Hewlett-Packard (Canada)

Software -- Software Engineering.

Quality engineering. Analysis of quality information and quality improvement effort. Fundamentals of designing experiments. Orthogonal array experiments I. Orthogonal array experiments II. Parameter design for continuous data. Parameter design for discrete data. Alternative parameter design and other considerations. Parameter design for dynamic characteristics. Tolerance design. Response surface design and analysis.

This paper explores compiler techniques for reducing the memory needed to load and run program executables. In embedded systems, where economic incentives to reduce both ram and rom are strong, the size of compiled code is increasingly important. Similarly, in mobile and network computing, the need to transmit an executable before running it places a premium on code size. Our work focuses on reducing the size of a program's code segment, using pattern-matching techniques to identify and coalesce together repeated instruction sequences. In contrast to other methods, our framework preserves the ability to run program executables directly, without an intervening decompression stage. Our compression framework is integrated into an industrial-strength optimizing compiler, which allows us to explore the interaction between code compression and classical code optimization techniques, and requires that we contend with the difficulties of compressing previously optimized code. The specific contributions in this paper include a comprehensive experimental evaluation of code compression for a Risc-like architecture, a more powerful pattern-matching scheme for improved identification of repeated code fragments, and a new form of profile-driven code compression that reduces the speed penalty arising from compression.

Statistical methods for quality improvement , Statistical methods for quality improvement , کتابخانه دیجیتال جندی شاپور اهواز

Demand for memory capacity and bandwidth keeps increasing rapidly in modern computer systems, and memory power consumption is becoming a considerable portion of the system power budget. However, the current DDR DIMM standard is not well suited to effectively serve CMP memory requests from both a power and performance perspective. We propose a new memory module called a multicore DIMM, where DRAM chips are grouped into multiple virtual memory devices, each of which has its own data path and receives separate commands. The Multicore DIMM is designed to improve the energy efficiency of memory systems with small impact on system performance. Dividing each memory modules into 4 virtual memory devices brings a simultaneous 22%, 7.6%, and 18% improvement in memory power, IPC, and system energy-delay product respectively on a set of multithreaded applications and consolidated workloads.

Diode array detection (DAD) in capillary electrophoresis (CE) offers similar advantages over single-wavelength detection as it does in high performance liquid chromatography (HPLC). Thus, confirmation of compound identity and establishment of peak purity are critical issues in CE, necessitating sensitive and specific detection. With an optimized optical system, DAD yields sensitivity comparable to that of single or variable wavelength detectors. Sensitivity can be further improved three to five times by use of expanded pathlength capillaries employing the so-called bubble cell. Optimization of optical design, as well as maintenance of spectral fidelity, will be discussed in this work. A variety of applications of CE, and specifically of micellar electrokinetic capillary chromatography (MEKC), with emphasis on quantitative analysis, sensitivity, linearity, spectral identification, and peak purity verification will be presented. The use of spectral information for peak tracking in MEKC method development and for the assessment of purity of electrodistorted peaks will also be illustrated.

Computer simulation of electrostatic discharge (ESD) for simplified objects is described and compared to measured transient fields of human/metal ESD. The simulation algorithm uses the method of moments in time domain, coupled with nonlinear arc resistance model. Transient currents and fields are analyzed from the electromagnetic compatibility (EMC) point of view. Validation of the numerical simulation is done by comparison to experimental data. The simulated structure models the human/metal ESD in its peak current and field values and their derivatives reasonably well.

A technique for measuring the risetimes of the fastest of these instruments, which will allow more accurate measurement of the fastest pulses, is described. The sampling process used by these oscilloscopes is essentially a brief switch closure of a few picoseconds between the signal to be measured at the oscilloscope input and a holding capacitor in the detection circuit. During this switch closure, sampling current flows from the input and is collected or integrated in a capacitor into a finite charge proportional to the input signal. The collected charge is then measured with an analog-to-digital converter. The sudden flow of sampling current during the switch closure creates an impulselike electric disturbance at the oscilloscope input. The characterization technique exploits the fact that this kickback response is a signature of the sampling process.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Digital color halftoning is the process of transforming continuous-tone color images into images with a limited number of colors. The importance of this process arises from the fact that many color imaging systems use output devices such as color printers and low-bit depth displays that are bilevel or multilevel with a few levels. The goal is to create the perception of a continuous-tone color image using the limited spatiochromatic discrimination capability of the human visual system. In decreasing order of how locally algorithms transform a given image into a halftone and, therefore, in increasing order of computational complexity and halftone quality, monochrome digital halftoning algorithms can be placed in one of three categories: 1) point processes (screening or dithering), 2) neighborhood algorithms (error diffusion), and 3) iterative methods. All three of these algorithm classes can be generalized to digital color halftoning with some modifications. For an in-depth discussion of monochrome halftoning algorithms, the reader is directed to the July 2003 issue of IEEE Signal Processing Magazine. In the remainder of this article, we only address those aspects of halftoning that specifically have to do with color. For a good overview of digital color halftoning, the reader is directed to Haines et al. (2003). In addition, Agar et al. (2003) contains a more in-depth treatment of some of the material found in this work.

Memory latency is a major issue for many modern microprocessor based systems, including the Hewlett-Packard PA-8000. Due to its fast clock rate and wide issue capability, cache misses in the PA-8000 are very expensive. The PA-8000 combines out-of-order execution with multiple outstanding memory requests to tolerate memory latency; however, this approach has its limitations. In order to substantially reduce much of the memory latency penalty, the PA-8000 uses software-based data cache prefetching. In this paper, we discuss the implementation of the data prefetch generation algorithm in the Hewlett-Packard Precision Architecture (HP-PA) compiler. We present performance results for SPECfp95 on a PA-8000 system that show speedups, due to data prefetching, of up to 100%.

This document specifies an Internet standards track protocol for the Internet community, and requests discussion and suggestions for improvements.

OBJECTIVE: Mountaineers face a variety of health risks at altitude including pulmonary edema; portable ultrasound may be used to diagnose high altitude pulmonary edema. This report tests the functionality of electronic equipment in a hypobaric test environment and the ability of remotely guided nonexperts to use ultrasound to evaluate respiratory status on Mt Everest. METHODS: Two ultrasound devices and associated video equipment were tested in a cooled (4 degrees C-5 degrees C) hypobaric chamber to 27000 feet (8230 m) before travel to Mt Everest. The ultrasound system was connected via satellite phone to a video streaming device and portable computer to stream video through the Internet for remote guidance of a novice user by an expert. Pulmonary interstitial fluid was quantified by the presence of "comet tail" artifacts. RESULTS: There was no notable degradation in equipment performance in cold, hypobaric conditions; ultrasound confirmation of increased comet tails was noted in the chamber despite oxygen supplementation and the very brief exposure. Two pulmonary surveys of asymptomatic participants were completed by novice operators within 25 minutes on Mt Everest. The remote expert was able to guide and identify comet tails suggestive of intermediate pulmonary interstitial fluid. Image quality was excellent. CONCLUSIONS: The tested ultrasound devices functioned nominally in cold, hypobaric conditions; acute changes in lung fluid content were noted in these conditions despite normoxia. We successfully used a satellite telemedical connection with a remote expert to guide thoracic ultrasound examinations at Advanced Base Camp on Mt Everest. Coupling portable ultrasound with remote expert guidance telemedicine provides a robust diagnostic capability in austere locations.

This paper evaluates performance characteristics of the HP GS1280 shared memory multiprocessor system. The GS1280 system contains up to 64 Alpha 21364 CPUs connected together via a torus-based interconnect. We describe architectural features of the GS1280 system. We compare and contrast the GS1280 to the previousgeneration Alpha systems: AlphaServer GS320 and ES45/SC45. We further quantitatively show the performance effects of these features using application results and profiling data based on the built-in performance counters. We find that the HP GS1280 often provides 2 to 3 times the performance of the AlphaServer GS320 at similar clock frequencies. We find the key reasons for such performance gains are advances in memory, inter-processor, and I/O subsystem designs.

BACKGROUND: Halothane attenuates endothelium-dependent relaxation. To differentiate halothane's effect on endothelium-derived relaxing factor/nitric oxide (EDRF/NO) production from its effect on nitric oxide action on vascular smooth muscle, halothane's effect on endothelium-dependent relaxation was studied in a bioassay system. METHODS: Indomethacin-treated, bovine aortic endothelial cells (BAEC) grown on microcarrier beads, continuously perfused by oxygenated and carbonated (95% O2, 5% CO2) Krebs-Ringer solution served as nitric oxide donors while an isolated denuded rabbit aortic ring directly superfused by the effluent of the BAEC and precontracted with phenylephrine was used to detect EDRF/NO release. The effect of basal and bradykinin-stimulated EDRF release on the tension of the vascular ring was measured. In the bioassay, it was possible to treat either the vascular denuded ring alone or the vascular ring plus the BAEC with halothane by adding it to the perfusate either upstream or downstream from the BAEC. Halothane (final concentration 2.2%) was added to the perfusate at these two positions, and its effect on the relaxation induced by EDRF/NO was determined. In some experiments, the preparations were treated with hemoglobin or L-monomethyl-L-arginine to attenuate the relaxation induced by the EDRF/NO pathway. Finally, halothane's effect on vascular relaxation induced by an increasing concentration of sodium nitroprusside was measured. Halothane's concentration in the perfusate was determined by gas chromatography using electron capture for anesthetic measurement. RESULTS: EDRF/NO released by the BAEC was responsible for the relaxation of the vascular ring. Halothane added to the perfusate potentiated the tension induced by phenylephrine (7.1 +/- 1.89%) and attenuated the relaxation induced by the release of EDRF/NO. This effect was reversible after discontinuation of halothane. Halothane's effect was present even when the anesthetic was added to the perfusate downstream to the perfusion of the endothelial cells. Halothane had no effect on the vascular relaxation induced by sodium nitroprusside. CONCLUSIONS: The authors' data demonstrate that halothane does not interfere with endothelial cell release of EDRF/NO and its smooth muscle cell relaxation but seems to modify either EDRF/NO half-life or its activated redox form.

Petaflops systems will have tens to hundreds of thousands of compute nodes which increases the likelihood of faults. Applications use checkpoint/restart to recover from these faults, but even under ideal conditions, applications running on more than 30,000 nodes will likely spend more than half of their total run time saving checkpoints, restarting, and redoing work that was lost. We created a library that performs redundant computations on additional nodes allocated to the application. An active node and its redundant partner form a node bundle which will only fail, and cause an application restart, when both nodes in the bundle fail. The goal of this library is to learn whether this can be done entirely at the user level, what requirements this library places on a Reliability, Availability, and Serviceability (RAS) system, and what its impact on performance and run time is. We find that our redundant MPI layer library imposes a relatively modest performance penalty for applications, but that it greatly reduces the number of applications interrupts. This reduction in interrupts leads to huge savings in restart and rework time. For large-scale applications the savings compensate for the performance loss and the additional nodes required for redundant computations.

BACKGROUND: SNOMED CT is being increasingly adopted as the standard clinical terminology for health care applications. Existing clinical applications that use legacy interface terminology need to migrate to the preferred SNOMED CT standard. In this paper, we describe our experience and methodology for mapping concepts from a legacy system to SNOMED CT. METHODS: Our approach includes the establishment of mapping rules between terminologists and back and forth collaboration of the mapped results through one or more iterations in order to reach consensus on the final maps. RESULTS: We highlight our results not only in terms of the number of matches, quality of maps, use of post-coordination, and multiple maps but also include our observations about SNOMED CT including inconsistencies, redundancies and omissions related to our legacy mapping. CONCLUSION: Our methodology and lessons learned from this mapping exercise may be helpful to other terminologists who may be similarly challenged to migrate their legacy terminology to SNOMED CT. This mapping process and resulting discoveries about SNOMED CT may further contribute to refinement of this dynamic, clinical terminology standard.

Ethernet is constantly evolving, adapting to the needs of the networking world, addressing the requirements of both operators and end users, while making sure that the resulting technology is cost-efficient, reliable, and operates in a plug-and-play manner. The IEEE 802.3 Working Group has been working for the last 30+ years, pushing the boundaries on the speed and capacity of wireline Ethernet links, migrating from shared medium CSMA/CD systems to switched point-to-point Ethernet and then introducing multilane technology and point-to-point emulation over shared media of passive optical networks. In this article, we look at the latest projects adding new features and capabilities to the family of wired Ethernet standards, enabling the exponential growth of the Ethernet ecosystem, driven by technical maturity, cost effectiveness, and broad market support.

The detection and analysis of contaminants in soils, sediments, and solid wastes is currently a common problem. This paper examines applying automated supercritical fluid extraction (SFE) systems to examples of common environmental problems: petroleum products from leaking underground storage tanks and polychlorinated biphenyls from oil. Contaminants are extracted using SFE and analyzed by gas chromatography (GC), high-pressure liquid chromatography (HPLC), and mass spectrometry GC-MS. The total petroleum hydrocarbon (TPH) extraction was performed according to the Environmental Protection Agency's (EPA) Draft Method 3560. Work with polyaromatic hydrocarbons (PAH) is a first step toward deriving a similar EPA SFE method. The PCB from oil matrix work was done to explore whether SFE would decrease coextractant interferences with the GC-MS analysis relative to established manual procedures, thereby affording lower detection levels and improved quantitation. The following will be presented: a description of a fully automated system consisting of an SFE coupled to a GC (TPH assay), inter laboratory results for PAH (HPLC analysis), and a comparison of the extract cleanliness of PCB-containing fractions obtained with manual and SFE methods.

This work describes two data center efficiency metrics: Power Usage Effectiveness (PUE) and Compute Power Efficiency (CPE). PUE characterizes the fraction of the total data center power used for IT work. CPE characterizes the overall data center efficiency, considering IT equipment utilization as well as how power is used in the data center. The PUE results from three data center studies are presented here. The data suggests that a carefully designed and managed data center has a PUE of 2.0. More studies are required to determine the range of values for the typical data center. A data center infrastructure and energy cost model is presented to compare hardware costs to infrastructure and energy costs. The impact of PUE on these costs is examined to illustrate the impact of data center efficiency on the total cost of operating a data center.

In the literature of the coaching profession, the voice of the client is rarely heard. This case study examines the coaching process from the perspective of both the coach and the participant, providing unique insights into the art of coaching. Beginning with background descriptions of the coach and the participant, the authors move into a discussion of the first coaching engagement, which began in 2000. Two years later, after Jennifer had been promoted into a larger and more complex assignment, the authors began working together again. The authors discuss highlights of the coaching experience from each of their perspectives and compare what was similar and different across the 2 coaching engagements.