Dukyun Nam

Improvement of Task Retrieval Performance Using AMGA in a Large-Scale Virtual Screening

In this paper, we address performance and scalability issues when AMGA (ARDA Metadata Grid Application) is used as a metadata service for task retrieval in the WISDOM (Wide in Silico Docking on Malaria) environment, and propose optimization techniques to deal with the issues. First, to deal with the performance problem due to the communication overhead caused by the need for jobs to call a series of AMGA operations in order for them to retrieve a task from the AMGA server in the WISDOM environment, we propose a new AMGA operation which allows jobs deployed on the Grid to retrieve a task in a single operation instead of calling series of existing AMGA operations. According to the performance study that we have done, the throughput of task retrieval using the new AMGA operation can be as much as 70 times higher than the throughput of using the existing AMGA operations. Second, to address the scalability problem when thousands of jobs running have access to the single AMGA server concurrently in an attempt to grab available tasks, we propose the use of multiple AMGA servers for the purpose of task retrieval. Our test results demonstrate that throughput can be improved linearly in proportion to the number of AMGA servers set up for load balancing.

High performance parallelization of Boyer---Moore algorithm on many-core accelerators

Boyer–Moore (BM) algorithm is a single pattern string matching algorithm. It is considered as the most efficient string matching algorithm and used in many applications. The algorithm first calculates two string shift rules based on the given pattern string in the preprocessing phase. Using the two shift rules, pattern matching operations are performed against the target input string in the second phase. The string shift rules calculated in the first phase let parts of the target input string be skipped where there are no matches to be found in the second phase. The second phase is a time consuming process and needs to be parallelized in order to realize the high performance string matching. In this paper, we parallelize the BM algorithm on the latest many-core accelerators such as the Intel Xeon Phi and the Nvidia Tesla K20 GPU along with the general-purpose multi-core microprocessors. For the parallel string matching, the target input data is partitioned amongst multiple threads. Data lying on the threads’ boundaries is searched redundantly so that the pattern string lying on the boundary between two neighboring threads cannot be missed. The redundant data search overheads increases significantly for a large number of threads. For a fixed target input length, the number of possible matches decreases as the pattern length increases. Furthermore, the positions of the pattern string are spread all over the target data randomly. This leads to the unbalanced workload distribution among threads. We employ the dynamic scheduling and the multithreading techniques to deal with the load balancing issue. We also use the algorithmic cascading technique to maximize the benefit of the multithreading and to reduce the overheads associated with the redundant data search between neighboring threads. Our parallel implementation leads to

Application Parameter Description Scheme for Multiple Job Generation in Problem Solving Environment

\sim

OCI-based group communication support in CORBA

∼17-times speedup on the Xeon Phi and

Research Process Support with Organizational Flow in e-Science

\sim

Performance of Large-Scale Electronic Structure Calculations on Built-in FPGA Systems

∼47-times speedup on the Nvidia Tesla K20 GPU compared with a serial implementation on the host Intel Xeon processor.