Low‐level PGAS computing on many‐core processors with TSHMEM

Diminishing returns from increased clock frequencies and instruction‐level parallelism have forced computer architects to adopt architectures that exploit wider parallelism through multiple processor cores. While emerging many‐core architectures have progressed at a remarkable rate, concerns arise regarding the performance and productivity of numerous parallel‐programming tools for application development. Development of parallel applications on many‐core processors often requires developers to familiarize themselves with unique characteristics of a target platform while attempting to maximize performance and maintain correctness of their applications. The family of partitioned global address space (PGAS) programming models comprises the current state of the art in balancing performance and programmability. One such PGAS approach is SHMEM, a lightweight, shared‐memory programming library that has demonstrated high performance and productivity potential for parallel‐computing systems with distributed‐memory architectures. In the paper, we present research, design, and analysis of a new SHMEM infrastructure specifically crafted for low‐level PGAS on modern and emerging many‐core processors featuring dozens of cores and more. Our approach (with a new library known as TSHMEM) is investigated and evaluated atop two generations of Tilera architectures, which are among the most sophisticated and scalable many‐core processors to date, and is intended to enable similar libraries atop other architectures now emerging. In developing TSHMEM, we explore design decisions and their impact on parallel performance for the Tilera TILE‐Gx and TILEPro many‐core architectures, and then evaluate the designs and algorithms within TSHMEM through microbenchmarking and applications studies with other communication libraries. Our results with barrier primitives provided by the Tilera libraries show dissimilar performance between the TILE‐Gx and TILEPro; therefore, TSHMEM's barrier design takes an alternative approach and leverages the on‐chip mesh network to provide consistent low‐latency performance. In addition, our experiments with TSHMEM show that naive collective algorithms consistently outperformed linear distributed collective algorithms when executed in an SMP‐centric environment. In leveraging these insights for the design of TSHMEM, our approach outperforms the OpenSHMEM reference implementation, achieves similar to positive performance over OpenMP and OSHMPI atop MPICH, and supports similar libraries in delivering high‐performance parallel computing to emerging many‐core systems. Copyright © 2015 John Wiley & Sons, Ltd.     

Selection of funding schemes by a borrowing decision model: a Hong Kong case study

In financial decision‐making, a number of mathematical models have been developed for financial management in construction. However, optimizing both qualitative and quantitative factors and the semi‐structured nature of construction finance optimization problems are key challenges in solving construction finance decisions. The selection of funding schemes by a modified construction loan acquisition model is solved by an adaptive genetic algorithm (AGA) approach. The basic objectives of the model are to optimize the loan and to minimize the interest payments for all projects. Multiple projects being undertaken by a medium‐size construction firm in Hong Kong were used as a real case study to demonstrate the application of the model to the borrowing decision problems. A compromise monthly borrowing schedule was finally achieved. The results indicate that Small and Medium Enterprise (SME) Loan Guarantee Scheme (SGS) was first identified as the source of external financing. Selection of sources of funding can then be made to avoid the possibility of financial problems in the firm by classifying qualitative factors into external, interactive and internal types and taking additional qualitative factors including sovereignty, credit ability and networking into consideration. Thus a more accurate, objective and reliable borrowing decision can be provided for the decision‐maker to analyse the financial options.     

CD26 Induces Colorectal Cancer Angiogenesis and Metastasis through CAV1/MMP1 Signaling

CD26 has been reported as a marker for colorectal cancer stem cells endowed with tumor-initiating properties and capable of colorectal cancer (CRC) metastasis. In this study, we investigated the functional effect of CD26 on CRC angiogenesis and metastasis, and the potential underlying mechanism. The functional effects of CD26 overexpression or repression were determined by a wound healing experiment, and cell migration and invasion assays in vitro and in mouse models. Differentially expressed genes regulated by CD26 were identified by genome-wide mRNA expression array and validated by quantitative PCR. CD26 functionally regulated CRC cell migration and invasion in vitro and angiogenesis and metastasis in vivo. Genome-wide mRNA expression array and qPCR showed that MMP1 was up-regulated in CD26+ subpopulation, and a subsequent experiment demonstrated the regulatory effect of CD26 on MMP1 in CRC cell lines with CD26 repression or overexpression. Furthermore, overexpression of CAV1 abrogated the CD26-regulated MMP1 induction in CRC cell lines. This study demonstrated the functional roles of CD26 in inducing CRC migration, invasion, angiogenesis and metastasis and identified the potential involvement of MMP1 and CAV1 in such process. CD26 is an attractive therapeutic target for combating tumor progression to improve the prognosis of CRC patients.     

Comparison and Characterization of Compounds with Antioxidant Activity in Lycium barbarum Using High‐Performance Thin Layer Chromatography Coupled with DPPH Bioautography and Tandem Mass Spectrometry

Methanol extracts from 50 batches of Lycium barbarum (L. barbarum, wolfberry) in China were compared and characterized using high‐performance thin‐layer chromatography coupled with 2,2‐diphenyl‐1‐picrylhydrazyl (DPPH) bioautography (HPTLC‐DPPH) and electrospray ionization quadrupole time‐of‐flight tandem mass spectrometry (ESI‐Q‐TOF‐MS/MS), respectively. Results showed that similar components occupying the major antioxidant activity existed in L. barbarum collected from different origins. However, the average antioxidant capacities of methanol extracts of L. barbarum collected in Ningxia were significantly higher than those of Qinghai, Xinjiang, Inner Mongolia, and Gansu, which may contribute to rational use of L. barbarum in China. Furthermore, the chemical structure of compound with the highest antioxidant capacity was tentatively identified as 2‐O‐β‐d ‐glucopyranosyl‐l ‐ascorbic acid using ESI‐Q‐TOF‐MS/MS analysis, which possessed high potentials to be used as an antioxidant biomarker for the quality control of L. barbarum. Results are helpful for the bioactivity‐based quality control of L. barbarum, and beneficial for the improvement of their performance in functional/health foods area, suggesting that HPTLC‐DPPH bioautography with ESI‐Q‐TOF‐MS/MS could be used as a routine approach for quality control of antioxidant components in L. barbarum.     

Distribution, characteristics, and worldwide inventory of dioxins in kaolin ball clays

Distribution, characteristics, and global inventory of dioxins (polychlorinated dibenzo-p-dioxins [PCDDs] and dibenzofurans [PCDFs] and dioxin like polychlorinated biphenyls) in kaolin clays collected from 10 countries were investigated. Dioxins were found in all kaolin clay samples analyzed, at total concentrations ranging from 1.2 pg/g (Brazil) to 520,000 pg/g (USA). Dioxin concentrations in kaolin clays from a few countries (e.g., Brazil and UK) were lower than those reported for background soils in Japan. Dioxin profiles in kaolin clays were characterized by the domination of the congener octachlorodibenzo-p-dioxin (OCDD), and the concentrations of other congeners decreased in the order of reduction in the levels of chlorination. Furthermore, specific distribution of congeners, with predominant proportions of 1,4,6,9-substituted PCDDs within each homologue group, was found in most clay samples. The ratios of concentrations of PCDD to PCDF and 1,2,3,7,8,9-HxCDD to 1,2,3,6,7,8-HxCDD indicated differences in the profiles found for anthropogenic sources (including pentachlorophenol) and kaolin clays. Concentrations of PCDD/Fs in kaolin clays, except for American ball clays, did not exceed the environmental criteria set by the Law Concerning Special Measures against Dioxins in Japan. Based on the average concentrations measured in our study, inventories of PCDD/Fs from the production/usage of ball clays on a global scale were estimated to be 650 kg/yr; the corresponding value on a TEQ basis is 2400 g-TEQ/yr. More than 480 kg of OCDD is estimated to be released annually from the production of kaolin clays worldwide, suggesting that kaolin clays can be a major contributor for additional source of dioxins, especially OCDD, in the environment.