RaftLib: A C++ template library for high performance stream parallel processing

2016 ◽  
Vol 31 (5) ◽  
pp. 391-404 ◽  
Author(s):  
Jonathan C Beard ◽  
Peng Li ◽  
Roger D Chamberlain
Keyword(s):  
High Performance ◽  
Performance Monitoring ◽  
Stream Processing ◽  
Automatic Parallelization ◽  
Optimization Techniques ◽  
Streaming Data ◽  
Great Promise ◽  
Full Spectrum ◽  
Legacy Code ◽  
Template Library

Stream processing is a compute paradigm that has been around for decades, yet until recently has failed to garner the same attention as other mainstream languages and libraries (e.g. C++, OpenMP, MPI). Stream processing has great promise: the ability to safely exploit extreme levels of parallelism to process huge volumes of streaming data. There have been many implementations, both libraries and full languages. The full languages implicitly assume that the streaming paradigm cannot be fully exploited in legacy languages, while library approaches are often preferred for being integrable with the vast expanse of extant legacy code. Libraries, however are often criticized for yielding to the shape of their respective languages. RaftLib aims to fully exploit the stream processing paradigm, enabling a full spectrum of streaming graph optimizations, while providing a platform for the exploration of integrability with legacy C/C++ code. RaftLib is built as a C++ template library, enabling programmers to utilize the robust C++ standard library, and other legacy code, along with RaftLib’s parallelization framework. RaftLib supports several online optimization techniques: dynamic queue optimization, automatic parallelization, and real-time low overhead performance monitoring.

scholarly journals Phytochemical variability during vegetation of Chamerion angustifolium (L.) Holub genotypes derived from in vitro cultures

2021 ◽  
Author(s):  
Mariola Dreger ◽  
Katarzyna Seidler-Łożykowska ◽  
Milena Szalata ◽  
Artur Adamczak ◽  
Karolina Wielgus
Keyword(s):  
High Performance Liquid Chromatography ◽  
Liquid Chromatography ◽  
High Performance ◽  
Array Detector ◽  
Reproduction Rate ◽  
Full Spectrum ◽  
Breeding Programs ◽  
Chamerion Angustifolium ◽  
Oenothein B

AbstractThe purpose of the study was to evaluate Chamerion angustifolium (L.) Holub genotypes for preliminary selection and further breeding programs aimed at obtaining a suitable industrial form for the pharmaceutical applications. Clonally propagated plants representing 10 genotypes of Ch. angustifolium were regenerated under in vitro conditions, hardened and planted in the field. Studies included an evaluation of shoot proliferation, phytochemical assessment of in vitro and ex vitro plants as well as investigations of intraspecies variability regarding four phenological stages: vegetative, beginning of blooming, full blooming, and green fruit phases. Quantitative and qualitative analyses of bioactive compounds were performed using high-performance liquid chromatography coupled with diode array detector and tandem mass spectrometer (HPLC–DAD–MS/MS) and high-performance liquid chromatography (HPLC) methods. The efficiency of shoot multiplication varied between genotypes from 8.12 to 21.48 shoots per explant. A high reproduction rate (> 20 shoots per explant) was recorded for four lines (PL_45, PL_44, PL_58, DE_2). Plants grown in vitro synthesized oenothein B (11.2–22.3 mg g−1 DW) and caffeic acid derivatives. Plants harvested from field contained the full spectrum of polyphenols characteristic for this species, and oenothein B and quercetin 3-O-glucuronide were the most abundant. The maximal content of oenothein B was determined in the vegetative phase of fireweed, while some flavonoids were found in the highest amount in full blooming phase. The results of analysis of variance indicated significant differences among genotypes in oenothein B, 3-O-caffeoylquinic acid and flavonoids accumulation in four phenological phases. PL_44 plants were characterized by high content of oenothein B and quercetin 3-O-glucuronide as well as a relatively high level of other flavonoids. Based on our phytochemical and micropropagation studies, PL_44 genotype was the best candidate for early selection and further breeding programs.

Inductive Effect as a Universal Concept to Design Efficient Catalysts for CO2 Electrochemical Reduction: Electronegativity Difference Makes Difference

2021 ◽  
Author(s):  
Huihuang Chen ◽  
Weng Fu ◽  
Zhigang Geng ◽  
Jie Zeng ◽  
Bo Yang
Keyword(s):  
Electrochemical Reduction ◽  
Energy Supply ◽  
Environmental Remediation ◽  
High Performance ◽  
Inductive Effect ◽  
Great Promise ◽  
Electronegativity Difference

CO2 electrochemical reduction (CO2ER) into valuable chemical feedstocks holds great promise for energy supply and environmental remediation but remains a challenge due to the lack of high-performance electrocatalysts. Inductive effect,...

A Target-Lighted dsDNA-Indicator for High-Performance Monitoring of Mercury Pollution and Its Antagonists Screening

2017 ◽  
Vol 51 (20) ◽  
pp. 11884-11890 ◽  
Author(s):  
Zhihe Qing ◽  
Lixuan Zhu ◽  
Xiaoxuan Li ◽  
Sheng Yang ◽  
Zhen Zou ◽  
...  
Keyword(s):  
High Performance ◽  
Performance Monitoring ◽  
Mercury Pollution

scholarly journals Implementation of Scientific Computing Applications on the Cell Broadband Engine

2009 ◽  
Vol 17 (1-2) ◽  
pp. 135-151 ◽  
Author(s):  
Guochun Shi ◽  
Volodymyr V. Kindratenko ◽  
Ivan S. Ufimtsev ◽  
Todd J. Martinez ◽  
James C. Phillips ◽  
...  
Keyword(s):  
High Performance ◽  
Scientific Computing ◽  
Lessons Learned ◽  
Optimization Techniques ◽  
Cell Processor ◽  
Intrinsic Properties ◽  
Cell Broadband Engine ◽  
Performance Improvements ◽  
Cell Architecture ◽  
Practical Recommendations

The Cell Broadband Engine architecture is a revolutionary processor architecture well suited for many scientific codes. This paper reports on an effort to implement several traditional high-performance scientific computing applications on the Cell Broadband Engine processor, including molecular dynamics, quantum chromodynamics and quantum chemistry codes. The paper discusses data and code restructuring strategies necessary to adapt the applications to the intrinsic properties of the Cell processor and demonstrates performance improvements achieved on the Cell architecture. It concludes with the lessons learned and provides practical recommendations on optimization techniques that are believed to be most appropriate.

Building sponge-like robust architectures of CNT–graphene–Si composites with enhanced rate and cycling performance for lithium-ion batteries

2015 ◽  
Vol 3 (7) ◽  
pp. 3962-3967 ◽  
Author(s):  
Xiaolei Wang ◽  
Ge Li ◽  
Fathy M. Hassan ◽  
Matthew Li ◽  
Kun Feng ◽  
...  
Keyword(s):  
Lithium Ion Batteries ◽  
Anode Materials ◽  
High Performance ◽  
Rate Capability ◽  
Lithium Ion ◽  
Cycling Performance ◽  
Cycling Stability ◽  
Great Promise ◽  
Practical Applications ◽  
Excellent Cycling Stability

High-performance robust CNT–graphene–Si composites are designed as anode materials with enhanced rate capability and excellent cycling stability for lithium-ion batteries. Such an improvement is mainly attributed to the robust sponge-like architecture, which holds great promise in future practical applications.

scholarly journals A New Vectorization Technique for Expression Templates in C++

2012 ◽  
Vol 10 (4) ◽  
Author(s):  
J Progsch ◽  
Y Ineichen ◽  
A Adelmann
Keyword(s):  
High Performance ◽  
Performance Gap ◽  
New Approach ◽  
Loop Unrolling ◽  
Basic Linear Algebra Subprograms ◽  
Template Library ◽  
Abstract Interface ◽  
Expression Templates ◽  
Performance Computing ◽  
Expression Template

Vector operations play an important role in high performance computing and are typically provided by highly optimized libraries that implement the Basic Linear Algebra Subprograms (BLAS) interface. In C++ templates and operator overloading allow the implementation of these vector operations as expression templates which construct custom loops at compile time and providing a more abstract interface. Unfortunately existing expression template libraries lack the performance of fast BLAS implementations. This paper presents a new approach - Statically Accelerated Loop Templates (SALT) - to close this performance gap by combining expression templates with an aggressive loop unrolling technique. Benchmarks were conducted using the Intel C++ compiler and GNU Compiler Collection to assess the performance of our library relative to Intel's Math Kernel Library as well as the Eigen template library. The results show that the approach is able to provide optimization comparable to the fastest available BLAS implementations, while retaining the convenience and flexibility of a template library.

scholarly journals Preliminary Sailplane Design Using MDO And Multi-Fidelity Analysis

2021 ◽  
Author(s):  
Chris V. Pilcher
Keyword(s):  
Multidisciplinary Design Optimization ◽  
High Performance ◽  
Vortex Lattice ◽  
Optimization Techniques ◽  
Multidisciplinary Design ◽  
Preliminary Design ◽  
Adaptive Meshing ◽  
Analysis Methods ◽  
And Performance ◽  
Modern Optimization

A multidisciplinary design optimization (MDO) strategy for the preliminary design of a sailplane has been developed. The proposed approach applies MDO techniques and multi-fidelity analysis methods which have seen successful use in many aerospace design applications. A customized genetic algorithm (GA) was developed to control the sailplane optimization that included aerodynamics/stability, structures/weights and balance and, performance/airworthiness disciplinary analysis modules. An adaptive meshing routine was developed to allow for accurate modeling of the aero structural couplinginvolved in wing design, which included a finite element method (FEM) structural solver along with a vortex lattice aerodynamics solver. Empirical equations were used to evaluate basic sailplane performance and airworthiness requirements. This research yielded an optimum design that correlated well with an existing high performance sailplane. The results of this thesis suggest that preliminary sailplane design is a well suited application for modern optimization techniques when coupled with, multi-fidelity analysis methods.

Adapting Ant Colony for Topology Optimization of Compliant Mechanisms With Variable Material Density

2017 ◽  
Author(s):  
Nadim Diab
Keyword(s):  
Topology Optimization ◽  
Ant Colony Optimization ◽  
High Performance ◽  
Compliant Mechanisms ◽  
Optimization Technique ◽  
Optimization Techniques ◽  
Ant Colony ◽  
Intensity Level ◽  
Material Density ◽  
Swarm Intelligence Optimization

Swarm intelligence optimization techniques are widely used in topology optimization of compliant mechanisms. The Ant Colony Optimization has been implemented in various forms to account for material density distribution inside a design domain. In this paper, the Ant Colony Optimization technique is applied in a unique manner to make it feasible to optimize for the beam elements’ cross-section and material density simultaneously. The optimum material distribution algorithm is governed by two various techniques. The first technique treats the material density as an independent design variable while the second technique correlates the material density with the pheromone intensity level. Both algorithms are tested for a micro displacement amplifier and the resulting optimized topologies are benchmarked against reported literature. The proposed techniques culminated in high performance and effective designs that surpass those presented in previous work.

Sign in / Sign up

Export Citation Format

Share Document