PLUTO plus : Near-Complete Modeling of Affine Transformations for Parallelism and Locality

Affine transformations have proven to be very powerful for loop restructuring due to their ability to model a very wide range of transformations. A single multi-dimensional affine function can represent a long and complex sequence of simpler transformations. Existing affine transformation frameworks like the Pluto algorithm, that include a cost function for modern multicore architectures where coarse-grained parallelism and locality are crucial, consider only a sub-space of transformations to avoid a combinatorial explosion in finding the transformations. The ensuing practical tradeoffs lead to the exclusion of certain useful transformations, in particular, transformation compositions involving loop reversals and loop skewing by negative factors. In this paper, we propose an approach to address this limitation by modeling a much larger space of affine transformations in conjunction with the Pluto algorithm's cost function. We perform an experimental evaluation of both, the effect on compilation time, and performance of generated codes. The evaluation shows that our new framework, Pluto+, provides no degradation in performance in any of the Polybench benchmarks. For Lattice Boltzmann Method (LBM) codes with periodic boundary conditions, it provides a mean speedup of 1.33x over Pluto. We also show that Pluto+ does not increase compile times significantly. Experimental results on Polybench show that Pluto+ increases overall polyhedral source-to-source optimization time only by 15%. In cases where it improves execution time significantly, it increased polyhedral optimization time only by 2.04x.

Nanoparticle induced miscibility in LCST polymer blends: critically assessing the enthalpic and entropic effects

The use of copolymer and polymer blends widened the possibility of creating materials with multilayered architectures. Hierarchical polymer systems with a wide array of micro and nanostructures are generated by thermally induced phase separation (TIPS) in partially miscible polymer blends. Various parameters like the interaction between the polymers, concentration, solvent/non-solvent ratio, and quenching temperature have to be optimized to obtain these micro/nanophase structures. Alternatively, the addition of nanoparticles is another strategy to design materials with desired hetero-phase structures. The dynamics of the polymer nanocomposite depends on the statistical ordering of polymers around the nanoparticle, which is dependent on the shape of the nanoparticle. The entropic loss due to deformation of polymer chains, like the repulsive interactions due to coiling and the attractive interactions in the case of swelling has been highlighted in this perspective article. The dissipative particle dynamics has been discussed and is correlated with the molecular dynamics simulation in the case of polymer blends. The Cahn Hillard Cook model on variedly shaped immobile fillers has shown difference in the propagation of the composition wave. The nanoparticle shape has a contributing effect on the polymer particle interaction, which can change the miscibility window in the case of these phase separating polymer blends. Quantitative information on the effect of spherical particles on the demixing temperature is well established and further modified to explain the percolation of rod shaped particles in the polymer blends. These models correlate well with the experimental observations in context to the dynamics induced by the nanoparticle in the demixing behavior of the polymer blend. The miscibility of the LCST polymer blend depends on the enthalpic factors like the specific interaction between the components, and the solubility product and the entropic losses occurring due to the formation of any favorable interactions. Hence, it is essential to assess the entropic and enthalpic interactions induced by the nanoparticles independently. The addition of nanoparticles creates heterogeneity in the polymer phase it is localized. This can be observed as an alteration in the relaxation behavior of the polymer. This changes the demixing behavior and the interaction parameter between the polymers. The compositional changes induced due to the incorporation of nanoparticles are also attributed as a reason for the altered demixing temperature. The particle shape anisotropy causes a direction dependent depletion, which changes the phase behavior of the blend. The polymer-grafted nanoparticles with varying grafting density show tremendous variation in the miscibility of the blend. The stretching of the polymer chains grafted on the nanoparticles causes an entropy penalty in the polymer blend. A comparative study on the different shaped particles is not available up to date for understanding these aspects. Hence, we have juxtaposed the various computational studies on nanoparticle dynamics, the shape effect of NPs on homopolymers and also the cases of various polymer blends without nanoparticles to sketch a complete picture on the effect of various particles on the miscibility of LCST blends.

Conceptual design of three-dimensional scaffolds of powder-based materials for bone tissue engineering applications

Purpose - The purpose of this paper is to investigate the possibility to construct tissue-engineered bone repair scaffolds with pore size distributions using rapid prototyping techniques. Design/methodology/approach - The fabrication of porous scaffolds with complex porous architectures represents a major challenge in tissue engineering and the design aspects to mimic complex pore shape as well as spatial distribution of pore sizes of natural hard tissue remain unexplored. In this context, this work aims to evaluate the three-dimensional printing process to study its potential for scaffold fabrication as well as some innovative design of homogeneously porous or gradient porous scaffolds is described and such design has wider implication in the field of bone tissue engineering. Findings - The present work discusses biomedically relevant various design strategies with spatial/radial gradient in pore sizes as well as with different pore sizes and with different pore geometries. Originality/value - One of the important implications of the proposed novel design scheme would be the development of porous bioactive/biodegradable composites with gradient pore size, porosity, composition and with spatially distributed biochemical stimuli so that stem cells loaded into scaffolds would develop into complex tissues such as those at the bone-cartilage interface.

Electron mobility in few-layer MoxW1-xS2

Heterostructures of two-dimensional (2D) layered materials are increasingly being explored for electronics in order to potentially extend conventional transistor scaling and to exploit new device designs and architectures. Alloys form a key underpinning of any heterostructure device technology and therefore an understanding of their electronic properties is essential. In this paper, we study the intrinsic electron mobility in few-layer MoxW1-xS2 as limited by various scattering mechanisms. The room temperature, energy-dependent scattering times corresponding to polar longitudinal optical (LO) phonon, alloy and background impurity scattering mechanisms are estimated based on the Born approximation to Fermi's golden rule. The contribution of individual scattering rates is analyzed as a function of 2D electron density as well as of alloy composition in MoxW1-xS2. While impurity scattering limits the mobility for low carrier densities (<2-4x10(12) cm(-2)), LO polar phonon scattering is the dominant mechanism for high electron densities. Alloy scattering is found to play a non-negligible role for 0.5 < x < 0.7 in MoxW1-xS2. The LO phonon-limited and impurity-limited mobilities show opposing trends with respect to alloy mole fractions. The understanding of electron mobility in MoxW1-xS2 presented here is expected to enable the design and realization of heterostructures and devices based on alloys of MoS2 andWS(2).

Molecular Cage Impregnated Palladium Nanoparticles: Efficient, Additive-Free Heterogeneous Catalysts for Cyanation of Aryl Halides

Two shape-persistent covalent cages (CC1(r) and CC2(r)) have been devised from triphenyl amine-based trialdehydes and cyclohexane diamine building blocks utilizing the dynamic imine chemistry followed by imine bond reduction. The cage compounds have been characterized by several spectroscopic techniques which suggest that CC1(r) and CC2(r) are 2+3] and 8+12] self-assembled architectures, respectively. These state-of-the-art molecules have a porous interior and stable aromatic backbone with multiple palladium binding sites to engineer the controlled synthesis and stabilization of ultrafine palladium nanoparticles (PdNPs). As-synthesized cage-embedded PdNPs have been characterized by transmission electron microscopy (TEM), scanning electron microscopy (SEM), and powder X-ray diffraction (PXRD). Inductively coupled plasma optical emission spectrometry reveals that Pd@CC1(r) and Pd@CC2(r) have 40 and 25 wt% palladium loading, respectively. On the basis of TEM analysis, it has been estimated that as small as similar to 1.8 nm PdNPs could be stabilized inside the CC1(r), while larger CC2(r) could stabilize similar to 3.7 nm NPs. In contrast, reduction of palladium salts in the absence of the cages form structure less agglomerates. The well-dispersed cage-embedded NPs exhibit efficient catalytic performance in the cyanation of aryl halides under heterogeneous, additive-free condition. Moreover, these materials have excellent stability and recyclability without any agglomeration of PdNPs after several cycles.

Electron mobility in few-layer MoxW1-xS2

Heterostructures of two-dimensional (2D) layered materials are increasingly being explored for electronics in order to potentially extend conventional transistor scaling and to exploit new device designs and architectures. Alloys form a key underpinning of any heterostructure device technology and therefore an understanding of their electronic properties is essential. In this paper, we study the intrinsic electron mobility in few-layer MoxW1-xS2 as limited by various scattering mechanisms. The room temperature, energy-dependent scattering times corresponding to polar longitudinal optical (LO) phonon, alloy and background impurity scattering mechanisms are estimated based on the Born approximation to Fermi's golden rule. The contribution of individual scattering rates is analyzed as a function of 2D electron density as well as of alloy composition in MoxW1-xS2. While impurity scattering limits the mobility for low carrier densities (<2-4x10(12) cm(-2)), LO polar phonon scattering is the dominant mechanism for high electron densities. Alloy scattering is found to play a non-negligible role for 0.5 < x < 0.7 in MoxW1-xS2. The LO phonon-limited and impurity-limited mobilities show opposing trends with respect to alloy mole fractions. The understanding of electron mobility in MoxW1-xS2 presented here is expected to enable the design and realization of heterostructures and devices based on alloys of MoS2 andWS(2).

PolyMage: Automatic Optimization for Image Processing Pipelines

This paper presents the design and implementation of PolyMage, a domain-specific language and compiler for image processing pipelines. An image processing pipeline can be viewed as a graph of interconnected stages which process images successively. Each stage typically performs one of point-wise, stencil, reduction or data-dependent operations on image pixels. Individual stages in a pipeline typically exhibit abundant data parallelism that can be exploited with relative ease. However, the stages also require high memory bandwidth preventing effective utilization of parallelism available on modern architectures. For applications that demand high performance, the traditional options are to use optimized libraries like OpenCV or to optimize manually. While using libraries precludes optimization across library routines, manual optimization accounting for both parallelism and locality is very tedious. The focus of our system, PolyMage, is on automatically generating high-performance implementations of image processing pipelines expressed in a high-level declarative language. Our optimization approach primarily relies on the transformation and code generation capabilities of the polyhedral compiler framework. To the best of our knowledge, this is the first model-driven compiler for image processing pipelines that performs complex fusion, tiling, and storage optimization automatically. Experimental results on a modern multicore system show that the performance achieved by our automatic approach is up to 1.81x better than that achieved through manual tuning in Halide, a state-of-the-art language and compiler for image processing pipelines. For a camera raw image processing pipeline, our performance is comparable to that of a hand-tuned implementation.

Accelerating method of moments based package-board 3D parasitic extraction using FPGA

In this article, a Field Programmable Gate Array (FPGA)-based hardware accelerator for 3D electromagnetic extraction, using Method of Moments (MoM) is presented. As the number of nets or ports in a system increases, leading to a corresponding increase in the number of right-hand-side (RHS) vectors, the computational cost for multiple matrix-vector products presents a time bottleneck in a linear-complexity fast solver framework. In this work, an FPGA-based hardware implementation is proposed toward a two-level parallelization scheme: (i) matrix level parallelization for single RHS and (ii) pipelining for multiple-RHS. The method is applied to accelerate electrostatic parasitic capacitance extraction of multiple nets in a Ball Grid Array (BGA) package. The acceleration is shown to be linearly scalable with FPGA resources and speed-ups over 10x against equivalent software implementation on a 2.4GHz Intel Core i5 processor is achieved using a Virtex-6 XC6VLX240T FPGA on Xilinx's ML605 board with the implemented design operating at 200MHz clock frequency. (c) 2016 Wiley Periodicals, Inc. Microwave Opt Technol Lett 58:776-783, 2016