An iterative expanding and shrinking process for processor allocation in mixed-parallel workflow scheduling.

Parallel computation has been widely applied in a variety of large-scale scientific and engineering applications. Many studies indicate that exploiting both task and data parallelisms, i.e. mixed-parallel workflows, to solve large computational problems can get better efficacy compared with either pure task parallelism or pure data parallelism. Scheduling traditional workflows of pure task parallelism on parallel systems has long been known to be an NP-complete problem. Mixed-parallel workflow scheduling has to deal with an additional challenging issue of processor allocation. In this paper, we explore the processor allocation issue in scheduling mixed-parallel workflows of moldable tasks, called M-task, and propose an Iterative Allocation Expanding and Shrinking (IAES) approach. Compared to previous approaches, our IAES has two distinguishing features. The first is allocating more processors to the tasks on allocated critical paths for effectively reducing the makespan of workflow execution. The second is allowing the processor allocation of an M-task to shrink during the iterative procedure, resulting in a more flexible and effective process for finding better allocation. The proposed IAES approach has been evaluated with a series of simulation experiments and compared to several well-known previous methods, including CPR, CPA, MCPA, and MCPA2. The experimental results indicate that our IAES approach outperforms those previous methods significantly in most situations, especially when nodes of the same layer in a workflow might have unequal workloads.

SLA-constrained service selection for minimizing costs of providing composite cloud services under stochastic runtime performance.

Composite cloud services based on the methodologies of Software as a Service and Service-Oriented Architecture are transforming how people develop and use software. Cloud service providers are confronting the service selection problem when composing composite cloud services. This paper deals with an important type of service selection problem, minimizing the total cost of providing a composite cloud service with respect to the constraints of service level agreement (SLA). Two types of SLA are considered in the study: per-request-based SLA and ratio-based SLA. We present three service selection approaches for dynamic cloud environments where services' performance might vary with time. The first two are iterative compound approaches for per-request-based SLA and the third approach is a one-step method for ratio-based SLA based on the Chebyshev's theorem and nonlinear programming. Experimental results show that our approaches outperform the previous method significantly in terms of total cost reduction.

Ds transposon is biased towards providing splice donor sites for exonization in transgenic tobacco.

Insertion of transposed elements into introns can lead to their activation as alternatively spliced cassette exons, an event called exonization, which can enrich the complexity of transcriptomes and proteomes. In this study, the first exonization event was detected when the modified rice EPSPS marker gene was inserted with the Ac transposon 5' end, which provided a splice donor site to yield abundant novel transcripts. To assess the contribution of splice donor and acceptor sites of transposon sequences, we inserted a Ds element into each intron of the EPSPS marker gene. This process yielded 14 constructs, with the Ds transposon inserted in the forward and reverse direction in each of the 7 introns of the EPSPS marker gene. The constructs were transformed into tobacco plants, and novel transcripts were identified by RT-PCR with specific primers. Exonization of Ds in EPSPS was biased towards providing splice donor sites of the inserted Ds sequence. Additionally, when the Ds inserted in reverse direction, a continuous splice donor consensus region was determined by offering 4 donor sites in the same intron. Information on these exonization events may help enhance gene divergence and functional genomic studies.

Metastatic carcinoma of the breast: a case with the unusual presentation of unilateral periorbital edema.

BACKGROUND: Metastasis of mammary cancer involving the orbit is common, and it typically presents with enophthalmos and restrictions of ocular motility. We report a case of mammary cancer with the unusual presentation of unilateral periorbital edema only. The possible mechanisms of unilateral periorbital swelling are discussed. CASE: Metastasis of breast cancer involving unilateral eyelid edema was diagnosed in a 66-year-old woman. A biopsy was performed to confirm the etiology after vague neuroimaging findings. The diagnosis was based on the histopathologic features of carcinomatous cells in the excised specimen. OBSERVATIONS: Insidious, progressive unilateral upper and lower eyelid swelling of the right eye disappeared after one cycle of palliative chemotherapy. Neither restriction nor proptosis developed in the whole course. CONCLUSIONS: Possible metastasis should be considered as a possible etiology of unilateral eyelid edema, even without a palpable mass or limitation of ocular motility. A biopsy should be performed in cases of unexplained eyelid edema.