Search results for " Parallel"
showing 10 items of 224 documents
An autonomous petrological database for geodynamic simulations of magmatic systems
2022
SUMMARY Self-consistent modelling of magmatic systems is challenging as the melt continuously changes its chemical composition upon crystallization, which may affect the mechanical behaviour of the system. Melt extraction and subsequent crystallization create new rocks while depleting the source region. As the chemistry of the source rocks changes locally due to melt extraction, new calculations of the stable phase assemblages are required to track the rock evolution and the accompanied change in density. As a consequence, a large number of isochemical sections of stable phase assemblages are required to study the evolution of magmatic systems in detail. As the state-of-the-art melting diag…
Evaluation of chloroplast genome annotation tools and application to analysis of the evolution of coffee species.
2018
International audience; Chloroplast sequences are widely used for phylogenetic analysis due to their high degree of conservation in plants. Whole chloroplast genomes can now be readily obtained for plant species using new sequencing methods, giving invaluable data for plant evolution However new annotation methods are required for the efficient analysis of this data to deliver high quality phylogenetic analyses. In this study, the two main tools for chloroplast genome annotation were compared. More consistent detection and annotation of genes were produced with GeSeq when compared to the currently used Dogma. This suggests that the annotation of most of the previously annotated chloroplast …
The loss of dispersal on islands hypothesis revisited: Implementing phylogeography to investigate evolution of dispersal traits in Periploca (Apocyna…
2017
Aim: The loss of dispersal on islands hypothesis (LDIH) posits that wind-dispersed plants should exhibit reduced dispersal potential, particularly if island populations are old. In this study, we tested this hypothesis using a detailed phylogeographical framework across different geographical scales. Location: Mainland and island areas of the Atlantic and Mediterranean regions, including Macaronesia (Canary Islands and Cape Verde) and Mediterranean islands in the strait of Sicily. Methods: Forty-five populations of Periploca laevigata, a wind-dispersed shrub, were sampled. Plastid and nuclear microsatellite data were used to reconstruct spatio-temporal patterns of island colonization, and e…
Coupling agent-based with equation-based models to study spatially explicit megapopulation dynamics
2018
International audience; The incorporation of the spatial heterogeneity of real landscapes into population dynamics remains extremely difficult. We propose combining equation-based modelling (EBM) and agent-based modelling (ABM) to overcome the difficulties classically encountered. ABM facilitates the description of entities that act according to specific rules evolving on various scales. However, a large number of entities may lead to computational difficulties (e.g., for populations of small mammals, such as voles, that can exceed millions of individuals). Here, EBM handles age-structured population growth, and ABM represents the spreading of voles on large scales. Simulations applied to t…
Online Scheduling of Task Graphs on Hybrid Platforms
2018
Modern computing platforms commonly include accelerators. We target the problem of scheduling applications modeled as task graphs on hybrid platforms made of two types of resources, such as CPUs and GPUs. We consider that task graphs are uncovered dynamically, and that the scheduler has information only on the available tasks, i.e., tasks whose predecessors have all been completed. Each task can be processed by either a CPU or a GPU, and the corresponding processing times are known. Our study extends a previous \(4\sqrt{m/k}\)-competitive online algorithm [2], where m is the number of CPUs and k the number of GPUs (\(m\ge k\)). We prove that no online algorithm can have a competitive ratio …
Massively Parallel ANS Decoding on GPUs
2019
In recent years, graphics processors have enabled significant advances in the fields of big data and streamed deep learning. In order to keep control of rapidly growing amounts of data and to achieve sufficient throughput rates, compression features are a key part of many applications including popular deep learning pipelines. However, as most of the respective APIs rely on CPU-based preprocessing for decoding, data decompression frequently becomes a bottleneck in accelerated compute systems. This establishes the need for efficient GPU-based solutions for decompression. Asymmetric numeral systems (ANS) represent a modern approach to entropy coding, combining superior compression results wit…
WarpDrive: Massively Parallel Hashing on Multi-GPU Nodes
2018
Hash maps are among the most versatile data structures in computer science because of their compact data layout and expected constant time complexity for insertion and querying. However, associated memory access patterns during the probing phase are highly irregular resulting in strongly memory-bound implementations. Massively parallel accelerators such as CUDA-enabled GPUs may overcome this limitation by virtue of their fast video memory featuring almost one TB/s bandwidth in comparison to main memory modules of state-of-the-art CPUs with less than 100 GB/s. Unfortunately, the size of hash maps supported by existing single-GPU hashing implementations is restricted by the limited amount of …
Massively Parallel Huffman Decoding on GPUs
2018
Data compression is a fundamental building block in a wide range of applications. Besides its intended purpose to save valuable storage on hard disks, compression can be utilized to increase the effective bandwidth to attached storage as realized by state-of-the-art file systems. In the foreseeing future, on-the-fly compression and decompression will gain utmost importance for the processing of data-intensive applications such as streamed Deep Learning tasks or Next Generation Sequencing pipelines, which establishes the need for fast parallel implementations. Huffman coding is an integral part of a number of compression methods. However, efficient parallel implementation of Huffman decompre…
Towards a Reference Architecture for Archival Systems: Use Case With Product Data
2014
Long-term preservation of product data is imperative for many organizations. A product data archive should be designed to ensure information accessibility and understanding over time. Approaches, such as the Open Archival Information System Reference Model (OAIS RM) and the Audit and Certification of Trustworthy Digital Repositories (ACTDR), provide a framework for conceptually describing and evaluating archives. These approaches are generic and do not focus on particular contexts or content types such as product data. Moreover, these approaches offer no guidance on how to formally and comprehensively describe archival systems. Such descriptions should include the business activities that a…
Reliable diagnostics using wireless sensor networks
2019
International audience; Monitoring activities in industry may require the use of wireless sensor networks, for instance due to difficult access or hostile environment. But it is well known that this type of networks has various limitations like the amount of disposable energy. Indeed, once a sensor node exhausts its resources, it will be dropped from the network, stopping so to forward information about maybe relevant features towards the sink. This will result in broken links and data loss which impacts the diagnostic accuracy at the sink level. It is therefore important to keep the network's monitoring service as long as possible by preserving the energy held by the nodes. As packet trans…