feeding selectivity --- p.33 / Chapter 3.2.1.1 --- HPLC of phytoplankton pigments --- p.33 / Chapter 3.2.1.2 --- Fluorometric measurement of chlorophyll-α --- p.35 / Chapter 3.2.1.3 --- Plankton identification and enumeration --- p.36 / Chapter 3.2.2 --- Laboratory feeding experiments for investigation of pigment degradation in zooplankton gut --- p.37 / Chapter CHAPTER 4 --- RESULTS --- p.41 / Chapter 4.1 --- Information on Tolo Harbour --- p.41 / Chapter 4.1.1 --- Temperature and salinity in Tolo Harbour --- p.41 / Chapter 4.1.2 --- Plankton composition and community in Tolo Harbour --- p.43 / Chapter 4.1.2.1 --- Phytoplankton --- p.43 / Chapter 4.1.2.2 --- Zooplankton --- p.50 / Chapter 4.2 --- Seasonal zooplankton feeding selectivity investigated by HPLC phytoplankton pigment analysis --- p.53 / Chapter 4.2.1 --- Verification of HPLC pigment analysis by fluorometric analysis --- p.53 / Chapter 4.2.2 --- Correlations between phytoplankton cell densities and pigment concentrations in water samples --- p.55 / Chapter 4.2.3 --- Feeding selectivity of zooplankton on different phytoplankton groups --- p.73 / Chapter 4.2.4 --- Feeding selectivity of zooplankton on dinoflagellates --- p.87 / Chapter 4.2.5 --- Feeding selectivity of zooplankton on diatoms --- p.87 / Chapter 4.3 --- Feeding selectivity on phytoplankton by other cladoceran - Pseudevadne tergestina --- p.89 / Chapter 4.4 --- Pigment degradation in zooplankton guts after ingestion of phytoplankton --- p.90 / Chapter 4.5 --- Clearance rates of P. avirostris and Paracalanus spp. in feeding experiments --- p.101 / Chapter CHAPTER 5 --- DISCUSSIONS --- p.105 / Chapter 5.1 --- Experiment design --- p.105 / Chapter 5.2 --- Seasonal zooplankton feeding selectivity investigated by HPLC phytoplankton pigment analysis --- p.108 / Chapter 5.2.1 --- Correlations between phytoplankton cell densities and pigment concentrations in water samples --- p.108 / Chapter 5.2.2 --- Feeding selectivity of zooplankton on different phytoplankton groups --- p.108 / Chapter 5.2.3 --- Feeding selectivity of Pseudevadne tergestina --- p.111 / Chapter 5.3 --- Feeding experiments for investigating pigment degradation in guts of zooplankton --- p.112 / Chapter 5.3.1 --- Principle --- p.112 / Chapter 5.3.2 --- Degradation for different pigments in guts of P. avirostris and Paracalanus spp. --- p.112 / Chapter 5.4 --- Clearance rates of P. avirostris and Paracalanus spp. --- p.114 / Chapter 5.4.1 --- p. avirostris --- p.114 / Chapter 5.4.2 --- Paracalanus spp. --- p.115 / Chapter 5.5 --- Limitations of HPLC analysis of phytoplankton pigments --- p.116 / Chapter 5.6 --- Environmental events related to feeding selectivity of zooplankton in Tolo Harbour --- p.118 / Chapter 5.6.1 --- Energy transfer in trophic level --- p.118 / Chapter 5.6.2 --- Abilities of p. avirostris and Paracalanus spp. to control red tides in Tolo Harbour --- p.118 / Chapter CHAPTER 6 --- CONCLUSION --- p.120 / REFERENCES --- p.122 / APPENDIX

An analytical and experimental investigation on the shear strength of High Performance Concrete (HPC) beams with vertical shear reinforcement or stirrups was carried out. The analytical work involved developing a theory based on the truss analogy, capable of predicting the response and shear strength of such beams subjected to combined bending moment and shear force.The experimental work comprised forty-eight beam specimens in eight series of tests. Most of the beams were 250 mm wide, 350 mm deep and had a clear span of approximately 2 metres. The largest beam was 250 mm wide, 600 mm deep and had a clear span of 3.1 metres. Test parameters included the concrete cover to the shear reinforcement cage, shear reinforcement ratio, longitudinal tensile steel ratio, overall beam depth, shear span-to-depth ratio and concrete compressive strength. The loading configurations included using one, two or four symmetrically placed concentrated loads on simply supported spans.The theory predicted the shear strength of the beams in the present study well. When beams from previous investigations were included, the theory also gave good prediction of the shear strength. Apart from this, comparisons of shear strength were also made with the predictions by the shear design provisions contained in the Australian Standard AS 3600 (1994), American Concrete Institute Building Code ACI 318-95, Eurocode EC2 Part 1 and Canadian Standard CSA A23.3-94. The AS 3600 method was found to give the best correlation with the test results among all the code methods.

Many parallel machines, both commercial and experimental, have been/are being designed with toroidal interconnection networks. For a given number of nodes, the torus has a relatively larger diameter, but better cost/performance tradeoffs, such as higher channel bandwidth, and lower node degree, when compared to the hypercube. Thus, the torus is becoming a popular topology for the interconnection network of a high performance parallel computers. In a multicomputer, the resources, such as I/O devices or software packages, are distributed over the networks. The first part of the thesis investigates efficient methods of distributing resources in a torus network. Three classes of placement methods are studied. They are (1) distant-t placement problem: in this case, any non-resource node is at a distance of at most t from some resource nodes, (2) j-adjacency problem: here, a non-resource node is adjacent to at least j resource nodes, and (3) generalized placement problem: a non-resource node must be a distance of at most t from at least j resource nodes. This resource placement technique can be applied to allocating spare processors to provide fault-tolerance in the case of the processor failures. Some efficient spare processor placement methods and reconfiguration schemes in the case of processor failures are also described. In a torus based parallel system, some algorithms give best performance if the data are distributed to processors numbered in Cartesian order; in some other cases, it is better to distribute the data to processors numbered in Gray code order. Since the placement patterns may be changed dynamically, it is essential to find efficient methods of rearranging the data from Gray code order to Cartesian order and vice versa. In the second part of the thesis, some efficient methods for data transfer from Cartesian order to radix order and vice versa are developed. The last part of the thesis gives results on generating edge disjoint Hamiltonian cycles in k-ary n-cubes, hypercubes, and 2D tori. These edge disjoint cycles are quite useful for many communication algorithms. / Graduation date: 1997

Existing parallel file systems are proving inadequate in two important arenas: programmability and performance. Both of these inadequacies can largely be traced to the fact that nearly all parallel file systems evolved from Unix and rely on a Unix-oriented, single-stream, block-at-a-time approach to file I/O. This one-size-fits-all approach to parallel file systems is inadequate for supporting applications running on distributed-memory parallel computers. This research provides a migration path away from the traditional approaches to parallel I/O at two levels. At the level seen by the programmer, we show how file operations can be closely integrated with the semantics of a parallel language. Principles for this integration are illustrated in their application to C*, a virtual-processor- oriented language. The result is that traditional C file operations with familiar semantics can be used in C* where the programmer works--at the virtual processor level. To facilitate high performance within this framework, machine-independent modes are used. Modes change the performance of file operations, not their semantics, so programmers need not use ambiguous operations found in many parallel file systems. An automatic mode detection technique is presented that saves the programmer from extra syntax and low-level file system details. This mode detection system ensures that the most commonly encountered file operations are performed using high-performance modes. While the high-performance modes allow fast collective movement of file data, they must include optimizations for redistribution of file data, a common operation in production scientific code. This need is addressed at the file system level, where we provide enhancements to Disk-Directed I/O for redistributing file data. Two enhancements are geared to speeding fine-grained redistributions. One uses a two-phase, or indirect, approach to redistributing data among compute nodes. The other relies on I/O nodes to guide the redistribution by building packets bound for compute nodes. We model the performance of these enhancements and determine the key parameters determining when each approach should be used. Finally, we introduce the notion of collective prefetching and identify its performance benefits and implementation tradeoffs. / Graduation date: 1997

The objective of this research was to evaluate the current design specifications for use on prestressed, High Performance Concrete (HPC) bridge girders. An AASHTO Type IV and modified BT-56 girders were constructed with a 10,000 psi HPC to which a composite 7000 psi HPC deck was cast on top. The composite girders were tested in flexure, with the Type IV being tested to failure. The results of the flexure tests showed that the current AASHTO Specification for cracking moment and ultimate capacity are conservative. In addition to flexural testing, each composite girder was studied with respect to the deck contraction induced girder deflection. Each deck and girder were instrumented with strain gauges and string potentiometes. The results of the study indicated the induced deflections are significantly greater than deflections from the deck dead load, and should be considered to accurately predict bridge deflection.