AN MPI PERFORMANCE MONITORING INTERFACE FOR CELL BASED COMPUTE NODES

2009 ◽  
Vol 19 (04) ◽  
pp. 535-552
Author(s):  
HIKMET DURSUN ◽  
KEVIN J. BARKER ◽  
DARREN J. KERBYSON ◽  
SCOTT PAKIN ◽  
RICHARD SEYMOUR ◽  
...  

In this paper, we present a methodology for profiling parallel applications executing on the family of architectures commonly referred as the "Cell" processor. Specifically, we examine Cell-centric MPI programs on hybrid clusters containing multiple Opteron and IBM PowerXCell 8i processors per node such as those used in the petascale Roadrunner system. We analyze the performance of our approach on a PlayStation3 console based on Cell Broadband Engine—the CBE—as well as an IBM BladeCenter QS22 based on PowerXCell 8i. Our implementation incurs less than 0.5% overhead and 0.3 µs per profiler call for a typical molecular dynamics code on the Cell BE while efficiently utilizing the limited local store of the Cell's SPE cores. Our worst-case overhead analysis on the PowerXCell 8i costs 3.2 µs per profiler call while using only two 5 KiB buffers. We demonstrate the use of our profiler on a cluster of hybrid nodes running a suite of scientific applications. Our analyses of inter-SPE communication (across the entire cluster) and function call patterns provide valuable information that can be used to optimize application performance.

1984 ◽  
Vol 99 (1) ◽  
pp. 95s-103s ◽  
Author(s):  
P Mangeat ◽  
K Burridge

In this review we discuss some of the proteins for which a role in linking actin to the fibroblast plasma membrane has been suggested. We focus on the family of proteins related to erythrocyte spectrin, proteins that have generally been viewed as having an organization and a function in actin-membrane attachment similar to those of erythrocyte spectrin. Experiments in which we precipitated the nonerythrocyte spectrin within living fibroblasts have led us to question this supposed similarity of organization and function of the nonerythrocyte and erythrocyte spectrins. Intracellular precipitation of fibroblast spectrin does not affect the integrity of the major actin-containing structures, the stress fiber microfilament bundles. Unexpectedly, however, we found that the precipitation of spectrin results in a condensation and altered distribution of the vimentin class of intermediate filaments in most cells examined. Although fibroblast spectrin may have a role in the attachment of some of the cortical, submembranous actin, it is surprising how little the intracellular immunoprecipitation of the spectrin affects the cells. Several proteins have been found concentrated at the ends of stress fibers, where the actin filaments terminate at focal contacts. Two of these proteins, alpha-actinin and fimbrin, have properties that suggest that they are not involved in the attachment of the ends of the bundles to the membrane but are more probably involved in the organization and cross-linking of the filaments within the bundles. On the other hand, vinculin and talin are two proteins that interact with each other and may form part of a chain of attachments between the ends of the microfilament bundles and the focal contact membrane. Their role in this attachment, however, has not been established and further work is needed to examine their interaction with actin and to identify any other components with which they may interact, particularly in the plasma membrane.


Genetics ◽  
2003 ◽  
Vol 165 (2) ◽  
pp. 613-621 ◽  
Author(s):  
Douglas R Dorer ◽  
Jamie A Rudnick ◽  
Etsuko N Moriyama ◽  
Alan C Christensen

Abstract Within the unique Triplo-lethal region (Tpl) of the Drosophila melanogaster genome we have found a cluster of 20 genes encoding a novel family of proteins. This family is also present in the Anopheles gambiae genome and displays remarkable synteny and sequence conservation with the Drosophila cluster. The family is also present in the sequenced genome of D. pseudoobscura, and homologs have been found in Aedes aegypti mosquitoes and in four other insect orders, but it is not present in the sequenced genome of any noninsect species. Phylogenetic analysis suggests that the cluster evolved prior to the divergence of Drosophila and Anopheles (250 MYA) and has been highly conserved since. The ratio of synonymous to nonsynonymous substitutions and the high codon bias suggest that there has been selection on this family both for expression level and function. We hypothesize that this gene family is Tpl, name it the Osiris family, and consider possible functions. We also predict that this family of proteins, due to the unique dosage sensitivity and the lack of homologs in noninsect species, would be a good target for genetic engineering or novel insecticides.


Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1590
Author(s):  
Arnak Poghosyan ◽  
Ashot Harutyunyan ◽  
Naira Grigoryan ◽  
Clement Pang ◽  
George Oganesyan ◽  
...  

The main purpose of an application performance monitoring/management (APM) software is to ensure the highest availability, efficiency and security of applications. An APM software accomplishes the main goals through automation, measurements, analysis and diagnostics. Gartner specifies the three crucial capabilities of APM softwares. The first is an end-user experience monitoring for revealing the interactions of users with application and infrastructure components. The second is application discovery, diagnostics and tracing. The third key component is machine learning (ML) and artificial intelligence (AI) powered data analytics for predictions, anomaly detection, event correlations and root cause analysis. Time series metrics, logs and traces are the three pillars of observability and the valuable source of information for IT operations. Accurate, scalable and robust time series forecasting and anomaly detection are the requested capabilities of the analytics. Approaches based on neural networks (NN) and deep learning gain an increasing popularity due to their flexibility and ability to tackle complex nonlinear problems. However, some of the disadvantages of NN-based models for distributed cloud applications mitigate expectations and require specific approaches. We demonstrate how NN-models, pretrained on a global time series database, can be applied to customer specific data using transfer learning. In general, NN-models adequately operate only on stationary time series. Application to nonstationary time series requires multilayer data processing including hypothesis testing for data categorization, category specific transformations into stationary data, forecasting and backward transformations. We present the mathematical background of this approach and discuss experimental results based on implementation for Wavefront by VMware (an APM software) while monitoring real customer cloud environments.


Author(s):  
Diana Hamdan ◽  
Lisa A. Robinson

Excessive infiltration of immune cells into the kidney is a key feature of acute and chronic kidney diseases. The family of chemokines are key drivers of this process. CX3CL1 (fractalkine) is one of two unique chemokines synthesized as a transmembrane protein which undergoes proteolytic cleavage to generate a soluble species. Through interacting with its cognate receptor, CX3CR1, CX3CL1 was originally shown to act as a conventional chemoattractant in the soluble form, and as an adhesion molecule in the transmembrane form. Since then, other functions of CX3CL1 beyond leukocyte recruitment have been described, including cell survival, immunosurveillance, and cell-mediated cytotoxicity. This review summarizes diverse roles of CX3CL1 in kidney disease and potential uses as a therapeutic target and novel biomarker. As the CX3CL1-CX3CR1 axis has been shown to contribute to both detrimental and protective effects in various kidney diseases, a thorough understanding of how the expression and function of CX3CL1 are regulated is needed to unlock its therapeutic potential.


2009 ◽  
Vol 17 (1-2) ◽  
pp. 135-151 ◽  
Author(s):  
Guochun Shi ◽  
Volodymyr V. Kindratenko ◽  
Ivan S. Ufimtsev ◽  
Todd J. Martinez ◽  
James C. Phillips ◽  
...  

The Cell Broadband Engine architecture is a revolutionary processor architecture well suited for many scientific codes. This paper reports on an effort to implement several traditional high-performance scientific computing applications on the Cell Broadband Engine processor, including molecular dynamics, quantum chromodynamics and quantum chemistry codes. The paper discusses data and code restructuring strategies necessary to adapt the applications to the intrinsic properties of the Cell processor and demonstrates performance improvements achieved on the Cell architecture. It concludes with the lessons learned and provides practical recommendations on optimization techniques that are believed to be most appropriate.


2018 ◽  
Author(s):  
Rois Ainul Umah ◽  
Tian Fitriara Huda ◽  
(Prosiding Seminar Nasional FKIP Univeristas PGRI Banyuwangi

Banyuwangi is an area rich in various cultures and customs, this is because Banyuwangi district is inhabited by various ethnic groups. The majority of the sub-districts of Banyuwangi are osing tribe who live in the village of fern and urban village of rejo. Joglo building as one of the traditional Javanese buildings in it contained philosophy that suits the life of the people. The arrangement of the room in Joglo is generally divided into three parts, namely the meeting room called pendopo, the living room or the space used to hold the show called pringgitan, and the back room called dalem or omah jero as the family room. For the people of Banyuwangi especially those who still preserve the joglo house just like the osing tribe have begun to experience the shifting of its role and function where in this case joglo house serve as additional need for home decoration, private residence of the citizen, until used as permanent building of cafe and restaurant. From the description above, the researcher felt that the community did not understand the function of the role and shape of the architecture of the Javanese house which has become the culture of the inheritance slowly changed by causing a shift to the cultural values contained within it. The shift in value will sooner or later bring changes to traditional architectural forms, structures and functions.


Author(s):  
Norikazu Ikoma ◽  
◽  
Akihiro Asahara ◽  

Real time visual tracking by particle filter has been implemented on Cell Broadband Engine in parallel. Major problem for the implementation is small size of Local Store (LS) in SPEs (Synergistic PEs), which are computational cores, to deal with image of large size. As a first step for the implementation, we focus on color single object tracking, which is one of the most simple case of visual tracking. By elaborating to compress the color extracted image into bit-wise representation of binary image, all information of the color extracted image can be stored in LS for 640×480 size of original image. By applying our previous implementation of general particle filter algorithm on Cell/B.E. to this specific case, we have achieved real time performance of visual tracking on PlayStation®3 about 7 fps with a camera of maximum 15 fps.


Author(s):  
Roman Andriushchenko ◽  
Milan Češka ◽  
Sebastian Junges ◽  
Joost-Pieter Katoen

AbstractThis paper presents a novel method for the automated synthesis of probabilistic programs. The starting point is a program sketch representing a finite family of finite-state Markov chains with related but distinct topologies, and a reachability specification. The method builds on a novel inductive oracle that greedily generates counter-examples (CEs) for violating programs and uses them to prune the family. These CEs leverage the semantics of the family in the form of bounds on its best- and worst-case behaviour provided by a deductive oracle using an MDP abstraction. The method further monitors the performance of the synthesis and adaptively switches between inductive and deductive reasoning. Our experiments demonstrate that the novel CE construction provides a significantly faster and more effective pruning strategy leading to an accelerated synthesis process on a wide range of benchmarks. For challenging problems, such as the synthesis of decentralized partially-observable controllers, we reduce the run-time from a day to minutes.


Sign in / Sign up

Export Citation Format

Share Document