基于MPI和OpenMP混合编程的高分三号数据分布式并行转换算法

高分三号是我国C波段多极化合成孔径雷达卫星。PolSARpro是欧空局支持下的一款极化SAR影像处理的开源软件,为了便于利用该软件处理高分三号数据,本文提出了一种基于MPI和OpenMP并以PolSARpro软件的数据格式要求进行分布式并行转换算法,实现将高分三号极化数据快速精确转化为复数散射矩阵S2数据格式,通过KingMap V8.0平台实现了算法并在实际数据中进行测试,验证了算法的可行性、正确性和高效性。

基于CGA的MPI程序分支覆盖测试套件生成

针对程序的分支覆盖测试,元启发式搜索技术已经被广泛应用于测试数据生成中。然而,当前的研究成果主要适用于串行程序。因此,为覆盖消息传递接口(Message Passing Interface,MPI)程序的分支,该文研究基于协同进化遗传算法(Co-evolutionary Genetic Algorithm,CGA)的测试套件生成方法(简称为:CGA生成法),该方法具有不受不可行分支影响的优势。首先,基于收集覆盖信息的探针,定义最小归一化分支距离,并以此设计出相应的适应度值函数;然后,使用CGA生成进化个体,并基于设计的适应度值函数,计算这些个体的适应值;最后,基于计算的适应值,选择子种群中代表个体,以构成合作种群。所提CGA生成法应用于7个基准MPI程序,并与其他多种方法进行比较。实验结果表明,CGA生成法的覆盖率通常高于其他搜索算法。

基于MPI+CUDA的DSMC/PIC耦合模拟异构并行及性能优化研究

DSMC/PIC耦合模拟是一类重要的高性能计算应用,大规模DSMC/PIC耦合模拟计算量巨大,需要实现高效并行计算。由于粒子动态注入、迁移等操作,基于MPI并行的DSMC/PIC耦合模拟往往通信开销较大且难以实现负载均衡。针对自主研发的DSMC/PIC耦合模拟软件,在原有MPI并行优化版本上设计实现了高效的MPI+CUDA异构并行算法,结合GPU体系结构和DSMC/PIC计算特点,开展了GPU访存优化、GPU线程工作负载优化、CPU-GPU数据传输优化及DSMC/PIC数据冲突优化等一系列性能优化。在北京北龙超级云HPC系统的NVIDIA V100和A100 GPU上,针对数亿粒子规模的脉冲真空弧等离子体羽流应用,开展了大规模DSMC/PIC耦合异构并行模拟,相比原有纯MPI并行,GPU异构并行大幅缩短了模拟时间,两块GPU卡较192核的CPU加速比达到550%,同时具有更好的强可扩展性。

利用MPI实现点云SAC-IA并行配准

采样一致性初始配准算法(SAC-IA)是点云的一种粗配准算法。针对大规模点云SAC-IA配准效率低、实时性差等问题,本文提出利用消息传递接口MPI实现点云SAC-IA多进程并行配准,主要包括法向量并行估计、SPFH特征及FPFH特征并行计算和SAC-IA并行配准。实验结果表明,MPI多进程并行算法可显著提高点云SAC-IA配准速度。

压电陶瓷作动器的MPI动态迟滞建模与控制

压电陶瓷是一种具有迟滞非线性的智能材料。为了实现系统的精密跟踪控制,提出一种基于MPI(modified Prandtl-Ishlinskii)的Hammerstein动态迟滞模型,并基于该模型设计了滑模跟踪控制方案。在play算子的上升边沿和下降边沿阈值处引入了延时系数,并串联死区算子构成改进的非对称PI(Prandtl-Ishlinskii)模型,基于MPI的Hammerstein动态迟滞非线性模型可以描述压电陶瓷作动器的率相关迟滞特性。通过采集在单频率10 Hz,40 Hz,80 Hz和复合频率10~90 Hz正弦输入电压信号下的压电陶瓷作动器的位移数据,并采用粒子群算法和最小二乘递推方法辨识MPI模型参数和ARX(auto regressive model with exogenous input)模型参数,验证了模型的可行性,相较于基于经典PI的Hammerstein动态迟滞模型,模型误差分别降低了37%,42%,35%和24%。最后,构建迟滞补偿器,利用Hammerstein模型的模块化特点,提出一种可以实现对系统动态跟踪控制的滑模控制方案,并搭建了滑模控制压电系统试验平台,对单频率1 Hz,40 Hz,80 Hz和复合频率10~90 Hz的正弦输入电压信号进行了微位移实时跟踪控制试验,试验中的相对误差在7.62%以内,均方根最大误差为1.8573μm,表明所提出的滑模控制器有较强的跟踪性能。

基于MPI的鲲鹏CPU核间通信研究

核间通信延时是影响高性能计算系统整体运行效率的重要因素.国产鲲鹏CPU在高性能计算领域应用日益广泛,针对鲲鹏CPU的缓存架构及多核间接口互联进行分析,研究影响鲲鹏CPU核间通信延时的因素.在消息传递接口(MPI)环境下进行节点内核间通信实验,对包括跨三级缓存、跨物理CPU通信等不同模式下通信延时进行对比,发现通信数据包大于500 KB后,跨L3 Cache TAG的通信延时反优于共享L3 Cache TAG的通信延时.针对通信数据包在64 KB大小时的通信延迟异常,分析得出是MPI的Eager模式和Rendezvous模式的默认切换阈值所造成.对这两种模式进行实验对比,验证不同大小的通信数据包在不同模式下和跨核通信时的延时特征,Eager模式更适合低延时的小消息发送.在实际应用中可根据通信数据包大小调整两种模式的默认切换阈值,以达到更好的传输效果.实验结果表明由于鲲鹏CPU存在复杂的多核结构,在并行计算程序设计时可以进行针对性优化,以提升程序的运行效率.

An MPI parallel DEM-IMB-LBM framework for simulating fluid-solid interaction problems

The high-resolution DEM-IMB-LBM model can accurately describe pore-scale fluid-solid interactions,but its potential for use in geotechnical engineering analysis has not been fully unleashed due to its prohibitive computational costs.To overcome this limitation,a message passing interface(MPI)parallel DEM-IMB-LBM framework is proposed aimed at enhancing computation efficiency.This framework utilises a static domain decomposition scheme,with the entire computation domain being decomposed into multiple subdomains according to predefined processors.A detailed parallel strategy is employed for both contact detection and hydrodynamic force calculation.In particular,a particle ID re-numbering scheme is proposed to handle particle transitions across sub-domain interfaces.Two benchmarks are conducted to validate the accuracy and overall performance of the proposed framework.Subsequently,the framework is applied to simulate scenarios involving multi-particle sedimentation and submarine landslides.The numerical examples effectively demonstrate the robustness and applicability of the MPI parallel DEM-IMB-LBM framework.

MPI+CUDA联合加速重力场反演的并行算法

针对重力场解算过程中数据量巨大的问题,联合MPI(massage passing interface)与CUDA(compute unified device architecture)提出基于最小二乘法的重力场解算过程的并行加速算法。使用MPI完成复杂过程的任务分配,实现全局层面的并行加速;基于CUDA编写大规模矩阵相乘的并行加速程序,并针对不同类型的矩阵进行适配,同时联合MPI将法矩阵的计算过程进一步细分,实现对分进程内存峰值的压缩。在单机上完成30阶与120阶重力场仿真解算任务,结果表明,反演30阶重力场时加速比可达180;反演120阶重力场时,并行计算单次迭代仅耗时2 h,而串行模式下无法计算。

Association between triglyceride-glucose index and colorectal polyps:A retrospective cross-sectional study

BACKGROUND Colorectal polyps(CPs)are frequently occurring abnormal growths in the colorectum,and are a primary precursor of colorectal cancer(CRC).The triglyceride-glucose(TyG)index is a novel marker that assesses metabolic health and insulin resistance,and has been linked to gastrointestinal cancers.AIM To investigate the potential association between the TyG index and CPs,as the relation between them has not been documented.METHODS A total of 2537 persons undergoing a routine health physical examination and colonoscopy at The First People's Hospital of Kunshan,Jiangsu Province,China,between January 2020 and December 2022 were included in this retrospective cross-sectional study.After excluding individuals who did not meet the eligibility criteria,descriptive statistics were used to compare characteristics between patients with and without CPs.Logistic regression analyses were conducted to determine the associations between the TyG index and the prevalence of CPs.The TyG index was calculated using the following formula:Ln[triglyceride(mg/dL)×glucose(mg/dL)/2].The presence and types of CPs was determined based on data from colonoscopy reports and pathology reports.RESULTS A nonlinear relation between the TyG index and the prevalence of CPs was identified,and exhibited a curvilinear pattern with a cut-off point of 2.31.A significant association was observed before the turning point,with an odds ratio(95% confidence interval)of 1.70(1.40,2.06),P<0.0001.However,the association between the TyG index and CPs was not significant after the cut-off point,with an odds ratio(95% confidence interval)of 0.57(0.27,1.23),P=0.1521.CONCLUSION Our study revealed a curvilinear association between the TyG index and CPs in Chinese individuals,suggesting its potential utility in developing colonoscopy screening strategies for preventing CRC.

A phenology-based vegetation index for improving ratoon rice mapping using harmonized Landsat and Sentinel-2 data

Ratoon rice,which refers to a second harvest of rice obtained from the regenerated tillers originating from the stubble of the first harvested crop,plays an important role in both food security and agroecology while requiring minimal agricultural inputs.However,accurately identifying ratoon rice crops is challenging due to the similarity of its spectral features with other rice cropping systems(e.g.,double rice).Moreover,images with a high spatiotemporal resolution are essential since ratoon rice is generally cultivated in fragmented croplands within regions that frequently exhibit cloudy and rainy weather.In this study,taking Qichun County in Hubei Province,China as an example,we developed a new phenology-based ratoon rice vegetation index(PRVI)for the purpose of ratoon rice mapping at a 30 m spatial resolution using a robust time series generated from Harmonized Landsat and Sentinel-2(HLS)images.The PRVI that incorporated the red,near-infrared,and shortwave infrared 1 bands was developed based on the analysis of spectro-phenological separability and feature selection.Based on actual field samples,the performance of the PRVI for ratoon rice mapping was carefully evaluated by comparing it to several vegetation indices,including normalized difference vegetation index(NDVI),enhanced vegetation index(EVI)and land surface water index(LSWI).The results suggested that the PRVI could sufficiently capture the specific characteristics of ratoon rice,leading to a favorable separability between ratoon rice and other land cover types.Furthermore,the PRVI showed the best performance for identifying ratoon rice in the phenological phases characterized by grain filling and harvesting to tillering of the ratoon crop(GHS-TS2),indicating that only several images are required to obtain an accurate ratoon rice map.Finally,the PRVI performed better than NDVI,EVI,LSWI and their combination at the GHS-TS2 stages,with producer's accuracy and user's accuracy of 92.22 and 89.30%,respectively.These results demonstrate that the proposed PRVI based on HLS data can effectively identify ratoon rice in fragmented croplands at crucial phenological stages,which is promising for identifying the earliest timing of ratoon rice planting and can provide a fundamental dataset for crop management activities.

MPI/OpenMP-Based Parallel Solver for Imprint Forming Simulation

In this research,we present the pure open multi-processing(OpenMP),pure message passing interface(MPI),and hybrid MPI/OpenMP parallel solvers within the dynamic explicit central difference algorithm for the coining process to address the challenge of capturing fine relief features of approximately 50 microns.Achieving such precision demands the utilization of at least 7 million tetrahedron elements,surpassing the capabilities of traditional serial programs previously developed.To mitigate data races when calculating internal forces,intermediate arrays are introduced within the OpenMP directive.This helps ensure proper synchronization and avoid conflicts during parallel execution.Additionally,in the MPI implementation,the coins are partitioned into the desired number of regions.This division allows for efficient distribution of computational tasks across multiple processes.Numerical simulation examples are conducted to compare the three solvers with serial programs,evaluating correctness,acceleration ratio,and parallel efficiency.The results reveal a relative error of approximately 0.3%in forming force among the parallel and serial solvers,while the predicted insufficient material zones align with experimental observations.Additionally,speedup ratio and parallel efficiency are assessed for the coining process simulation.The pureMPI parallel solver achieves a maximum acceleration of 9.5 on a single computer(utilizing 12 cores)and the hybrid solver exhibits a speedup ratio of 136 in a cluster(using 6 compute nodes and 12 cores per compute node),showing the strong scalability of the hybrid MPI/OpenMP programming model.This approach effectively meets the simulation requirements for commemorative coins with intricate relief patterns.

一种基于HDFS的分布式文件系统MPIFS

传统的MPI(Message Passing Interface)计算特点是数据向计算迁移,对于数据量庞大的计算任务具有先天的不足。文中提出一种支持MPI的分布式文件系统MPIFS的架构及实现。该文件系统基于HDFS(Hadoop Distributed File System),使得MPI在MPIFS上能同时支持计算密集型和数据密集型计算,设置两个类型的批处理词频统计实验,所需数据都分布式存储在MPIFS分布式文件系统中,通过调用系统提供的统一数据接口实现数据访问。1个计算节点在本地计算大小为m的文件,n个计算节点分布式并行计算大小为n×m的文件,两者计算时间相同,MPIFS中文件总量不变,计算节点数量减少,计算时间t变长,可得出MPIFS文件系统架构可行,能够支持MPI实现计算向数据迁移的并行计算。

On traceable iterated line graph and hamiltonian path index

Xiong and Liu[21]gave a characterization of the graphs G for which the n-iterated line graph L^(n)(G)is hamiltonian,for n≥2.In this paper,we study the existence of a hamiltonian path in L^(n)(G),and give a characterization of G for which L^(n)(G)has a hamiltonian path.As applications,we use this characterization to give several upper bounds on the hamiltonian path index of a graph.

An evaluation of ureteral diameter ratio and vesicoureteral reflux index in the treatment of primary vesicoureteral reflux

Objective:Vesicoureteral reflux(VUR)index is a simple,validated tool that reliably predicts significant improvement and spontaneous resolution of primary reflux in children.The aim of this study was to evaluate and compare the ureter diameter ratio(UDR)and VUR index(VURx)of patients treated with endoscopic injection(EI)and ureteroneocystostomy(UNC)methods in the pediatric age group due to primary VUR.Methods:Patients under the age of 18 years old who underwent EI and UNC with the diagnosis of primary VUR between January 2011 and September 2021 were determined as the participants.The UDR was assessed using voiding cystourethrography,and the VURx score was determined prior to treatment based on hospital records included in the study.Results:A total of 255 patients,60(23.5%)boys and 195(76.5%)girls,with a mean age of 76.5(range 13.0e204.0)months,were included in the study.EI was applied to 130(51.0%)patients and UNC was applied to 125(49.0%)patients due to primary VUR.The optimum cut-off for the distal UDR was obtained as 0.17 with sensitivity and specificity of 73.0%and 63.0%,respectively.The positive and negative predictive values were 66.0%and 70.0%,respectively.Conclusion:When the UDR and VURx score are evaluated together for the surgical treatment of primary VUR in the pediatric age group,it is thought that it may be useful in predicting the clinical course of the disease and evaluating surgical treatment options.

Association between the cumulative triglyceride-glucose index and the recurrence of atrial fibrillation after radiofrequency catheter ablation

BACKGROUND Triglyceride-glucose(TyG)index values are a new surrogate marker for insulin resistance.This study aimed to explore the relationship between cumulative TyG index values and atrial fibrillation(AF)recurrence after radiofrequency catheter ablation(RFCA).METHODS A total of 576 patients with AF who underwent RFCA at the Second Affiliated Hospital of Xi'an Jiaotong University were included in this study.The participants were grouped based on cumulative TyG index values tertiles within 3 months after ablation.Cox regression and restricted cubic spline analyses were used to determine the relationship between cumulative TyG index values and AF recurrence.The predictive value of all risk factors was assessed by receiver operating curve analysis.RESULTS There were 375 patients completed the study(age:63.23±10.73 years,64.27%male).The risk of AF recurrence increased with increasing cumulative TyG index values tertiles.After adjusting for potential confounders,patients in the medium cumulative TyG index group[hazard ratio(HR)=4.949,95%CI:1.778–13.778,P=0.002]and the high cumulative TyG index group(HR=8.716,95%CI:3.371–22.536,P<0.001)had a higher risk of AF recurrence than those in the low cumulative TyG index group.The restricted cubic spline regression model also showed an increased risk of AF recurrence with increasing cumulative TyG index values.When considering cumulative TyG index values,left atrial diameter,and lactate dehydrogenase levels as a comprehensive factor,the model could effectively predict AF recurrence after RFCA[area under the curve(AUC)=0.847,95%CI:0.797–0.897,P<0.001].CONCLUSIONS Cumulative TyG index values were a risk factor for AF recurrence after RFCA.Monitoring longitudinal TyG index values may assist with optimized for risk stratification and outcome prediction for AF recurrence.

Early peripheral perfusion index predicts 28-day outcome in patients with septic shock

BACKGROUND:To investigate the prognostic value of the peripheral perfusion index(PPI)in patients with septic shock.METHODS:This prospective cohort study,conducted at the emergency intensive care unit of Peking University People's Hospital,recruited 200 patients with septic shock between January 2023 and August 2023.These patients were divided into survival(n=84)and death(n=116)groups based on 28-day outcomes.Clinical evaluations included laboratory tests and clinical scores,with lactate and PPI values assessed upon admission to the emergency room and at 6 h and 12 h after admission.Risk factors associated with mortality were analyzed using univariate and multivariate Cox regression analyses.Receiver operator characteristic(ROC)curve was used to assess predictive performance.Mortality rates were compared,and Kaplan-Meier survival plots were created.RESULTS:Compared to the survival group,patients in the death group were older and had more severe liver damage and coagulation dysfunction,necessitating higher norepinephrine doses and increased fl uid replacement.Higher lactate levels and lower PPI levels at 0 h,6 h,and 12 h were observed in the death group.Multivariate Cox regression identifi ed prolonged prothrombin time(PT),decreased 6-h PPI and 12-h PPI as independent risk factors for death.The area under the curves for 6-h PPI and 12-h PPI were 0.802(95%CI 0.742-0.863,P<0.001)and 0.945(95%CI 0.915-0.974,P<0.001),respectively,which were superior to Glasgow Coma Scale(GCS),Sequential Organ Failure Assessment(SOFA)scores(0.864 and 0.928).Cumulative mortality in the low PPI groups at 6 h and 12 h was signifi cantly higher than in the high PPI groups(6-h PPI:77.52%vs.22.54%;12-h PPI:92.04%vs.13.79%,P<0.001).CONCLUSION:PPI may have value in predicting 28-day mortality in patients with septic shock.

Actuality and underlying mechanisms of systemic immuneinflammation index and geriatric nutritional risk index prognostic value in hepatocellular carcinoma

This editorial contains comments on the article“Correlation between preoperative systemic immune inflammation index,nutritional risk index,and prognosis of radical resection of liver cancer”in a recent issue of the World Journal of Gastrointestinal Surgery.It pointed out the actuality and importance of the article and focused primarily on the underlying mechanisms making the systemic immuneinflammation index(SII)and geriatric nutritional risk index(GNRI)prediction features valuable.There are few publications on both SII and GNRI together in hepatocellular carcinoma(HCC)and patient prognosis after radical surgery.Neutrophils release cytokines,chemokines,and enzymes,degrade extracellular matrix,reduce cell adhesion,and create conditions for tumor cell invasion.Neutrophils promote the adhesion of tumor cells to endothelial cells,through physical anchoring.That results in the migration of tumor cells.Pro-angiogenic factors from platelets enhance tumor angiogenesis to meet tumor cell supply needs.Platelets can form a protective film on the surface of tumor cells.This allows avoiding blood flow damage as well as immune system attack.It also induces the epithelial-mesenchymal transformation of tumor cells that is critical for invasiveness.High SII is also associated with macro-and microvascular invasion and increased numbers of circulating tumor cells.A high GNRI was associated with significantly better progression-free and overall survival.HCC patients are a very special population that requires increased attention.SII and GNRI have significant survival prediction value in both palliative treatment and radical surgery settings.The underlying mechanisms of their possible predictive properties lie in the field of essential cancer features.Those features provide tumor nutrition,growth,and distribution throughout the body,such as vascular invasion.On the other hand,they are tied to the possibility of patients to resist tumor progression and development of complications in both postoperative and cancer-related settings.The article is of considerable interest.It would be helpful to continue the study follow-up to 2 years and longer.External validation of the data is needed.

A Transparent Photoresist Made of Titanium Dioxide Nanoparticle-Embedded Acrylic Resin with a Tunable Refractive Index for UV-Imprint Lithography

Transparent photoresists with a high refractive index(RI)and high transmittance in visible wavelengths have promising functionalities in optical fields.This work reports a kind of tunable optical material composed of titanium dioxide nanoparticles embedded in acrylic resin with a high RI for ultraviolet(UV)-imprint lithography.The hybrid film exhibits a tunable RI of up to 1.67(589 nm)after being cured by UV light,while maintaining both a high transparency of over 98%in the visible light range and a low haze of less than 0.05%.The precision machining of optical microstructures can be imprinted easily and efficiently using the hybrid resin,which acts as a light guide plate(LGP)to guide the light from the side to the top in order to conserve the energy of the display device.These preliminary studies based on both laboratory and commercial experiments pave the way for exploiting the unparalleled optical properties of nanocomposite resins and promoting their industrial application.

Antecedent Precipitation Index to Estimate Soil Moisture and Correlate as a Triggering Process in the Occurrence of Landslides

Landslides are highly dangerous phenomena that occur in different parts of the world and pose significant threats to human populations. Intense rainfall events are the main triggering process for landslides in urbanized slope regions, especially those considered high-risk areas. Various other factors contribute to the process;thus, it is essential to analyze the causes of such incidents in all possible ways. Soil moisture plays a critical role in the Earth’s surface-atmosphere interaction systems;hence, measurements and their estimations are crucial for understanding all processes involved in the water balance, especially those related to landslides. Soil moisture can be estimated from in-situ measurements using different sensors and techniques, satellite remote sensing, hydrological modeling, and indicators to index moisture conditions. Antecedent soil moisture can significantly impact runoff for the same rainfall event in a watershed. The Antecedent Precipitation Index (API) or “retained rainfall,” along with the antecedent moisture condition from the Natural Resources Conservation Service, is generally applied to estimate runoff in watersheds where data is limited or unavailable. This work aims to explore API in estimating soil moisture and establish thresholds based on landslide occurrences. The estimated soil moisture will be compared and calibrated using measurements obtained through multisensor capacitance probes installed in a high-risk area located in the mountainous region of Campos do Jordão municipality, São Paulo, Brazil. The API used in the calculation has been modified, where the recession coefficient depends on air temperature variability as well as the climatological mean temperature, which can be considered as losses in the water balance due to evapotranspiration. Once the API is calibrated, it will be used to extrapolate to the entire watershed and consequently estimate soil moisture. By utilizing recorded mass movements and comparing them with API and soil moisture, it will be possible to determine thresholds, thus enabling anticipation of landslide occurrences.

Systemic immune-inflammation index,neutrophilto-lymphocyte ratio,and platelet-to-lymphocyte ratio in patients with type 2 diabetes at different stages of diabetic retinopathy

AIM:To investigate systemic immune-inflammation index(SII),neutrophil-to-lymphocyte ratio(NLR),and plateletto-lymphocyte ratio(PLR)levels in patients with type 2 diabetes at different stages of diabetic retinopathy(DR).METHODS:This retrospective study included 141 patients with type 2 diabetes mellitus(DM):45 without diabetic retinopathy(NDR),47 with non-proliferative diabetic retinopathy(NPDR),and 49 with proliferative diabetic retinopathy(PDR).Complete blood counts were obtained,and NLR,PLR,and SII were calculated.The study analysed the ability of inflammatory markers to predict DR using receiver operating characteristic(ROC)curves.The relationships between DR stages and SII,PLR,and NLP were assessed using multivariate logistic regression.RESULTS:The average NLR,PLR,and SII were higher in the PDR group than in the NPDR group(P=0.011,0.043,0.009,respectively);higher in the NPDR group than in the NDR group(P<0.001 for all);and higher in the PDR group than in the NDR group(P<0.001 for all).In the ROC curve analysis,the NLR,PLR,and SII were significant predictors of DR(P<0.001 for all).The highest area under the curve(AUC)was for the PLR(0.929 for PLR,0.925 for SII,and 0.821 for NLR).Multivariate regression analysis indicated that NLR,PLR,and SII were statistically significantly positive and independent predictors for the DR stages in patients with DM[odds ratio(OR)=1.122,95%confidence interval(CI):0.200–2.043,P<0.05;OR=0.038,95%CI:0.018–0.058,P<0.05;OR=0.007,95%CI:0.001–0.01,P<0.05,respectively).CONCLUSION:The NLR,PLR,and SII may be used as predictors of DR.