High-performance computing and networking as tools for accurate emission computed tomography reconstruction.

The usefulness and complementarity of gallium (67Ga) scintigraphy and computed tomography (CT) in the management of patients with lymphoma have been extensively demonstrated. Owing to a lack of anatomical landmarks and physiological distribution of the tracer, precise localisation of abnormalities on 67Ga scintigraphy can be difficult. As fusion imaging techniques between single-photon emission tomography (SPET) and CT have been developed recently, we investigated whether use of CT/67Ga SPET fusion imaging could help in the interpretation of 67Ga scintigraphy. From November 1999 to May 2001, 52 consecutive fusion studies were performed in 38 patients [22 patients with Hodgkin's disease (HD) and 16 patients with non-Hodgkin's lymphoma (NHL)] as part of pre-treatment staging (n=13), treatment evaluation (n=20) or evaluation of suspected recurrence (n=19). 67Ga scintigraphy was carried out 2 and 6 days following the injection of 185-220 MBq 67Ga citrate. On day 2, 67Ga SPET and CT were performed, focussing on the chest and/or the abdomen/pelvis. Data from each imaging method were co-registered using external markers. 67Ga scintigraphy and CT were initially interpreted independently by nuclear medicine physicians and radiologists. CT/67Ga SPET fusion studies were then jointly interpreted and both practitioners indicated when fusion provided additional information in comparison with CT and 67Ga SPET alone. Image fusion was considered to be of benefit in 12/52 (23%) studies which were performed for initial staging (n=4), treatment evaluation (n=4) or evaluation of suspected recurrence (n=4). In these cases, image fusion allowed either confirmation and/or localisation of pathological gallium uptake (n=10) or detection of lesions not visible on CT scan (n=2). Fusion was relevant for discrimination between osseous lesions and lymph node involvement adjacent to bone, especially in the thoracic and lumbar spine and pelvis. In the abdomen and pelvis, fusion helped to differentiate physiological bowel elimination from abnormal uptake, and assisted in precisely locating uptake in neighbouring viscera of the left hypochondrium, including the spleen, left liver lobe, coeliac area, stomach wall and even the splenic flexure. At the thoracic level, fusion also proved useful for demonstrating clearly the relationships of abnormal foci to the pleura, hepatic dome, mediastinum, ribs or thoracic spine. Clinical management was altered by fusion imaging in one patient (chemotherapy was given instead of radiotherapy) and was potentially affected in three other patients (in that, in conjunction with other factors, the results of fusion imaging had an influence on the decision regarding use of irradiation and especially the treatment volume). In conclusion, CT/67Ga SPET fusion imaging allowed precise localisation of gallium uptake and correct attribution to the involved viscera, thereby altering the diagnosis in 20%-25% of studies in comparison with CT and 67Ga SPET analyses alone. CT/67Ga SPET fusion therefore appears valuable in facilitating the interpretation of 67Ga scintigraphy and we recommend its use in patients with lymphoma when CT and 67Ga scintigraphy are planned.

While High-Performance Computing (HPC) resources are powerful for tackling complex, computationally intensive analysis and modeling problems, access to these resources varies across disciplines. Domain scientists in a variety of fields such as social and environmental sciences often lack in-depth technical skills (e.g., familiarity with terminal, knowledge of job schedulers) to effectively utilize HPC resources, hindering desired research. In this context, CyberGIS-Compute is a middleware toolkit designed to democratize HPC access with the main goal of enabling domain scientists in diverse fields to solve computationally intensive problems. A key challenge facing model developers on CyberGIS-Compute is to create a containerized software environment for their models. Domain experts unfamiliar with HPC are generally unfamiliar with containerization technologies (e.g., Docker, Singularity) and thus unable to create/test containers to execute their models. But if they have access to science gateways, they would want to use these familiar software environments on HPC resources. This paper describes a novel approach to integrating the Cern Virtual Machine File System (CVMFS) into CyberGIS-Compute to provide consistent software environments across science gateways and HPC resources.

Abstract. Permafrost thaw has been observed at several locations across the Arctic tundra in recent decades; however, the pan-Arctic extent and spatiotemporal dynamics of thaw remains poorly explained. Thaw-induced differential ground subsidence and dramatic microtopographic transitions, such as transformation of low-centered ice-wedge polygons (IWPs) into high-centered IWPs can be characterized using very high spatial resolution (VHSR) commercial satellite imagery. Arctic researchers demand for an accurate estimate of the distribution of IWPs and their status across the tundra domain. The entire Arctic has been imaged in 0.5 m resolution by commercial satellite sensors; however, mapping efforts are yet limited to small scales and confined to manual or semi-automated methods. Knowledge discovery through artificial intelligence (AI), big imagery, and high performance computing (HPC) resources is just starting to be realized in Arctic science. Large-scale deployment of VHSR imagery resources requires sophisticated computational approaches to automated image interpretation coupled with efficient use of HPC resources. We are in the process of developing an automated Mapping Application for Permafrost Land Environment (MAPLE) by combining big imagery, AI, and HPC resources. The MAPLE uses deep learning (DL) convolutional neural nets (CNNs) algorithms on HPCs to automatically map IWPs from VHSR commercial satellite imagery across large geographic domains. We trained and tasked a DLCNN semantic object instance segmentation algorithm to automatically classify IWPs from VHSR satellite imagery. Overall, our findings demonstrate the robust performances of IWP mapping algorithm in diverse tundra landscapes and lay a firm foundation for its operational-level application in repeated documentation of circumpolar permafrost disturbances.

Biomedical data are quickly growing in volume and in variety, providing clinicians an opportunity for better clinical decision support. Here, we demonstrate a robust platform that uses software automation and high performance computing (HPC) resources to achieve real-time analytics of clinical data, specifically magnetic resonance imaging (MRI) data. We used the Agave application programming interface to facilitate communication, data transfer, and job control between an MRI scanner and an off-site HPC resource. In this use case, Agave executed the graphical pipeline tool GRAphical Pipeline Environment (GRAPE) to perform automated, real-time, quantitative analysis of MRI scans. Same-session image processing will open the door for adaptive scanning and real-time quality control, potentially accelerating the discovery of pathologies and minimizing patient callbacks. We envision this platform can be adapted to other medical instruments, HPC resources, and analytics tools.

In this paper, we are demonstrating the implementation flow of algorithms using deep Convolutional Neural Networks (CNN). Deploying CNNs solely on CPU-GPU based platforms deal with issues of high power consumption and comparatively slower processing speeds than hardware accelerators like FPGA. FPGA offers high parallel-processing capability, hardware re-configurability, reduced latency and low power consumption. To further improve flexibility in programming the hardware accelerator, we decided to use High Level Synthesis (HLS) tool based on OpenCL framework for development of our CNN model and implementing it on cloud. We are using Xilinx SDAccel development environment targeting Amazon’s AWS EC2 F1 instances. We are using Cloud based services for our model visualization on FPGAs. Cloud provides FPGA as a service with High Performance Computing (HPC) resources and enables us to deploy our optimized code on provided FPGA accelerated instance without need of buying an actual hardware. AWS EC2 F1 instance uses Xilinx Ultrascale+VU9P chip as a Hardware platform.

The NERSC Web Toolkit (NEWT) brings High Performance Computing (HPC) to the web through easy to write web applications. Our work seeks to make HPC resources more accessible and useful to scientists who are more comfortable with the web than they are with command line interfaces. The effort required to get a fully functioning web application is decreasing, thanks to Web 2.0 standards and protocols such as AJAX, HTML5, JSON and REST. We believe HPC can speak the same language as the web, by leveraging these technologies to interface with existing grid technologies. NEWT presents computational and data resources through simple transactions against URIs. In this paper we describe our approach to building web applications for science using a RESTful web service. We present the NEWT web service and describe how it can be used to access HPC resources in a web browser environment using AJAX and JSON. We discuss our REST API for NEWT, and address specific challenges in integrating a heterogeneous collection of backend resources under a single web service. We provide examples of client side applications that leverage NEWT to access resources directly in the web browser. The goal of this effort is to create a model whereby HPC becomes easily accessible through the web, allowing users to interact with their scientific computing, data and applications entirely through such web interfaces.

It is our great pleasure to welcome you to the fourth workshop on high performance computational finance at the SC'11 International Conference for High Performance Computing, Networking, Storage and Analysis which is being held on Sunday the 13th of November in Seattle. The purpose of this workshop is to bring together practitioners, researchers, vendors, and scholars from the complementary fields of computational finance and high performance computing, in order to promote an exchange of ideas, discuss future collaborations and develop new research directions. Financial companies increasingly rely on high performance computers to analyze high volumes of financial data, automatically execute trades, and manage risk. As financial market data continues to grow in volume and complexity, and algorithmic trading grows in popularity, there is increased demand for computational power. Recent years have seen the dramatic increase in compute capabilities across a variety of systems. The systems have also become more complex with trends towards heterogeneous systems consisting of general-purpose cores and acceleration devices. With this emergence arises the need for extracting the performance from these systems without significant programming effort, which is not affordable in highly paced financial environments. Domain Specific Languages (DSLs) have resurged as an efficient way to meet these challenges. DSLs for computational finance is therefore the theme for the 2011 workshop. We have assembled a diverse program, consisting of four keynotes and five technical presentations selected by a program committee of prominent experts in computational finance and high performance computing. Our speakers represent the finance industry, computer vendors and academia and will contribute to a program which will address the broader challenges of designing large-scale high performance computing infrastructure for the finance industry in addition to specific implementation challenges in computational finance. We are confident that this workshop will continue to build on the success of the previous workshops by stimulating research in the area of high performance computational finance.

Third conference on hypercube concurrent computers and applications

In this work we announce and evaluate a high throughput virtual screening pipeline for in-silico screening of virtual compound databases using high performance computing (HPC). Notable features of this pipeline are an automated receptor preparation scheme with unsupervised binding site identification. The pipeline includes receptor/target preparation, ligand preparation, VinaLC docking calculation, and molecular mechanics/generalized Born surface area (MM/GBSA) rescoring using the GB model by Onufriev and co-workers [J. Chem. Theory Comput. 2007, 3, 156-169]. Furthermore, we leverage HPC resources to perform an unprecedented, comprehensive evaluation of MM/GBSA rescoring when applied to the DUD-E data set (Directory of Useful Decoys: Enhanced), in which we selected 38 protein targets and a total of ∼0.7 million actives and decoys. The computer wall time for virtual screening has been reduced drastically on HPC machines, which increases the feasibility of extremely large ligand database screening with more accurate methods. HPC resources allowed us to rescore 20 poses per compound and evaluate the optimal number of poses to rescore. We find that keeping 5-10 poses is a good compromise between accuracy and computational expense. Overall the results demonstrate that MM/GBSA rescoring has higher average receiver operating characteristic (ROC) area under curve (AUC) values and consistently better early recovery of actives than Vina docking alone. Specifically, the enrichment performance is target-dependent. MM/GBSA rescoring significantly out performs Vina docking for the folate enzymes, kinases, and several other enzymes. The more accurate energy function and solvation terms of the MM/GBSA method allow MM/GBSA to achieve better enrichment, but the rescoring is still limited by the docking method to generate the poses with the correct binding modes.

A large percentage of colleges and universities in the world do not have a HPC culture existing on campus, where access to supercomputing resources (hardware) or supercomputing personnel (faculty and technical staff) and the need to work on grand challenge applications (GCA) is considerably absent. Incorporating courses related to HPC in such institutions presents multiple challenges - non-availability of HPC resources, academic staff trained in HPC related areas, inertia faced in changing the curriculum, absence of a tangible local industry, paucity of funds, lack of enthusiasm among academicians and perceived ignorance. This paper presents a classification of institutions based on three HPC related criteria and highlights the challenges faced in introducing HPC related courses into institutions that do not have a HPC culture. Experiences related to introducing HPC related topics in two institutions, PACE in India and KKU in Saudi Arabia, falling in two different regions in the classification, have been highlighted.

Usually, scientific applications outlive the lifespan of the High Performance Computing (HPC) systems for which they are initially developed. The innovations in the HPC systems’ hardware and parallel programming standards drive the modernization of HPC applications so that they continue being performant. While such code modernization efforts may not be challenging for HPC experts and well-funded research groups, many domain-experts and students may find it challenging to adapt their applications for the latest HPC systems due to lack of expertise, time, and funds. The challenges of such domain-experts and students can be mitigated by providing them high-level tools for code modernization and migration. A brief overview of two such high-level tools is presented in this chapter. These tools support the code modernization and migration efforts by assisting users in parallelizing their applications and porting them to HPC systems with high-bandwidth memory. The tools are named as: Interactive Parallelization Tool (IPT) and Interactive Code Adaptation Tool (ICAT). Such high-level tools not only improve the productivity of their users and the performance of the applications but they also improve the utilization of HPC resources.

High-performance computing (HPC) has become a critical enabler of scientific advancement across many research domains. As the HPC user community continues to expand, there is an increasing need to reduce barriers to entry and improve accessibility for researchers with varying levels of computational expertise. This paper presents a modular, responsive, and user-friendly web-based dashboard built upon the Open OnDemand framework. The system integrates several redesigned functional pages, providing streamlined access to announcements, system status, job information, and resource usage. By consolidating these capabilities into an intuitive interface with a modern design, the dashboard enhances user experience, reduces reliance on command-line tools, and facilitates more efficient interaction with HPC resources.

Our aim is to develop a physically correct simulation of blood flow through intracranial aneurysms. It shall provide means to estimate rupture risks by calculating the distribution of pressure and shear stresses in an intracranial aneurysm, in order to support the planning of clinical interventions. Due to the time-critical nature of the application, we are forced to use the most efficient state-of-the-art numerical methods and technologies together with high performance computing (HPC) infrastructures. The Navier-Stokes equations for the blood flow are discretized via the finite element method (FEM), and the resulting linear equation systems are handled by an algebraic multigrid (AMG) solver. First comparisons of our simulation results with commercial CFD (computational fluid dynamics) software already show good medical relevance for diagnostic decision support. Another challenge is the visualization of our simulation results at acceptable interaction response rates. Physicians require quick and highly interactive visualization of velocity, pressure and stress to be able to assess the rupture risk of an individual vessel morphology. To meet these demands, parallel visualization techniques and high performance computing resources are utilized. In order to provide physicians with access to remote HPC resources which are not available at every hospital, computing infrastructure of the Austrian Grid is utilized for simulation and visualization.

The meteorological high-performance computing resource is the support platform for the weather forecast and climate prediction numerical model operation. The scientific and objective method to evaluate the application of meteorological high-performance computing resources can not only provide reference for the optimization of active resources, but also provide a quantitative basis for future resource construction and planning. In this paper, the concept of the utility value B and index compliance rate E of the meteorological high performance computing system are presented. The evaluation process, evaluation index and calculation method of the high performance computing resource application benefits are introduced.

분자 동역학 기법을 사용한 재료 파괴 시뮬레이션은 계산량의 방대함으로 인하여 극히 최근까지 활발한 연구가 진행되지 못하였으나 최근 컴퓨터의 성능향상으로 인하여 새로운 연구분야로 떠오르고 있다. 분자 동역학은 그 특성상 계산 집약적인 환경을 요구함으로 대규모의 연산을 위해서는 슈퍼컴퓨터나 클러스터(cluster)의 사용이 필수적이나 고가의 장비와 사용료로 인하여 많은 제한을 받아왔다. 본 연구에서는 PC를 사용하여 클러스터를 제작하고, 균열이 있는 시편을 사용하여 파괴현상에 대한 분자 수준의 거동을 시뮬레이션 하였으며, 클러스터의 노드(node) 수, 효율, 분자 수, 노드간의 통신시간 등의 상호관계를 파악하여 최적의 성능을 가진 클러스터를 구성하는 데 필요한 요소들을 분석하였다. 제작된 PC 클러스터를 사용하여 약 50,000개의 분자를 사용한 재료 파괴 시뮬레이션을 수행하였다. For molecular dynamics requires high-performance computers or supercomputers to handle huge amount of computation, it is not until recent days that the application of molecular dynamics to materials fracture simulations draw some attention from many researchers. With the recent advent of high-performance computers, computation intensive methods become more tractable than ever. However, carrying out materials simulation on high-performance computers costs too much in general. In this study, a PC cluster consisting of multiple commodity PCs is established and computer simulations of materials with cracks are carried out on it via molecular dynamics technique. The effect of the number of nodes, speedup factors, and communication time between nodes are measured to verify the performance of the PC cluster. Upon using the PC cluster, materials fracture simulations with more than 50,000 molecules are carried out successfully.