scholarly journals Characterization of MPI Communication Primitives on a Heterogeneous Cluster

2009 ◽  
Vol 6 (2) ◽  
pp. 23
Author(s):  
Siti Arpah Ahmad ◽  
Mohamed Faidz Mohamed Said ◽  
Norazan Mohamed Ramli ◽  
Mohd Nasir Taib
Keyword(s):  
Message Passing ◽  
High Performance ◽  
Data Transfer ◽  
The Other ◽  
Small Cluster ◽  
Heterogeneous Cluster ◽  
Processing Power ◽  
Basic Performance ◽  
Point To Point

This paper focuses on the performance of basic communication primitives, namely the overlap of message transfer with computation in the point-to-point communication within a small cluster of four nodes. The mpptest has been implemented to measure the basic performance of MPI message passing routines with a variety of message sizes. The mpptest is capable of measuring performance with many participating processes thus exposing contention and scalability problems. This enables programmers to select message sizes in order to isolate and evaluate sudden changes in performance. Investigating these matters is interesting in that non-blocking calls have the advantage of allowing the system to schedule communications even when many processes are running simultaneously. On the other hand, understanding the characteristics of computation and communication overlap is significant, because high- performance kernels often strive to achieve this, since it is both advantageous with respect to data transfer and latency hiding. The results indicate that certain overlap sizes utilize greater node processing power either in blocking send and receive operations or non-blocking send and receive operations. The results have elucidated a detailed MPI characterization of the performance regarding the overlap of message transfer with computation in a small cluster system. 

scholarly journals Improving data transfer for model coupling

2015 ◽  
Vol 8 (10) ◽  
pp. 8981-9020 ◽  
Author(s):  
C. Zhang ◽  
L. Liu ◽  
G. Yang ◽  
R. Li ◽  
B. Wang
Keyword(s):  
Performance Improvement ◽  
Message Passing ◽  
Message Passing Interface ◽  
Data Transfer ◽  
The Public ◽  
Message Size ◽  
Abstract Data ◽  
Point To Point ◽  
Component Models ◽  
Size Variable

Abstract. Data transfer, which means transferring data fields between two component models or rearranging data fields among processes of the same component model, is a fundamental operation of a coupler. Most of state-of-the-art coupler versions currently use an implementation based on the point-to-point (P2P) communication of the Message Passing Interface (MPI) (call such an implementation "P2P implementation" for short). In this paper, we reveal the drawbacks of the P2P implementation, including low communication bandwidth due to small message size, variable and big number of MPI messages, and jams during communication. To overcome these drawbacks, we propose a butterfly implementation for data transfer. Although the butterfly implementation can outperform the P2P implementation in many cases, it degrades the performance in some cases because the total message size transferred by the butterfly implementation is larger than that by the P2P implementation. To make the data transfer completely improved, we design and implement an adaptive data transfer library that combines the advantages of both butterfly implementation and P2P implementation. Performance evaluation shows that the adaptive data transfer library significantly improves the performance of data transfer in most cases and does not decrease the performance in any cases. Now the adaptive data transfer library is open to the public and has been imported into a coupler version C-Coupler1 for performance improvement of data transfer. We believe that it can also improve other coupler versions.

Design and characterization of a T-shaped two-axis force sensor

Sensor Review ◽  
2019 ◽  
Vol 39 (6) ◽  
pp. 776-782
Author(s):  
Liang Zhong ◽  
Feifei Li ◽  
Yuxin Peng ◽  
Qiang Yang ◽  
Mingming Zhang ◽  
...  
Keyword(s):  
Design Methodology ◽  
Simple Structure ◽  
Force Sensor ◽  
The Other ◽  
Strain Gauges ◽  
Content Type ◽  
Sensor Head ◽  
Compact Size ◽  
Basic Performance

Purpose This paper aims to propose a type of T-shaped two-axis force sensor for measuring the forces in x- and z-axes. The developed sensor has a simple structure and can be effectively assembled into compact devices. Design/methodology/approach A T-shaped plate, with both ends fixed on a base, is used as the substrate of the sensor. Eight strain gauges are placed in the root of the plate or near the sensor head, which can construct two full Wheatstone bridges on the upper and lower surfaces of the plate. When the x- or z-axes forces are applied to the sensor head, different deformation can be generated to the strain gauges. Therefore, the two Wheatstone bridges can be constructed with a different configuration for measuring the forces in x- or z-axes, respectively. Findings A prototype was designed and constructed and experiments were carried out to test the basic performance of the sensor. It has been verified that the developed sensor could measure the x- and z-axes forces independently with a high resolution of 2.5 and 5 mN, respectively. Originality/value Only one thin plate was used in the design, the forces in x- and z-axes could be measured independently and simultaneously, which made the sensor with a simple structure and compact size. Experiments were also verified that there was no crosstalk error occurred in one axis when the force was applied to the other axis.

scholarly journals A new adaptive data transfer library for model coupling

2016 ◽  
Vol 9 (6) ◽  
pp. 2099-2113
Author(s):  
Cheng Zhang ◽  
Li Liu ◽  
Guangwen Yang ◽  
Ruizhe Li ◽  
Bin Wang
Keyword(s):  
Performance Improvement ◽  
Message Passing ◽  
Message Passing Interface ◽  
Data Transfer ◽  
State Of The Art ◽  
The Public ◽  
Abstract Data ◽  
Network Contention ◽  
Point To Point ◽  
Size Variable

Abstract. Data transfer means transferring data fields from a sender to a receiver. It is a fundamental and frequently used operation of a coupler. Most versions of state-of-the-art couplers currently use an implementation based on the point-to-point (P2P) communication of the message passing interface (MPI) (referred to as “P2P implementation” hereafter). In this paper, we reveal the drawbacks of the P2P implementation when the parallel decompositions of the sender and the receiver are different, including low communication bandwidth due to small message size, variable and high number of MPI messages, as well as network contention. To overcome these drawbacks, we propose a butterfly implementation for data transfer. Although the butterfly implementation outperforms the P2P implementation in many cases, it degrades the performance when the sender and the receiver have similar parallel decompositions or when the number of processes used for running models is small. To ensure data transfer with optimal performance, we design and implement an adaptive data transfer library that combines the advantages of both butterfly implementation and P2P implementation. As the adaptive data transfer library automatically uses the best implementation for data transfer, it outperforms the P2P implementation in many cases while it does not decrease the performance in any cases. Now, the adaptive data transfer library is open to the public and has been imported into the C-Coupler1 coupler for performance improvement of data transfer. We believe that other couplers can also benefit from this.

scholarly journals The cbiS Gene of the Archaeon Methanopyrus kandleri AV19 Encodes a Bifunctional Enzyme with Adenosylcobinamide Amidohydrolase and α-Ribazole-Phosphate Phosphatase Activities

2006 ◽  
Vol 188 (12) ◽  
pp. 4227-4235 ◽  
Author(s):  
Jesse D. Woodson ◽  
Jorge C. Escalante-Semerena
Keyword(s):  
High Performance ◽  
Biochemical Characterization ◽  
The Other ◽  
Bifunctional Enzyme ◽  
Visible Spectroscopy ◽  
Uv Visible ◽  
Cobyric Acid ◽  
Methanopyrus Kandleri

ABSTRACT Here we report the initial biochemical characterization of the bifunctional α-ribazole-P (α-RP) phosphatase, adenosylcobinamide (AdoCbi) amidohydrolase CbiS enzyme from the hyperthermophilic methanogenic archaeon Methanopyrus kandleri AV19. The cbiS gene encodes a 39-kDa protein with two distinct segments, one of which is homologous to the AdoCbi amidohydrolase (CbiZ, EC 3.5.1.90) enzyme and the other of which is homologous to the recently discovered archaeal α-RP phosphatase (CobZ, EC 3.1.3.73) enzyme. CbiS function restored AdoCbi salvaging and α-RP phosphatase activity in strains of the bacterium Salmonella enterica where either step was blocked. The two halves of the cbiS genes retained their function in vivo when they were cloned separately. The CbiS enzyme was overproduced in Escherichia coli and was isolated to >95% homogeneity. High-performance liquid chromatography, UV-visible spectroscopy, and mass spectroscopy established α-ribazole and cobyric acid as the products of the phosphatase and amidohydrolase reactions, respectively. Reasons why the CbiZ and CobZ enzymes are fused in some archaea are discussed.

Measurement of residual stress by load and depth sensing indentation with spherical indenters

2001 ◽  
Vol 16 (7) ◽  
pp. 2091-2102 ◽  
Author(s):  
J. G. Swadener ◽  
B. Taljat ◽  
G.M. Pharr
Keyword(s):  
Residual Stress ◽  
Surface Stress ◽  
The Other ◽  
Spherical Indentation ◽  
Biaxial Bending ◽  
Depth Sensing ◽  
Unstressed State ◽  
Bending Stresses ◽  
Point To Point

A new experimental technique is presented for making measurements of biaxial residual stress using load and depth sensing indentation (nanoindentation). The technique is based on spherical indentation, which, in certain deformation regimes, can be much more sensitive to residual stress than indentation with sharp pyramidal indenters like the Berkovich. Two different methods of analysis were developed: one requiring an independent measure of the material's yield strength and the other a reference specimen in the unstressed state or other known reference condition. Experiments conducted on aluminum alloys to which controlled biaxial bending stresses were applied showed that the methods are capable of measuring the residual stress to within 10–20% of the specimen yield stress. Because the methods do not require imaging of the hardness impressions, they are potentially useful for making localized measurements of residual stress, as in thin films or small volumes, or for characterization of point-to-point spatial variations of the surface stress.

Treatment of biosolids flushed from sewer systems: characterization of biosolids and the sand extracted and the handling of washing water

1998 ◽  
Vol 38 (10) ◽  
pp. 231-239
Author(s):  
M. Montréjaud-Vignoles ◽  
T. Poujol ◽  
C. Vignoles
Keyword(s):  
Research Program ◽  
High Performance ◽  
Operating Conditions ◽  
The Other ◽  
Sewer Systems ◽  
Other Hand ◽  
Initial Results ◽  
Washing Water

A research program on the characteristics of biosolids flushed from sewer systems in Toulouse (southwest France) and on the quality of sand extracted from these biosolids by hydrocycloning was carried out using samples from different sites. The treatment of washing water through air flotation was also studied. These initial results show the difficulty in establishing a strict typology for each family of flushed biosolids. On the other hand, the measurements done after hydrocycloning the biosolids clearly show that it is possible to imagine high performance treatment centers which would be able to provide a homogeneously treated product only slightly polluted, starting from very variable waste. Under certain operating conditions. The flotation of washing water thus perfectly completes the treatment of biosolids, and allows one to obtain the weakest possible volume of residue.

Characterization of Wide Area Network Computing

2000 ◽  
Author(s):  
Christopher J. Freitas ◽  
Derrick B. Coffin ◽  
Richard L. Murphy
Keyword(s):  
Message Passing ◽  
High Performance ◽  
Local Area ◽  
Wide Area ◽  
Area Network ◽  
Wide Area Network ◽  
Network Computing ◽  
Distributed Parallel Computing ◽  
International Border

Abstract Distributed parallel computing using message-passing techniques on Networks of Workstations (NOW) has achieved widespread use in the context of Local Area Networks (LAN). Recently, the concept of Grid-based computing using Wide Area Networks (WAN) has been proposed as a general solution to distributed high performance computing. The use of computers and resources at different geographic locations connected by a Wide Area Network and executing a real application introduces additional variables that potentially complicate the efficient use of these resources. Presented here are the results of a study that begins to characterize the performance issues of a WAN-based NOW, connecting resources that span an international border.

A very rapid in situ Kikuchi technique to determine relative crystal misorientation

1988 ◽  
Vol 46 ◽  
pp. 830-831
Author(s):  
J. I. Bennetch
Keyword(s):  
Electron Beam ◽  
Analytical Techniques ◽  
Superplastic Forming ◽  
The Other ◽  
Kikuchi Pattern ◽  
Kikuchi Line ◽  
Line Analysis

In a recent study of the superplastic forming (SPF) behavior of certain Al-Li-X alloys, the relative misorientation between adjacent (sub)grains proved to be an important parameter. It is well established that the most accurate way to determine misorientation across boundaries is by Kikuchi line analysis. However, the SPF study required the characterization of a large number of (sub)grains in each sample to be statistically meaningful, a very time-consuming task even for comparatively rapid Kikuchi analytical techniques.In order to circumvent this problem, an alternate, even more rapid in-situ Kikuchi technique was devised, eliminating the need for the developing of negatives and any subsequent measurements on photographic plates. All that is required is a double tilt low backlash goniometer capable of tilting ± 45° in one axis and ± 30° in the other axis. The procedure is as follows. While viewing the microscope screen, one merely tilts the specimen until a standard recognizable reference Kikuchi pattern is centered, making sure, at the same time, that the focused electron beam remains on the (sub)grain in question.

Characterization of Rh/Si multilayer structure by HREM and HAADF

1992 ◽  
Vol 50 (1) ◽  
pp. 122-123
Author(s):  
Y. Cheng ◽  
J. Liu ◽  
M.B. Stearns ◽  
D.G. Steams
Keyword(s):  
Normal Incidence ◽  
High Resolution Electron Microscopy ◽  
X Rays ◽  
Beam Direction ◽  
Cross Sectional ◽  
Optical Elements ◽  
Resolution Electron ◽  
Point To Point ◽  
Better Than

The Rh/Si multilayer (ML) thin films are promising optical elements for soft x-rays since they have a calculated normal incidence reflectivity of ∼60% at a x-ray wavelength of ∼13 nm. However, a reflectivity of only 28% has been attained to date for ML fabricated by dc magnetron sputtering. In order to determine the cause of this degraded reflectivity the microstructure of this ML was examined on cross-sectional specimens with two high-resolution electron microscopy (HREM and HAADF) techniques.Cross-sectional specimens were made from an as-prepared ML sample and from the same ML annealed at 298 °C for 1 and 100 hours. The specimens were imaged using a JEM-4000EX TEM operating at 400 kV with a point-to-point resolution of better than 0.17 nm. The specimens were viewed along Si [110] projection of the substrate, with the (001) Si surface plane parallel to the beam direction.

Preparation and Characterization of NH2-Terminal Fibrinogen Bβ Fragments from N-DSK of Human Fibrinogen

1984 ◽  
Vol 51 (01) ◽  
pp. 016-021 ◽  
Author(s):  
S Birken ◽  
G Agosto ◽  
B Lahiri ◽  
R Canfield
Keyword(s):  
High Performance ◽  
Gel Filtration ◽  
Ion Exchange Chromatography ◽  
Exchange Chromatography ◽  
Reverse Phase ◽  
Human Fibrinogen ◽  
Human Volunteers ◽  
Cnbr Cleavage ◽  
Two Peaks

SummaryIn order to investigate the early release of NH2-terminal plasmic fragments from the Bβ chain of fibrinogen, substantial quantities of Bβ 1-42 and Bβ 1-21 are required as immunogens, as radioimmunoassay standards and for infusion into human volunteers to determine the half-lives of these peptides. Towards this end methods that employ selective proteolytic cleavage of these fragments from fibrinogen have been developed. Both the N-DSK fragment, produced by CNBr cleavage of fibrinogen, and Bβ 1-118 were employed as substrates for plasmin with the finding of higher yields from N-DSK. Bβ 1-42 and Bβ 1-21 were purified by gel filtration and ion-exchange chromatography on SP-Sephadex using volatile buffers. When the purified preparation of Bβ 1-42 was chromatographed on reverse-phase high performance liquid chromatography, two peaks of identical amino acid composition were separated, presumably due either to pyroglutamate or to amide differences.

Sign in / Sign up

Export Citation Format

Share Document