Browsing by Author "Wang, YM"

Now showing 1 - 8 of 8

An efficient venturi scrubber system to remove submicron particles in exhaust gas
(2005-03-01)
Tsai, CJ
;
Lin, CH
;
Wang, YM
;
Hunag, CH
;
Li, SN
An efficient venturi scrubber system making use of heterogeneous nucleation and condensational growth of particles was designed and tested to remove fine particles from the exhaust of a local scrubber where residual SiH4 gas was abated and lots of fine SiO2 particles were generated. In front of the venturi scrubber, normal-temperature fine-water mist mixes with high-temperature exhaust gas to cool it to the saturation temperature, allowing submicron particles to grow into micron sizes. The grown particles are then scrubbed efficiently in the venturi scrubber. Test results show that the present venturi scrubber system is effective for removing submicron particles. For SiO2 particles greater than 0.1 mum, the removal efficiency is greater than 80-90%, depending on particle concentration. The corresponding pressure drop is relatively low. For example, the pressure drop of the venturi scrubber is similar to15.4 +/- 2.4 cm H2O when the liquid-to-gas ratio is 1.50 L/m(3). A theoretical calculation has been conducted to simulate particle growth process and the removal efficiency of the venturi scrubber. The theoretical results agree with the experimental data reasonably well when SiO2 particle diameter is greater than 0.1 mum.
Classifying and alleviating the communication overheads in matrix computations on large-scale NUMA multiprocessors
(1998-12-01)
Wang, YM
;
Wang, HH
;
Chang, RC
;
資訊工程學系
;
Department of Computer Science
Large-scale, shared-memory multiprocessors have non-uniform memory access (NUMA) costs. The high communication cost dominates the source of matrix computations' execution. Memory contention and remote memory access are two major communication overheads on large-scale NUMA multiprocessors. However, previous experiments and discussions focus either on reducing the number of remote memory accesses or on alleviating memory contention overhead. In this paper, we propose a simple but effective processor allocation policy, called rectangular processor allocation, to alleviate both overheads at the same time. The policy divides the matrix elements into a certain number of rectangular blocks, and assigns each processor to compute the results of one rectangular block. This methodology may reduce a lot of unnecessary memory accesses to the memory modules. After running many matrix computations under a realistic memory system simulator, we confirmed that at least one-fourth of the communication overhead map be reduced. Therefore, we conclude that rectangular processor allocation policy performs better than other popular policies, and that the combination of rectangular processor allocation policy with software interleaving data allocation policy is a better choice to alleviate communication overhead. (C) 1998 Elsevier Science Inc. All rights reserved.
Classifying and alleviating the communication overheads in matrix computations on large-scale NUMA multiprocessors
(1998-12-01)
Wang, YM
;
Wang, HH
;
Chang, RC
;
資訊工程學系
;
Department of Computer Science
Large-scale, shared-memory multiprocessors have non-uniform memory access (NUMA) costs. The high communication cost dominates the source of matrix computations' execution. Memory contention and remote memory access are two major communication overheads on large-scale NUMA multiprocessors. However, previous experiments and discussions focus either on reducing the number of remote memory accesses or on alleviating memory contention overhead. In this paper, we propose a simple but effective processor allocation policy, called rectangular processor allocation, to alleviate both overheads at the same time. The policy divides the matrix elements into a certain number of rectangular blocks, and assigns each processor to compute the results of one rectangular block. This methodology may reduce a lot of unnecessary memory accesses to the memory modules. After running many matrix computations under a realistic memory system simulator, we confirmed that at least one-fourth of the communication overhead map be reduced. Therefore, we conclude that rectangular processor allocation policy performs better than other popular policies, and that the combination of rectangular processor allocation policy with software interleaving data allocation policy is a better choice to alleviate communication overhead. (C) 1998 Elsevier Science Inc. All rights reserved.
Clustered affinity scheduling on large-scale NUMA multiprocessors
(1997-10-01)
Wang, YM
;
Wang, HH
;
Chang, RC
;
資訊工程學系
;
Department of Computer Science
Modern shared-memory multiprocessors have high and non-uniform memory access (NUMA) costs. The communication cost gradually dominates the source of parallel applications' execution. Algorithms based on affinity, like affinity scheduling algorithm (AFS), perform better than dynamic algorithms, such as guided self-scheduling (GSS) and trapezoid self-scheduling (TSS). However, as the number of processors increases, AFS suffers heavy overheads for migrating workload. The overheads include remote reads to the queues for the indices information, synchronous writes to the queues for migrating iterations, and the time in loading data into cache. In this paper, we propose a new loop scheduling algorithm, clustered affinity scheduling (CAFS), to improve affinity scheduling algorithm. We distribute the processors into several clusters, and cluster-based migrations are carried on when imbalance occurs. We confirm our idea by running many applications under a realistic hierarchy memory simulator. Our results show that CAFS reduces at least 1/3 of both remote reads and synchronous writes to the queues under most applications. CAFS also improves the cache hit ratios, and balances the workload. Therefore, we conclude that under large NUMA multiprocessor, CAFS is a better choice among loop scheduling algorithms. (C) 1997 Elsevier Science Inc.
Hierarchical loop scheduling for clustered NUMA machines
(2000-12-01)
Wang, YM
;
Wang, HH
;
Chang, RC
;
資訊工程學系
;
Department of Computer Science
Loop scheduling is an important issue in the development of high performance multiprocessors. As modern multiprocessors have high and non-uniform memory access (NUMA) costs, the communication costs dominate the execution of parallel programs. Previous affinity algorithms perform better than dynamic algorithms under non-clustered NUMA multiprocessors, but they suffer heavy overheads when migrating work load under clustered NUMA machines. In this paper, we propose a new loop scheduling policy, hierarchical policy, to improve Various affinity scheduling algorithms (AFSs) for clustered NUMA machines. We cyclically distribute the iteration chunks to clusters. When imbalance occurs, the migration of iterations is carried on hierarchically. We use hierarchical policy to improve AFS and modified AFS (MAFS), and we call them Hierarchical AFS (HAFS) and Hierarchical MAFS (HMAFS), respectively. AFS uses a deterministic assignment policy to assign repeated executions of loop iteration to the same processor. MAFS modifies the migration policy of AFS, and reduces the number of synchronization operations. We confirm our idea by running many applications under a clustered NUMA simulator. Our experimental result shows that hierarchical policy reduces the inter-cluster remote memory accesses, decreases the locks to the queues, and effectively balances the work load. We also show that HMAFS is the best choice among these algorithms in most cases. (C) 2000 Elsevier Science Inc. All rights reserved.
Low complexity lossless video compression
(2004)
Fang, YC
;
Lee, CY
;
Wang, YM
;
Wang, CN
;
Chiang, TH
We present a line-based adaptive lossless video compression (LALVC) algorithm for interactive multimedia applications that demand low complexity and low latency. Communications between high-resolution display and storage devices require high bandwidth for exchanging raw data. To reduce cost of video transmission without losing data accuracy, lossless video cornpression is necessary. Considering low complexity and low delay, LALVC adopts a simple and efficient architecture that adopts one-pass, raster-scan. transform-free coding process and a simple predictor. For low latency, zero-motion prediction and one-frame buffer are used to reduce temporal redundancy. In addition, to maximize the coding efficiency for both natural and computer-generated video sequences, LALVC adaptively selects the best coding mode for each line of a frame. The entropy coding of each line is based on Golomb code that can enhance coding efficiency with less computation load and is easy for hardware realization. The Simulation results show that temporal preprocessing and line-based mode decision of LALVC can increase compression ratio with properly increased complexity as compared to that of JPEG-LS.
Physicochemical characterization of the dimeric lanthanide complexes [en{Ln(DO3A)(H2O)}(2)] and [pi{Ln(DTTA)(H2O)}(2)](2-): a variable-temperature O-17 NMR study
(2004-03-01)
Lee, TM
;
Cheng, TH
;
Ou, MH
;
Chang, CA
;
Liu, GC
The Gd(III) complexes of the two dimeric ligands [en(DO3A)(2)] {N,N'-bis[1,4,7-tris(carboxymethyl)-1,4,7,10-tetraazacyclododecan-10-yl-methylcarbonyl]-N,N'-ethylenediamine] and [pi(DTTA)(2)](8-) [bisdiethylenetriaminepentaacetic acid (tratis-1,2-cyclohexanediamine)] were synthesized and characterized. The O-17 NMR chemical shift of H2O induced by [en(Dy(DO3A)}(2)] and [pi{Dy(DTTA)}(2)](2-) at pH 6.80 proved the presence of 2.1 and 2.2 inner-sphere water molecules, respectively. Water proton spin-lattice relaxation rates for [en(Gd(DO3A)(H2O)}(2)] and [pi(Gd(DTTA)(H2O)}(2)](2-) at 37.0 +/- 0.1degreesC and 20 MHz are 3.60 +/- 0.05 and 5.25 +/- 0.05 mm(-1) s(-1) per Gd, respectively. The EPR transverse electronic relaxation rate and O-17 NMR transverse relaxation time for the exchange lifetime of the coordinated H2O molecule and the H-2 NMR longitudinal relaxation rate of the deuterated diamagnetic lanthanum complex for the rotational correlation time were thoroughly investigated, and the results were compared with those reported previously for other lanthanide(III) complexes. The exchange lifetimes for [en(Gd(DO3A)(H2O)}(2)] (769 +/- 10 ns) and [pi[Gd(DTTA)(H2O)}(2)](2-) (910 +/- 10 ns) are significantly higher than those of [Gd(DOTA)(H2O)](-) (243 ns) and [Gd(DTPA)(H2O)](2-) (303 ns) complexes. The rotational correlation times for [en{Gd(DO3A)(H2O)}(2)] (150 +/- 11 ps) and [pi[Gd(DTTA)(H2O)}(2)](2-) (130 +/- 12 ps) are slightly greater than those of [Gd(DOTA)(H2O)](-) (77 ps) and [Gd(DTPA)(H2O)](2-) (58 ps) complexes. The marked increase in relaxivity (r(1)) of [en{Gd(DO3A)(H2O)}(2)] and [pi{Gd(DTTA)(H2O)(2)](2-) result mainly from their longer rotational correlation time and higher molecular weight. Copyright (C) 2004 John Wiley Sons, Ltd.
Sortability of multi-partitions
(2002-12-01)
Hwang, FK
;
Wang, YM
;
Lee, JS
;
應用數學系
;
Department of Applied Mathematics
Recently, the theory of sortability of partition property has been shown to be an effective tool to prove the existence of an optimal partition with that property. In this paper, we extend the theory to multi-partition where the partition is on t types of components. We apply our results to settle an optimal assignment problem whose proof was incomplete as given in the literature.