arXiv subjects

Massimo Bernaschi

Publications and source records attributed to Massimo Bernaschi.

53 records · Page 3Linked to original sources

arXiv2019

Mesoscopic simulations at the physics-chemistry-biology interface

We discuss the Lattice Boltzmann-Particle Dynamics (LBPD) multiscale paradigm for the simulation of complex states of flowing matter at the interface between Physics, Chemistry and Biology. In particular, we describe current large-scale LBPD simulations of biopolymer translocation across cellular membranes, molecular transport in ion channels and amyloid aggregation in cells. We also provide prospects for future LBPD explorations in the direction of cellular organization, the direct simulation of full biological organelles, all the way to up to physiological scales of potential relevance to future precision-medicine applications, such as the accurate description of homeostatic processes. It is argued that, with the advent of Exascale computing, the mesoscale physics approach advocated in this paper, may come to age in the next decade and open up new exciting perspectives for physics-based computational medicine.

physics.comp-ph↗

arXiv2019

BitCracker: BitLocker meets GPUs

BitLocker is a full-disk encryption feature available in recent Windows versions. It is designed to protect data by providing encryption for entire volumes and it makes use of a number of different authentication methods. In this paper we present a solution, named BitCracker, to attempt the decryption, by means of a dictionary attack, of memory units encrypted by BitLocker with a user supplied password or the recovery password. To that purpose, we resort to GPU (Graphics Processing Units) that are, by now, widely used as general-purpose coprocessors in high performance computing applications. BitLocker decryption process requires the computation of a very large number of SHA- 256 hashes and also AES, so we propose a very fast solution, highly tuned for Nvidia GPU, for both of them. We analyze the performance of our CUDA implementation on several Nvidia GPUs and we carry out a comparison of our SHA-256 hash with the Hashcat password cracker tool. Finally, we present our OpenCL version, recently released as a plugin of the John The Ripper tool.

cs.CR↗

arXiv2018

AMG based on compatible weighted matching for GPUs

We describe main issues and design principles of an efficient implementation, tailored to recent generations of Nvidia Graphics Processing Units (GPUs), of an Algebraic Multigrid (AMG) preconditioner previously proposed by one of the authors and already available in the open-source package BootCMatch: Bootstrap algebraic multigrid based on Compatible weighted Matching for standard CPU. The AMG method relies on a new approach for coarsening sparse symmetric positive definite (spd) matrices, named "coarsening based on compatible weighted matching". It exploits maximum weight matching in the adjacency graph of the sparse matrix, driven by the principle of compatible relaxation, providing a suitable aggregation of unknowns which goes beyond the limits of the usual heuristics applied in the current methods. We adopt an approximate solution of the maximum weight matching problem, based on a recently proposed parallel algorithm, referred as the Suitor algorithm, and show that it allow us to obtain good quality coarse matrices for our AMG on GPUs. We exploit inherent parallelism of modern GPUs in all the kernels involving sparse matrix computations both for the setup of the preconditioner and for its application in a Krylov solver, outperforming preconditioners available in Nvidia AmgX library. We report results about a large set of linear systems arising from discretization of scalar and vector partial differential equations (PDEs).

math.NA↗

arXiv2016

Fluidization and wall slip of soft-glassy materials by controlled surface roughness

The motion of soft-glassy materials (SGM) in a confined geometry is strongly impacted by surface roughness. However, the effect of the spatial distribution of the roughness remains poorly understood from a more quantitative viewpoint. Here we present a comprehensive study of concentrated emulsions flowing in microfluidic channels, one wall of which is patterned with micron-size equally spaced grooves oriented perpendicularly to the flow direction. We show that roughness-induced fluidization can be quantitatively tailored by systematically changing both the width and separation of the grooves. We find that a simple scaling law describes such fluidization as a function of the density of grooves, suggesting common scenarios for droplet trapping and release. Numerical simulations confirm these views and are used to elucidate the relation between fluidization and the rate of plastic rearrangements.

cond-mat.soft↗

arXiv2016

GPU Based Detection of Topological Changes in Voronoi Diagrams

The Voronoi diagrams are an important tool having theoretical and practical applications in a large number of fields. We present a new procedure, implemented as a set of CUDA kernels, which detects, in a general and efficient way, topological changes in case of dynamic Voronoi diagrams whose generating points move in time. The solution that we provide has been originally developed to identify plastic events during simulations of soft-glassy materials based on a Lattice Boltzmann model with frustrated-short range attractive and mid/long-range repulsive-interactions. Along with the description of our approach, we present also some preliminary physics results.

cond-mat.soft↗

arXiv2016

Fluidisation and plastic activity in a model soft-glassy material flowing in micro-channels with rough walls

By means of mesoscopic numerical simulations of a model soft-glassy material, we investigate the role of boundary roughness on the flow behaviour of the material, probing the bulk/wall and global/local rheologies. We show that the roughness reduces the wall slip induced by wettability properties and acts as a source of fluidisation for the material. A direct inspection of the plastic events suggests that their rate of occurrence grows with the fluidity field, reconciling our simulations with kinetic elasto-plastic descriptions of jammed materials. Notwithstanding, we observe qualitative and quantitative differences in the scaling, depending on the distance from the rough wall and on the imposed shear. The impact of roughness on the orientational statistics is also studied.

cond-mat.soft↗

arXiv2016

Algorithms and Heuristics for Scalable Betweenness Centrality Computation on Multi-GPU Systems

Betweenness Centrality (BC) is steadily growing in popularity as a metrics of the influence of a vertex in a graph. The BC score of a vertex is proportional to the number of all-pairs-shortest-paths passing through it. However, complete and exact BC computation for a large-scale graph is an extraordinary challenge that requires high performance computing techniques to provide results in a reasonable amount of time. Our approach combines bi-dimensional (2-D) decomposition of the graph and multi-level parallelism together with a suitable data-thread mapping that overcomes most of the difficulties caused by the irregularity of the computation on GPUs. Furthermore, we propose novel heuristics which exploit the topology information of the graph in order to reduce time and space requirements of BC computation. Experimental results on synthetic and real-world graphs show that the proposed techniques allow the BC computation of graphs which are too large to fit in the memory of a single computational node along with a significant reduction of the computing time.

cs.DC↗

arXiv2014

Parallel Distributed Breadth First Search on the Kepler Architecture

We present the results obtained by using an evolution of our CUDA-based solution for the exploration, via a Breadth First Search, of large graphs. This latest version exploits at its best the features of the Kepler architecture and relies on a combination of techniques to reduce both the number of communications among the GPUs and the amount of exchanged data. The final result is a code that can visit more than 800 billion edges in a second by using a cluster equipped with 4096 Tesla K20X GPUs.

cs.DC↗

arXiv2014

Mesoscopic simulation study of wall roughness effects in micro-channel flows of dense emulsions

We study the Poiseuille flow of a soft-glassy material above the jamming point, where the material flows like a complex fluid with Herschel- Bulkley rheology. Microscopic plastic rearrangements and the emergence of their spatial correlations induce cooperativity flow behavior whose effect is pronounced in presence of confinement. With the help of lattice Boltzmann numerical simulations of confined dense emulsions, we explore the role of geometrical roughness in providing activation of plastic events close to the boundaries. We probe also the spatial configuration of the fluidity field, a continuum quantity which can be related to the rate of plastic events, thereby allowing us to establish a link between the mesoscopic plastic dynamics of the jammed material and the macroscopic flow behaviour.

cond-mat.soft↗

arXiv2014

Highly optimized simulations on single- and multi-GPU systems of 3D Ising spin glass

We present a highly optimized implementation of a Monte Carlo (MC) simulator for the three-dimensional Ising spin-glass model with bimodal disorder, i.e., the 3D Edwards-Anderson model running on CUDA enabled GPUs. Multi-GPU systems exchange data by means of the Message Passing Interface (MPI). The chosen MC dynamics is the classic Metropolis one, which is purely dissipative, since the aim was the study of the critical off-equilibrium relaxation of the system. We focused on the following issues: i) the implementation of efficient access patterns for nearest neighbours in a cubic stencil and for lagged-Fibonacci-like pseudo-Random Numbers Generators (PRNGs); ii) a novel implementation of the asynchronous multispin-coding Metropolis MC step allowing to store one spin per bit and iii) a multi-GPU version based on a combination of MPI and CUDA streams. We highlight how cubic stencils and PRNGs are two subjects of very general interest because of their widespread use in many simulation codes. Our code best performances ~3 and ~5 psFlip on a GTX Titan with our implementations of the MINSTD and MT19937 respectively.

cond-mat.dis-nn↗

arXiv2013

GPU peer-to-peer techniques applied to a cluster interconnect

Modern GPUs support special protocols to exchange data directly across the PCI Express bus. While these protocols could be used to reduce GPU data transmission times, basically by avoiding staging to host memory, they require specific hardware features which are not available on current generation network adapters. In this paper we describe the architectural modifications required to implement peer-to-peer access to NVIDIA Fermi- and Kepler-class GPUs on an FPGA-based cluster interconnect. Besides, the current software implementation, which integrates this feature by minimally extending the RDMA programming model, is discussed, as well as some issues raised while employing it in a higher level API like MPI. Finally, the current limits of the technique are studied by analyzing the performance improvements on low-level benchmarks and on two GPU-accelerated applications, showing when and how they seem to benefit from the GPU peer-to-peer method.

physics.comp-ph↗

arXiv2010

Shear Banding from lattice kinetic models with competing interactions

Soft Glassy Materials, Non Linear Rheology, Lattice Kinetic models, frustrated phase separation} We present numerical simulations based on a Boltzmann kinetic model with competing interactions, aimed at characterizating the rheological properties of soft-glassy materials. The lattice kinetic model is shown to reproduce typical signatures of driven soft-glassy flows in confined geometries, such as Herschel-Bulkley rheology, shear-banding and histeresys. This lends further credit to the present lattice kinetic model as a valuable tool for the theoretical/computational investigation of the rheology of driven soft-glassy materials under confinement.

cond-mat.soft↗

arXiv2009

Quantized biopolymer translocation through nanopores: departure from simple scaling

We discuss multiscale simulations of long biopolymer translocation through wide nanopores that can accommodate multiple polymer strands. The simulations provide clear evidence of folding quantization, namely, the translocation proceeds through multi-folded configurations characterized by a well-defined integer number of folds. As a consequence, the translocation time acquires a dependence on the average folding number, which results in a deviation from the single-exponent power-law characterizing single-file translocation through narrow pores. The mechanism of folding quantization allows polymers above a threshold length (approximately $1,000$ persistence lengths for double-stranded DNA) to exhibit cooperative behavior and as a result to translocate noticeably faster.

physics.bio-ph↗

arXiv2009

Numerical simulation of conformational variability in biopolymer translocation through wide nanopores

Numerical results on the translocation of long biopolymers through mid-sized and wide pores are presented. The simulations are based on a novel methodology which couples molecular motion to a mesoscopic fluid solvent. Thousands of events of long polymers (up to 8000 monomers) are monitored as they pass through nanopores. Comparison between the different pore sizes shows that wide pores can host a larger number of multiple biopolymer segments, as compared to smaller pores. The simulations provide clear evidence of folding quantization in the translocation process as the biopolymers undertake multi-folded configurations, characterized by a well-defined integer number of folds. Accordingly, the translocation time is no longer represented by a single-exponent power law dependence on the length, as it is the case for single-file translocation through narrow pores. The folding quantization increases with the biopolymer length, while the rate of translocated beads at each time step is linearly correlated to the number of resident beads in the pore. Finally, analysis of the statistics over the translocation work unravels the importance of the hydrodynamic interactions in the process.

physics.bio-ph↗

arXiv2008

Quantized current blockade and hydrodynamic correlations in biopolymer translocation through nanopores: evidence from multiscale simulations

We present a detailed description of biopolymer translocation through a nanopore in the presence of a solvent, using an innovative multi-scale methodology which treats the biopolymer at the microscopic scale as combined with a self-consistent mesoscopic description for the solvent fluid dynamics. We report evidence for quantized current blockade depending on the folding configuration and offer detailed information on the role of hydrodynamic correlations in speeding-up the translocation process.

physics.comp-ph↗

arXiv2007

Parallel multiscale modeling of biopolymer dynamics with hydrodynamic correlations

We employ a multiscale approach to model the translocation of biopolymers through nanometer size pores. Our computational scheme combines microscopic Molecular Dynamics (MD) with a mesoscopic Lattice Boltzmann (LB) method for the solvent dynamics, explicitly taking into account the interactions of the molecule with the surrounding fluid. We describe an efficient parallel implementation of the method which exhibits excellent scalability on the Blue Gene platform. We investigate both dynamical and statistical aspects of the translocation process by simulating polymers of various initial configurations and lengths. For a representative molecule size, we explore the effects of important parameters that enter in the simulation, paying particular attention to the strength of the molecule-solvent coupling and of the external electric field which drives the translocation process. Finally, we explore the connection between the generic polymers modeled in the simulation and DNA, for which interesting recent experimental results are available.

physics.comp-ph↗

arXiv2000

A critical review of techniques for Term Structure analysis

Fixed income markets share many features with the equity markets. However there are significant differences as well and many attempts have been done in the past to develop specific tools which describe (and possibly forecasts) the behavior of such markets. For instance, a correct pricing of fixed income securities with fixed cache flows requires the knowledge of the {\it term structure} of interest rates. A number of techniques have been proposed for estimating and interpreting the term structure, yet solid theoretical foundations and a comparative assessment of the results produced by these techniques are not available. In this paper we define the fundamental concepts with a mathematical terminology. Besides that, we report about an extensive set of experiments whose scope is to point out the strong and weak points of the most widely used approaches in this field.

cond-mat↗