Search For:

Displaying 1-35 out of 35 total
Improving MapReduce Performance by Streaming Input Data from Multiple Replicas
Found in: 2013 IEEE 5th International Conference on Cloud Computing Technology and Science (CloudCom)
By Jiadong Wu,Bo Hong
Issue Date:December 2013
pp. 623-630
The MapReduce programming model, along with its open-source implementation Hadoop has provided a cost effective solution for many data-intensive applications. Hadoop stores data distributively and exploits data locality by assigning tasks to where data is ...
 
Message from the PhD Forum Co-chairs
Found in: 2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW)
By Luc Bouge,Bo Hong
Issue Date:May 2013
pp. 2212-2213
No summary available.
 
Bi-Hadoop: Extending Hadoop to Improve Support for Binary-Input Applications
Found in: 2013 13th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)
By Xiao Yu,Bo Hong
Issue Date:May 2013
pp. 245-252
The MapReduce programming model, along with its open-source implementation - Hadoop - has provided a cost effective solution for many data-intensive applications. Hadoop stores data distributively and exploits data locality by assigning tasks to where data...
 
Collocating CPU-only Jobs with GPU-assisted Jobs on GPU-assisted HPC
Found in: 2013 13th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)
By Jiadong Wu,Bo Hong
Issue Date:May 2013
pp. 418-425
In recent years, GPU has evolved rapidly and exhibited great potential in accelerating scientific applications. Massive GPU-assisted HPC systems have been deployed. However, as a heterogeneous system, GPU-assisted HPC is harder to be programmed and utilize...
 
Profiling-based Adaptive Contention Management for Software Transactional Memory
Found in: 2012 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)
By Zhengyu He,Xiao Yu,Bo Hong
Issue Date:May 2012
pp. 1204-1215
In software transactional memory (STM) systems, the contention management (CM) policy decides what action to take when a conflict occurs. CM is crucial to the performance of STM systems. However, the performance of existing CMs is sensitive to transaction ...
 
PMU-guided Priority Adjustment to Guarantee Thread Performance on IBM POWER SMT Processor
Found in: 2012 26th IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
By Zhengyu He,Bo Hong
Issue Date:May 2012
pp. 1640-1648
Simultaneous-multithreading (SMT) is widely used to improve the overall efficiency of superscalar CPUs with hardware multi-threading. With SMT processors, it is challenging to guarantee the performance of each individual thread because resources are shared...
 
A GPU-accelerated Approximate Algorithm for Incremental Learning of Gaussian Mixture Model
Found in: 2012 26th IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
By Chunlei Chen,Dejun Mu,Huixiang Zhang,Bo Hong
Issue Date:May 2012
pp. 1937-1943
The Gaussian mixture model (GMM) is a widely used probabilistic clustering model. The incremental learning algorithm of GMM is the basis of a variety of complex incremental learning algorithms. It is typically applied to real-time or massive data problems ...
 
PhD Forum Introduction
Found in: 2012 26th IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
By Luc Bouge,Bo Hong
Issue Date:May 2012
pp. 2460-2461
No summary available.
 
Towards Profitable Virtual Machine Placement in the Data Center
Found in: Utility and Cloud Computing, IEEE Internatonal Conference on
By Weiming Shi,Bo Hong
Issue Date:December 2011
pp. 138-145
Motivated by the limit on the power usage effectiveness (PUE) of the data centers, the potential benefit of the consolidation, and the impetus of achieving maximum return on investment (ROI) on the cloud computing market, we investigate VM placement in the...
 
A GPU-Based Approach to Accelerate Computational Protein-DNA Docking
Found in: Computing in Science & Engineering
By Jiadong Wu,Chunlei Chen,Bo Hong
Issue Date:May 2012
pp. 20-29
This article describes a GPU-based high-performance computing method to tackle the protein-DNA docking problem. GPU-specific algorithmic techniques are developed to accelerate a docking algorithm that integrates Monte Carlo simulation and simulated anneali...
 
Improving Prediction Accuracy of Protein-DNA Docking with GPU Computing
Found in: Bioinformatics and Biomedicine, IEEE International Conference on
By Bo Hong,Jiadong Wu,Jun-tao Guo
Issue Date:November 2011
pp. 482-487
Protein-DNA docking is a very challenging problem in bioinformatics and has important implications in a number of applications (e.g. rational drug design). This paper presents a computational approach to improve the prediction accuracy of protein-DNA docki...
 
An Efficient k-Means Algorithm on CUDA
Found in: Parallel and Distributed Processing Workshops and PhD Forum, 2011 IEEE International Symposium on
By Jiadong Wu,Bo Hong
Issue Date:May 2011
pp. 1740-1749
The $k$-means algorithm is widely used for unsupervised clustering. This paper describes an efficient CUDA-based $k$-means algorithm. Different from existing GPU-based k-means algorithms, our algorithm achieves better efficiency by utilizing the triangle i...
 
Resource Allocation with a Budget Constraint for Computing Independent Tasks in the Cloud
Found in: Cloud Computing Technology and Science, IEEE International Conference on
By Weiming Shi, Bo Hong
Issue Date:December 2010
pp. 327-334
We consider the problem of running a large amount of independent equal-sized tasks in the cloud with a budget constraint. We model the cloud infrastructure by a node-weighted edge-weighted star-shaped graph which captures the different computing power and ...
 
An Analytical Model on the Execution of Transactional Memory
Found in: Computer Architecture and High Performance Computing, Symposium on
By Xiao Yu, Zhengyu He, Bo Hong
Issue Date:October 2010
pp. 175-182
In this paper, we develop an analytical model of the execution of transactional memory (TM) systems. This model employs queuing theory to analyze the impact of an essential set of TM design parameters including the conflict rate, number of checkpoints, and...
 
An Asynchronous Multithreaded Algorithm for the Maximum Network Flow Problem with Nonblocking Global Relabeling Heuristic
Found in: IEEE Transactions on Parallel and Distributed Systems
By Bo Hong,Zhengyu He
Issue Date:June 2011
pp. 1025-1033
In this paper, we present a novel asynchronous multithreaded algorithm for the maximum network flow problem. The algorithm is based on the classical push-relabel algorithm, which is essentially sequential and requires intensive and costly lock usages to pa...
 
Modeling the Run-time Behavior of Transactional Memory
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Zhengyu He, Bo Hong
Issue Date:August 2010
pp. 307-315
In this paper, we develop a queuing theory based analytical model to evaluate the performance of transactional memory. Based on the statistical characteristics observed on actual experiments, we model each transaction as a client requesting services from t...
 
On the Performance of Commit-Time-Locking Based Software Transactional Memory
Found in: High Performance Computing and Communications, 10th IEEE International Conference on
By Zhengyu He, Bo Hong
Issue Date:June 2009
pp. 180-187
Compared with lock-based synchronization techniques, Software Transactional Memory (STM) can significantly improve the programmability of multithreaded applications. Existing research results have demonstrated through experiments that current STM designs h...
 
A lock-free multi-threaded algorithm for the maximum flow problem
Found in: Parallel and Distributed Processing Symposium, International
By Bo Hong
Issue Date:April 2008
pp. 1-8
The maximum flow problem is an important graph problem with a wide range of applications. In this paper, we present a lock-free multi-threaded algorithm for this problem. The algorithm is based on the push-relabel algorithm proposed by Goldberg. By using r...
 
Adaptive Allocation of Independent Tasks to Maximize Throughput
Found in: IEEE Transactions on Parallel and Distributed Systems
By Bo Hong, Viktor Prasanna
Issue Date:October 2007
pp. 1420-1435
In this paper, we consider the task allocation problem for computing a large set of equal-sized independent tasks on a heterogeneous computing system where the tasks initially reside on a single computer (the root) in the system. This problem represents th...
 
Using MEMS-Based Storage to Boost Disk Performance
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Feng Wang, Bo Hong, Scott A. Brandt, Darrell D. E. Long
Issue Date:April 2005
pp. 202-209
Non-volatile storage technologies such as flash memory, Magnetic RAM (MRAM), and MEMS-based storage are emerging as serious alternatives to disk drives. Among these, MEMS storage is predicted to be the least expensive and highest density, and at about 1 ms...
 
The Relevance of Long-Range Dependence in Disk Traffic and Implications for Trace Synthesis
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Bo Hong, Tara M. Madhyastha
Issue Date:April 2005
pp. 316-326
Accurate disk workloads are crucial for storage systems design, but I/O traces are difficult to obtain, unwieldy to work with, and unparameterizable. I/O traces are often bursty and difficult to characterize. Although good models of I/O workloads would be ...
 
Reliability of MEMS-Based Storage Enclosures
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Bo Hong, Thomas J. E. Schwarz, Scott A. Brandt, Darrell D. E. Long
Issue Date:October 2004
pp. 571-579
MEMS-based storage is a new, non-volatile storage technology currently under development. It promises fast data access, high throughput, high storage density, small physical size, low power consumption, and low entry costs. These properties make MEMS-based...
 
Performance Optimization of a De-centralized Task Allocation Protocol via Bandwidth and Buffer Management
Found in: Challenges of Large Applications in Distributed Environments, International Workshop on
By Bo Hong, Viktor K. Prasanna
Issue Date:June 2004
pp. 108
Sharing the resources among various users and the lack of a centralized control are two key characteristics of many distributed heterogeneous computing systems. A critical challenge for designing applications in such systems is to coordinate the resources ...
 
Distributed Adaptive Task Allocation in Heterogeneous Computing Environments to Maximize Throughput
Found in: Parallel and Distributed Processing Symposium, International
By Bo Hong, Viktor K. Prasanna
Issue Date:April 2004
pp. 52b
In this paper, we consider the task allocation problem for computing a large set of equal-sized independent tasks on heterogeneous computing systems. This problem represents the computation paradigm for a wide range of applications such as SETI@home and Mo...
 
Bandwidth-Aware Resource Allocation for Heterogeneous Computing Systems to Maximize Throughput
Found in: Parallel Processing, International Conference on
By Bo Hong, Viktor K. Prasanna
Issue Date:October 2003
pp. 539
In this paper, we consider the resource allocation problem for computing a large set of equal-sized independent tasks on heterogeneous computing systems. This problem represents the computation paradigm for a wide range of applications such as SETI@home an...
 
Managing Flash Crowds on the Internet
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Ismail Ari, Bo Hong, Ethan L. Miller, Scott A. Brandt, Darrell D. E. Long
Issue Date:October 2003
pp. 246
A flash crowd is a surge in traffic to a particular Web site that causes the site to be virtually unreachable. We present a model of flash crowd events and evaluate the performance of various multi-level caching techniques suitable for managing these event...
 
Zone-Based Shortest Positioning Time First Scheduling for MEMS-Based Storage Devices
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Bo Hong, Scott A. Brandt, Darrell D. E. Long, Ethan L. Miller, Karen A. Glocer, Zachary N. J. Peterson
Issue Date:October 2003
pp. 104
Access latency to secondary storage devices is frequently a limiting factor in computer system performance. New storage technologies promise to provide greater storage densities at lower latencies than is currently obtainable with hard disk drives. MEMS-ba...
 
Tiling, Block Data Layout, and Memory Hierarchy Performance
Found in: IEEE Transactions on Parallel and Distributed Systems
By Neungsoo Park, Bo Hong, Viktor K. Prasanna
Issue Date:July 2003
pp. 640-654
<p><b>Abstract</b>—Recently, several experimental studies have been conducted on block data layout in conjunction with tiling as a data transformation technique to improve cache performance. In this paper, we analyze cache and TLB perform...
 
Adaptive Matrix Multiplication in Heterogeneous Environments
Found in: Parallel and Distributed Systems, International Conference on
By Bo Hong, Viktor K. Prasanna
Issue Date:December 2002
pp. 129
In this paper, an adaptive matrix multiplication algorithm for dynamic heterogeneous environments is developed and evaluated. Unlike the state-of-the-art approaches, where load balancing is achieved through unequal distribution of the matrix data among the...
 
Analysis of Memory Hierarchy Performance of Block Data Layout
Found in: Parallel Processing, International Conference on
By Neungsoo Park, Bo Hong, Viktor K. Prasanna
Issue Date:August 2002
pp. 35
Recently, several experimental studies have been conducted on block data layout as a data transformation technique used in conjunction with tiling to improve cache performance. In this paper, we provide a theoretical analysis for the TLB and cache performa...
 
Ensuring Performance in Activity-Based File Relocation
Found in: Performance, Computing, and Communications Conference, 2002. 21st IEEE International
By Joel C. Wu, Bo Hong, Scott A. Brandt
Issue Date:April 2007
pp. 75-84
Dynamic Storage Tiering (DST) is the concept of grouping storage devices into tiers based on their characteristics, and relocating files dynamically to leverage on the heterogeneity of the underlying devices. An important usage of DST is activity-based fil...
 
Communication Models for Algorithm Design in Networked Sensor Systems
Found in: Parallel and Distributed Processing Symposium, International
By Yang Yu, Viktor K. Prasanna, Bo Hong
Issue Date:April 2005
pp. 207b
Towards building a systematic methodology of algorithm design of applications of networked sensor systems, we formally define two link-wise communication models, the Collision Free Model (CFM) and the Collision Aware Model (CAM). While CFM provides ease of...
 
Clotho: an elastic MapReduce workload/runtime co-design
Found in: Proceedings of the 12th International Workshop on Adaptive and Reflective Middleware (ARM '13)
By Weiming Shi, Bo Hong
Issue Date:December 2013
pp. 1-6
The resource management of a multi-tenant MapReduce cluster can be hard given unpredictable user demands. Conventional resource management scheme would inevitably create a fair amount of spare resource fragments in the system. On the other hand, MapReduce ...
     
Using MEMS-based storage in computer systems---device modeling and management
Found in: ACM Transactions on Storage (TOS)
By Bo Hong, Darrell D. E. Long, Ethan L. Miller, Scott A. Brandt, Ying Lin
Issue Date:May 2006
pp. 139-160
MEMS-based storage is an emerging nonvolatile secondary storage technology. It promises high performance, high storage density, and low power consumption. With fundamentally different architectural designs from magnetic disk, MEMS-based storage exhibits un...
     
Using MEMS-based storage in computer systems---MEMS storage architectures
Found in: ACM Transactions on Storage (TOS)
By Bo Hong, Darrell D. E. Long, Feng Wang, Scott A. Brandt, Thomas J. E. Schwarz
Issue Date:February 2006
pp. 1-21
As an emerging nonvolatile secondary storage technology, MEMS-based storage exhibits several desirable properties including high performance, high storage volumic density, low power consumption, low entry cost, and small form factor. However, MEMS-based st...
     
 1