Python in the Cling World Lavrijsen, W
Journal of physics. Conference series,
12/2015, Letnik:
664, Številka:
6
Journal Article
Recenzirano
Odprti dostop
The language improvements in C++11 14 greatly reduce the amount of boilerplate code required and allow resource ownership to be clarified in interfaces. On top, the Cling C++ interpreter brings a ...truly interactive experience and real dynamic behavior to the language. Taken together, these developments bring C++ much closer to Python in ability, allowing the combination of PyROOT cppyy and Cling to integrate the two languages on a new level. This paper describes the current state of the art, including cross-language callbacks, automatic template instantiations, and the ability to use Python from Cling.
Data processing applications of the ATLAS experiment, such as event simulation and reconstruction, spend considerable amount of time in the initialization phase. This phase includes loading a large ...number of shared libraries, reading detector geometry and condition data from external databases, building a transient representation of the detector geometry and initializing various algorithms and services. In some cases the initialization step can take as long as 10-15 minutes. Such slow initialization has a significant negative impact on overall CPU efficiency of the production job, especially when the job is executed on opportunistic, often short-lived, resources such as commercial clouds or volunteer computing. In order to improve this situation, we can take advantage of the fact that ATLAS runs large numbers of production jobs with similar configuration parameters (e.g. jobs within the same production task). This allows us to checkpoint one job at the end of its configuration step and then use the generated checkpoint image for rapid startup of thousands of production jobs. By applying this technique we can bring the initialization time of a job from tens of minutes down to just a few seconds. In addition to that we can leverage container technology for restarting checkpointed applications on the variety of computing platforms, in particular of platforms different from the one on which the checkpoint image was created. We will describe the mechanism of creating checkpoint images of Geant4 simulation jobs with AthenaMP (the multi-process version of the ATLAS data simulation, reconstruction and analysis framework Athena) and the usage of these images for running ATLAS Simulation production jobs on volunteer computing resources (ATLAS@Home) and on Supercomputers.
Intel recently released the first commercial boards of its Many Integrated Core (MIC) Architecture. MIC is Intel's solution for the domain of throughput computing, currently dominated by general ...purpose programming on graphics processors (GPGPU). MIC allows the use of the more familiar x86 programming model and supports standard technologies such as OpenMP, MPI, and Intel's Threading Building Blocks (TBB). This should make it possible to develop for both throughput and latency devices using a single code base. In ATLAS Software, track reconstruction has been shown to be a good candidate for throughput computing on GPGPU devices. In addition, the newly proposed offline parallel event-processing framework, GaudiHive, uses TBB for task scheduling. The MIC is thus, in principle, a good fit for this domain. In this paper, we report our experiences of porting to and optimizing ATLAS tracking algorithms for the MIC, comparing the programmability and relative cost/performance of the MIC against those of current GPGPUs and latency-optimized CPUs.
The shared memory architecture of multicore CPUs provides HEP developers with the opportunity to reduce the memory footprint of their applications by sharing memory pages between the cores in a ...processor. ATLAS pioneered the multi-process approach to parallelize HEP applications. Using Linux fork() and the Copy On Write mechanism we implemented a simple event task farm, which allowed us to achieve sharing of almost 80% of memory pages among event worker processes for certain types of reconstruction jobs with negligible CPU overhead. By leaving the task of managing shared memory pages to the operating system, we have been able to parallelize large reconstruction and simulation applications originally written to be run in a single thread of execution with little to no change to the application code. The process of validating AthenaMP for production took ten months of concentrated effort and is expected to continue for several more months. Besides validating the software itself, an important and time-consuming aspect of running multicore applications in production was to configure the ATLAS distributed production system to handle multicore jobs. This entailed defining multicore batch queues, where the unit resource is not a core, but a whole computing node; monitoring the output of many event workers; and adapting the job definition layer to handle computing resources with different event throughputs. We will present scalability and memory usage studies, based on data gathered both on dedicated hardware and at the CERN Computer Center.
Objectives
In addition to breathing problems, patients with Robin sequence (RS) often encounter feeding difficulties (FD). Data regarding the occurrence of FD and possible influencing factors are ...scarce. The study aim was to elucidate these factors to improve treatment strategies.
Material and methods
A retrospective comparative cohort study was conducted, consisting of 69 infants diagnosed with both RS and a cleft palate and 64 isolated cleft palate only (iCPO) infants. Data regarding FD, growth, and airway intervention were collected during the first 2 years of life. A systematic review of the literature was conducted to identify reported FD in RS patients.
Results
RS patients had more FD (91 %) than iCPO patients (72 %;
p
= 0.004). Also, nasogastric (NG)-tube feeding was necessary more frequently and for a longer period (both
p
< 0.001). Growth was lower in RS than iCPO infants (
p
= 0.008) and was not affected by the kind of airway management (conservative/surgical;
p
= 0.178), cleft palate grade (
p
= 0.308), or associated disorders (
p
= 0.785). By contrast, surgical intervention subtype did significantly affect growth. Mean reported FD for RS in the literature is 80 % (range = 47–100 %), and 55 % (range = 11–100 %) of infants need NG-tube feeding.
Conclusions
FD is present in a large proportion of infants with RS, which indicates the need for early recognition and proper treatment to ensure optimal growth. Growth during the first 2 years of life is significantly lower in RS patients than iCPO patients, which indicates the need for careful attention and long-term follow-up.
Clinical relevance
This study indicates the need for early recognition and proper treatment of FD in RS to ensure optimal growth. In addition, growth needs careful attention and long-term follow-up.
The shared memory architecture of multicore CPUs provides HEP developers with the opportunity to reduce the memory footprint of their applications by sharing memory pages between the cores in a ...processor. ATLAS pioneered the multi-process approach to parallelize HEP applications. Using Linux fork() and the Copy On Write mechanism we implemented a simple event task farm, which allowed us to achieve sharing of almost 80% of memory pages among event worker processes for certain types of reconstruction jobs with negligible CPU overhead. By leaving the task of managing shared memory pages to the operating system, we have been able to parallelize large reconstruction and simulation applications originally written to be run in a single thread of execution with little to no change to the application code. The process of validating AthenaMP for production took ten months of concentrated effort and is expected to continue for several more months. Besides validating the software itself, an important and time-consuming aspect of running multicore applications in production was to configure the ATLAS distributed production system to handle multicore jobs. This entailed defining multicore batch queues, where the unit resource is not a core, but a whole computing node; monitoring the output of many event workers; and adapting the job definition layer to handle computing resources with different event throughputs. We will present scalability and memory usage studies, based on data gathered both on dedicated hardware and at the CERN Computer Center.
I/O Strategies for Multicore Processing in ATLAS van Gemmeren, P; Binet, S; Calafiura, P ...
Journal of physics. Conference series,
01/2012, Letnik:
396, Številka:
2
Journal Article, Conference Proceeding
Recenzirano
Odprti dostop
A critical component of any multicore/manycore application architecture is the handling of input and output. Even in the simplest of models, design decisions interact both in obvious and in subtle ...ways with persistence strategies. When multiple workers handle I/O independently using distinct instances of a serial I/O framework, for example, it may happen that because of the way data from consecutive events are compressed together, there may be serious inefficiencies, with workers redundantly reading the same buffers, or multiple instances thereof. With shared reader strategies, caching and buffer management by the persistence infrastructure and by the control framework may have decisive performance implications for a variety of design choices. Providing the next event may seem straightforward when all event data are contiguously stored in a block, but there may be performance penalties to such strategies when only a subset of a given event's data are needed; conversely, when event data are partitioned by type in persistent storage, providing the next event becomes more complicated, requiring marshalling of data from many I/O buffers. Output strategies pose similarly subtle problems, with complications that may lead to significant serialization and the possibility of serial bottlenecks, either during writing or in post-processing, e.g., during data stream merging. In this paper we describe the I/O components of AthenaMP, the multicore implementation of the ATLAS control framework, and the considerations that have led to the current design, with attention to how these I/O components interact with ATLAS persistent data organization and infrastructure.
The occurrence of severe neonatal hyperbilirubinemia (SH) is partly attributed to nonhospitalized perinatal care. The Netherlands have a high frequency of home births and nonhospitalized perinatal ...care, and the incidence of SH is unknown.
To assess the effects of home births and early hospital discharge on the incidence of SH in term-born infants in the Netherlands.
In this nationwide prospective surveillance study between 2005 and 2009, infants (≥37 weeks GA) were included if total serum bilirubin (TSB) was ≥500 µmol/l or if they received an exchange transfusion when TSB was ≥340 µmol/l.
Seventy-one infants had SH (incidence 10.4/100,000); 43 had a TSB ≥500 μmol/l (incidence 6.3/100,000) and 45 (63%) underwent an exchange transfusion. 26% of the infants with SH were born at home, which is similar to 22% of all term infants who are born at home in the Netherlands (p = 0.41). Maximum TSB levels were similar in infants born at home (523 ± 114 μmol/l) and infants born in hospital (510 ± 123 μmol/l; p = 0.70). Of the 51 infants born in hospital, 33 were discharged and readmitted with SH, with maximal TSB levels (567 ± 114 μmol/l), which were higher than in infants who remained hospitalized (406 ± 47 μmol/l; p = 0.0001).
The incidence of severe hyperbilirubinemia in term-born infants in the Netherlands is 10.4 per 100,000, which is similar to other developed countries. Home birth and early hospital discharge do not necessarily lead to a higher incidence of SH, provided that perinatal home care is well organized.
The ATLAS detector as installed in its experimental cavern at point 1 at CERN is described in this paper. A brief overview of the expected performance of the detector when the Large Hadron Collider ...begins operation is also presented.
Severe intrauterine hypoxia-ischemia and acidemia may lead to a disturbed neurodevelopment.
To study the effects of acidemia at birth on neurodevelopment in preterm and full-term neonates.
Short- and ...long-term outcome were studied retrospectively in 44 inborn preterms and 95 full-terms with severe acidemia at birth defined as a pH of the umbilical artery <7.00. Outcome was compared with 67 preterm and 90 full-term non-acidemic neonates (pH>7.15). Intraventricular hemorrhage (preterms) or seizures (both preterms and full-terms) were considered an adverse short-term outcome. Neonatal death, cerebral palsy or neurodevelopmental delay were considered an adverse long-term outcome.
Severe intraventricular hemorrhage (IVH) occurred in 5 of the 44 (11%) acidemic preterms and in none of the 67 (0%) non-acidemic preterms (p<0.01). Seizures were observed in 9 of the 44 (20%) and 11 of the 95 (12%) acidemic preterms and full-terms, respectively, and in none of the 67 (0%) and 1 of the 90 (1%) non-acidemic preterms and full-terms, respectively (p<0.001 for preterms, p<0.01 for full-terms). Nine preterms (6 acidemic, 3 non-acidemic) and 2 full-terms (both acidemic) died in the neonatal period. Adverse long-term outcome occurred in 32% of the acidemic preterms, in 21% of the non-acidemic preterms, in 7% of the acidemic full-terms and in 7% of the non-acidemic full-terms.
Acidemia at birth increased the occurrence of severe IVH in preterm neonates and seizures in both preterm and full-term neonates. However, no significant effect of acidemia on long-term outcome could be demonstrated.