Believe it or Not! Multicore CPUs can Match GPUs for FLOP-intensive Applications

In this work, we evaluate performance of a real-world image processing application that uses a cross-correlation algorithm to compare a given image with a reference one. The algorithm processes individual images represented as 2-dimensional matrices of single-precision floating-point values using O(n4) operations involving dot-products and additions. We implement this algorithm on a nVidia GTX 285 GPU using CUDA, and also parallelize it for the Intel Xeon (Nehalem) and IBM Power7 processors, using both manual and automatic techniques. Pthreads and OpenMP with SSE and VSX vector intrinsics are used for the manually parallelized version, while a state-of-the-art optimization framework based on the polyhedral model is used for automatic compiler parallelization and optimization. The performance of this algorithm on the nVidia GPU suffers from: (1) a smaller shared memory, (2) unaligned device memory access patterns, (3) expensive atomic operations, and (4) weaker single-thread performance. On commodity multi-core processors, the application dataset is small enough to fit in caches, and when parallelized using a combination of task and short-vector data parallelism (via SSE/VSX) or through fully automatic optimization from the compiler, the application matches or beats the performance of the GPU version. The primary reasons for better multi-core performance include larger and faster caches, higher clock frequency, higher on-chip memory bandwidth, and better compiler optimization and support for parallelization. The best performing versions on the Power7, Nehalem, and GTX 285 run in 1.02s, 1.82s, and 1.75s, respectively. These results conclusively demonstrate that, under certain conditions, it is possible for a FLOP-intensive structured application running on a multi-core processor to match or even beat the performance of an equivalent GPU version.

Broadband high-gain optical parametric chirped-pulse amplification near 780 nm with LBO-I near-degenerate near-collinear phase match

Near-degenerative near-collinear phase-match geometry for broadband optical parametric chirped-pulse amplification (OPCPA) at approximate to 780 nm is calculated in comparison with nondegenerate noncollinear phase-match geometry. In an experiment on LBO-I near-degenerate near-collinear OPCPA, high gain with broad gain bandwidth (approximate to 71 nm, FWHM) at approximate to 780 nm is achieved by using an approximate to 390-nm pumping pulse. The stretched broadband chirped signal pulse near 780 nm is amplified to approximate to 412 mu J with a pumping energy of approximate to 15 mJ, and the total gain is > 3.7 X 10(6), which agrees well with the calculation. For a broadband (covering approximate to 100 nm) chirped signal pulse, the theoretical gain bandwidth has been attained experimentally for the first time. (c) 2005 Society of Photo-Optical Instrumentation Engineers.

Broadband high-gain optical parametric chirped-pulse amplification near 780 nm with LBO-I near-degenerate near-collinear phase match

Near-degenerative near-collinear phase-match geometry for broadband optical parametric chirped-pulse amplification (OPCPA) at approximate to 780 nm is calculated in comparison with nondegenerate noncollinear phase-match geometry. In an experiment on LBO-I near-degenerate near-collinear OPCPA, high gain with broad gain bandwidth (approximate to 71 nm, FWHM) at approximate to 780 nm is achieved by using an approximate to 390-nm pumping pulse. The stretched broadband chirped signal pulse near 780 nm is amplified to approximate to 412 mu J with a pumping energy of approximate to 15 mJ, and the total gain is > 3.7 X 10(6), which agrees well with the calculation. For a broadband (covering approximate to 100 nm) chirped signal pulse, the theoretical gain bandwidth has been attained experimentally for the first time. (c) 2005 Society of Photo-Optical Instrumentation Engineers.

Theoretical research on noncollinear match conditions of the type I optical parametric process

Broad bandwidth group match conditions are reported for a noncollinear type I optical parametric process. The theoretical calculations corresponding to two special situations in practice were made, respectively, which are in accordance with the published experimental results. Furthermore, we provide a method to not only achieve maximal parametric bandwidth output but also match the group velocities between three waves. (c) 2006 Optical Society of America.

Beam match and preparation of SFC-CSR

In order to match the beam from the injection machine SFC of the HIRFL to the main ring of HIRFL-CSR, both beam emittance confining method and beam energy spread reducing method are proposed. The beam preparation principles and calculation results are presented

基于I-Match算法的垃圾邮件过滤研究

电子邮件(Electronic Mail，E-Mail)是目前使用最广泛的互联网应用。随着互联网络以惊人的速度增长，电子邮件成为发布恶意信息的一个重要途径，垃圾邮件已经成为危害互联网络的最大毒瘤。针对方式多样的垃圾邮件技术，垃圾邮件过滤系统往往也需要综合多种过滤技术以提高系统的有效性。其中摘要技术已经成为重要的垃圾邮件过滤方法之一：通过摘要技术判断一个邮件和已知垃圾邮件的相似度，从而对邮件进行分类。判断一个垃圾邮件过滤算法是否有效，要综合考虑算法的召回率、准确率以及时间性能。I-Match算法通过摘要值的精确匹配来判断两个邮件文本内容是否相似，算法在效率方面表现突出。但是I-Match算法在实际的应用中还存在很多问题，其中包括字典生成制约算法的性能以及面对攻击时算法表现出的鲁棒性不足。因此，优化算法的字典生成过程以及提高算法的鲁棒性成了算法应用于实际系统的两个重要问题。本文的主要工作包含以下内容： 对垃圾邮件进行相似性分析，包括垃圾邮件相似性的起因、垃圾邮件在时间和内容两方面所表现出的相似性特征。垃圾邮件体现出的相似性特征是使用摘要算法进行垃圾邮件过滤的必要条件之一。 改进I-Match算法的字典生成过程。提出利用特征的互信息作为特征选择依据改进字典生成过程，并对比几种不同的特征选择方式对算法性能的影响。 分析I-Match算法的鲁棒性以及几种I-Match改进算法对算法鲁棒性的提升，在实际的邮件语料上对各种改进算法进行评测，并综合分析各个算法的实用性。 完成了KSpam系统原型，以插件的形式综合多种邮件过滤方法，并给出了I-Match算法在KSpam系统中的实现方案。同时，系统实现了一种新式的邮件自动回收功能，有效减少邮件管理员的邮件语料收集工作。

Efeito do inseticida Match e sua interação com os inimigos naturais no controle de Spodoptera frugiperda (Smith, 1797), na cultura do milho.

2005

Strategy-proofness versus Efficiency in Matching with Indifferences: Redesigning the NYC High School Match

The design of the New York City (NYC) high school match involved trade-offs among efficiency, stability, and strategy-proofness that raise new theoretical questions. We analyze a model with indifferences-ties-in school preferences. Simulations with field data and the theory favor breaking indifferences the same way at every school-single tiebreaking-in a student-proposing deferred acceptance mechanism. Any inefficiency associated with a realized tiebreaking cannot be removed without harming student incentives. Finally, we empirically document the extent of potential efficiency loss associated with strategy-proofness and stability, and direct attention to some open questions. (JEL C78, D82, I21).

A numerical approach to C-14 wiggle-match dating of organic deposits: best fits and confidence intervals

14C wiggle-match dating (WMD) of peat deposits uses the non-linear relationship between 14C age and calendar age to match the shape of a sequence of closely spaced peat 14C dates with the 14C calibration curve. A numerical approach to WMD enables the quantitative assessment of various possible wiggle-match solutions and of calendar year confidence intervals for sequences of 14C dates. We assess the assumptions, advantages, and limitations of the method. Several case-studies show that WMD results in more precise chronologies than when individual 14C dates are calibrated. WMD is most successful during periods with major excursions in the 14C calibration curve (e.g., in one case WMD could narrow down confidence intervals from 230 to 36 yr).

Radiocarbon wiggle-match dating of proglacial lake sediments - Implications for the 8.2 ka event

The problem of insufficient age-control limits the utilisation of the 8.2 ka BP event for modelling freshwater forcing in climate change studies. High-resolution radiocarbon dates, magnetic susceptibility and lithostratigraphic evidence from a lake sediment core from Nedre Hervavatnet located at Sygnefjell in western Norway provide a record of the early Holocene. We use the method of radiocarbon wiggle-match dating of the lake sediments using the non-linear relationship between the C-14 calibration curve and the consecutive accumulation order of the sample series in order to build a high-resolution age-model. The timing and duration of Holocene environmental changes is estimated using 38 AMS radiocarbon dates on terrestrial macrofossils, insects and chironomids covering the time period from 9750 to 1180 cal BP. Chironomids, Salix and Betula leaves produce the most consistent results. Sedimentological and physical properties of the core suggest that three meltwater events with high sedimentation rates are superimposed on a long-term trend with glacier retreat between 9750 and 8000 cal BP. The lake sediment sequence of Nedre Hervavatnet demonstrates the following: only a reliable high-resolution geochronology based on carefully selected terrestrial macrofossils allows the reconstruction of a more refined and complex environmental change history before and during the 8.2 ka event. (C) 2009 Elsevier Ltd. All rights reserved.

Changes in solar activity and Holocene climatic shifts derived from C-14 wiggle-match dated peat deposits

Closely spaced sequences of accelerator mass spectrometer (AMS) C-14 dates of peat deposits display century-scale wiggles which can be fitted to the radiocarbon calibration curve. By wiggle-matching such sequences, high-precision calendar age chronologies can be generated which show that changes in mire surface wetness during the Bronze Age/Iron Age transition (c. 850 cal. BC) and the 'Little Ice Age' (Wolf, Sporer, Maunder and Dalton Minima) occurred during periods of suddenly increasing atmospheric concentration of C-14. Replicate evidence from peat-based proxy climate indicators in northwest Europe suggest these changes in climate may have been driven by temporary declines of solar activity. Carbon-accumulation rates of two raised peat bogs in the UK and Denmark record low values during the 'Little Ice Age' which reflects reduced primary productivity of the peat-forming vegetation during these periods of climatic deterioration.