Guilherme Andrade

Ritmo de crescimento de crianças com hiperplasia congênita da supra-renal em tratamento com baixas doses de hidrocortisona

We evaluated linear growth of 27 children with congenital adrenal hyperplasia (CAH) treated with low doses of oral hydrocortisone. They were followed-up during 6.1 +/- 1.8 years with daily hydrocortisone doses of 10.84 +/- 2.0 mg/m2 and 0.1 mg fludrocortisone (24 of them). Twenty-three were female. Mean chronological age (CA) was 6.1 +/- 2.9 years and bone age (BA) 6.9 +/- 3.3 (r = 0.66) at the beginning of the study. Five children showed BA advancement > 2 years relating to CA. It was calculated Height SD for CA (SD/H) and for BA (SD/BA) were calculated using NCHS as reference pattern. At the beginning of the study SD/H was -0.8 +/- 1.9 and corresponding SD/BA was -1.5 +/- 2.1; at the end SD/H was -0.17 +/- 1.5 and SD/BA was -1.34 +/- 1.2 (p = 0.02 and p = 0.51, respectively for the beginning and the end). BA changed 1.3 +/- 0.3 per year during this period. Children with advanced BA showed an improvement of SD/BA, from -4.55 +/- 0.9 at from the beginning, -4.55 +/- 0.9 to -2.48 +/- 0.4 at the end of follow-up, -2.48 +/- 0.4 (p = 0.003). The elevated plasma levels of 17-OH Progesterone (17OHP) and androstenedione showed further increase during follow-up. We conclude that children with CAH receiving low doses of hydrocortisone showed adequate growth during the follow-up, without excessive BA advancement, even though full suppression of plasma levels of 17OHP and androgens wasere not achieved.

Application performance analysis and efficient execution on systems with multi-core CPUs, GPUs and MICs

We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core (MIC)) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core operations of the application. We correlate the observed performance with the characteristics of computing devices and data access patterns, computation complexities, and parallelization forms of the operations. The results show a significant variability in the performance of operations with respect to the device used. The performances of operations with regular data access are comparable or sometimes better on a MIC than that on a GPU. GPUs are more efficient than MICs for operations that access data irregularly, because of the lower bandwidth of the MIC for random data accesses. We propose new performance-aware scheduling strategies that consider variabilities in operation speedups. Our scheduling strategies significantly improve application performance compared with classic strategies in hybrid configurations.

Efficient Execution of Microscopy Image Analysis on CPU, GPU, and MIC Equipped Cluster Systems

High performance computing is experiencing a major paradigm shift with the introduction of accelerators, such as graphics processing units (GPUs) and Intel Xeon Phi (MIC). These processors have made available a tremendous computing power at low cost, and are transforming machines into hybrid systems equipped with CPUs and accelerators. Although these systems can deliver a very high peak performance, making full use of its resources in real-world applications is a complex problem. Most current applications deployed to these machines are still being executed in a single processor, leaving other devices underutilized. In this paper we explore a scenario in which applications are composed of hierarchical dataflow tasks which are allocated to nodes of a distributed memory machine in coarse-grain, but each of them may be composed of several finer-grain tasks which can be allocated to different devices within the node. We propose and implement novel performance aware scheduling techniques that can be used to allocate tasks to devices. We evaluate our techniques using a pathology image analysis application used to investigate brain cancer morphology, and our experimental evaluation shows that the proposed scheduling strategies significantly outperforms other efficient scheduling techniques, such as Heterogeneous Earliest Finish Time - HEFT, in cooperative executions using CPUs, GPUs, and Masc. also experimentally show that our strategies are less sensitive to inaccuracy in the scheduling input data and that the performance gains are maintained as the application scales.

A Genetic Programming approach for feature selection in highly dimensional skewed data

High dimensionality, also known as the curse of dimensionality, is still a major challenge for automatic classification solutions. Accordingly, several feature selection (FS) strategies have been proposed for dimensionality reduction over the years. However, they potentially perform poorly in face of unbalanced data. In this work, we propose a novel feature selection strategy based on Genetic Programming, which is resilient to data skewness issues, in other words, it works well with both, balanced and unbalanced data. The proposed strategy aims at combining the most discriminative feature sets selected by distinct feature selection metrics in order to obtain a more effective and impartial set of the most discriminative features, departing from the hypothesis that distinct feature selection metrics produce different (and potentially complementary) feature space projections. We evaluated our proposal in biological and textual datasets. Our experimental results show that our proposed solution not only increases the efficiency of the learning process, reducing up to 83% the size of the data space, but also significantly increases its effectiveness in some scenarios.

Hierarchical Density-Based Clustering Based on GPU Accelerated Data Indexing Strategy

Due the recent increase of the volume of data that has been generated, organizing this data has become one of the biggest problems in Computer Science. Among the different strategies propose to deal efficiently and effectively for this purpose, we highlight those related to clustering, more specifically, density-based clustering strategies, which stands out for its ability to define clusters of arbitrary shape and the robustness to deal with the presence of data noise, such as DBSCAN and OPTICS. However, these algorithms are still a computational challenge since they are distance-based proposals. In this work we present a new approach to make OPTICS feasible based on data indexing strategy. Although the simplicity with which the data are indexed, using graphs, it allows explore various parallelization opportunities, which were explored using graphic processing unit (GPU). Based on this structure, the complexity of OPTICS is reduced to O(E *logV ) in the worst case, becoming itself very fast. In our evaluation we show that our proposal can be over 200x faster than its sequential version using CPU.

ParallelME: A Parallel Mobile Engine to Explore Heterogeneity in Mobile Computing Architectures

Following the evolution of desktops, mobile architectures are currently witnessing growth in processing power and complexity with the addition of different processing units like multi-core CPUs and GPUs. To facilitate programming and coordinating resource usage in these heterogeneous architectures, we present ParallelME, a ParallelMobile Engine designed to explore heterogeneity in mobile computing architectures. ParallelME provides a high-level library with a friendly programming language abstraction for developers, facilitating the programming of operations that can be translated into low-level parallel tasks. Additionally, these tasks are coordinated by a runtime framework, which is responsible for scheduling and controlling the execution on the low-level platform. ParallelMEs purpose is to explore parallelism with the benefit of not changing the programming model, through a simple programming language abstraction that is similar to sequential programming. We performed a comparative analysis of execution time, memory and power consumption between ParallelME, OpenCL and RenderScript using an image processing application. ParallelME greatly increases application performance with reasonable memory and energy consumption.

Efficient dynamic scheduling of heterogeneous applications in hybrid architectures

The emergence of different applications that deal with growing amounts of data at reasonable times, has stimulated the development of new computing architectures consisting of different processing units (PU). Runtime environments have been proposed in order to exploit these resource as much as possible by offering a variety of methods for dynamically scheduling tasks on different PUs. These schedulers determine which PU is better suited for executing each task, based upon a set of task parameters such as the amount of data, computation requirements, etc. Although large number of applications are heterogeneous, composed of tasks with different characteristics, the current techniques focus on these characteristics as isolated features leading to inefficient executions in several situations. In this work we present two new scheduling strategies, combining different existing strategies, that leads to more efficient executions in different scenarios. Our results show that our approach can be up to 20% more efficient than current techniques.

D-STHARk

The emergence of applications that demand to handle efficiently growing amounts of data has stimulated the development of new computing architectures with several Processing Units (PUs), such as CPUs core, graphics processing units (GPUs) and Intel Xeon Phi (MIC). Aiming to better exploit these architectures, recent works focus on proposing novel runtime environments that offer a variety of methods for scheduling tasks dynamically on different PUs. A main limitation of such proposals refers to the constrained system configurations, usually adopted to tune and test the proposals, since setting more complete and diversified evaluation environments is costly. In this context, we present D-STHARk, a GUI tool for evaluating Dynamic Scheduling of Tasks in Hybrid Simulated ARchitectures. D-STHARk provides a complete simulated execution environment that allows evaluating dynamic scheduling strategies on simulated applications and hybrid architectures. We evaluate our tool by simulating the dynamic scheduling strategies presented in [3], using the same architecture and application. D-STHARk was able to achieve the same conclusions originally reported by the authors. Moreover, we performed an experiment varying the number of coprocessors, which was not previously verified due to lack of real architectures, showing that we may reduce the energy consumption, while keeping the same performance.

Evaluating Dynamic Scheduling of Tasks in Mobile Architectures Using ParallelME Framework

Recently we observe that mobile phones stopped being just devices for basic communication to become providers of many applications that require increasing performance for good user experience. Inside today’s mobile phones we find different processing units (PU) with high computational capacity, as multicore architectures and co-processors like GPUs. Libraries and run-time environments have been proposed to improve applications’ performance by taking advantage of different PUs in a transparent way. Among these environments we can highlight the ParallelME. Despite the importance of task scheduling strategies in these environments, ParallelME has implemented only the First Come Firs Serve (FCFS) strategy. In this paper we extended the ParallelME framework by implementing and evaluating two different dynamic scheduling strategies, Heterogeneous Earliest Finish Time (HEFT) and Performance-Aware Multiqueue Scheduler (PAMS). We evaluate these strategies considering synthetic applications, and compare the proposals with the FCFS. For some scenarios, PAMS was proved to be up to 39% more efficient than FCFS. These gains usually imply on lower energy consumption, which is very desirable when working with mobile architectures.

A Framework for Direct and Transparent Data Exchange of Filter-stream Applications in Multi-GPUs Architectures

Abstract The massive data generation has been pushing for significant advances in computing architectures, reflecting in heterogeneous architectures composed by different types of processing units. The filter-stream paradigm is typically used to exploit the parallel processing power of these new architectures. The efficiency of applications in this paradigm is achieved by exploring a set of interconnected computers (cluster) using filters and communication between them in a coordinated way. In this work we propose, implement and test a generic abstraction for direct and transparent data exchange of filter-stream applications in heterogeneous cluster with multi-GPU (Graphics Processing Units). This abstraction allows hiding from the programmers all the low-level implementation details related to GPU communication and the control related to the location of filters. Further, we consolidate such abstraction into a framework. Empirical assessments using a real application show that the proposed abstraction layer eases the implementation of filter-stream applications without compromising the overall application performance.