Synergistic Execution of Stream Programs on Multicores with Accelerators

The StreamIt programming model has been proposed to exploit parallelism in streaming applications oil general purpose multicore architectures. The StreamIt graphs describe task, data and pipeline parallelism which can be exploited on accelerators such as Graphics Processing Units (GPUs) or CellBE which support abundant parallelism in hardware. In this paper, we describe a novel method to orchestrate the execution of if StreamIt program oil a multicore platform equipped with an accelerator. The proposed approach identifies, using profiling, the relative benefits of executing a task oil the superscalar CPU cores and the accelerator. We formulate the problem of partitioning the work between the CPU cores and the GPU, taking into account the latencies for data transfers and the required buffer layout transformations associated with the partitioning, as all integrated Integer Linear Program (ILP) which can then be solved by an ILP solver. We also propose an efficient heuristic algorithm for the work-partitioning between the CPU and the GPU, which provides solutions which are within 9.05% of the optimal solution on an average across the benchmark Suite. The partitioned tasks are then software pipelined to execute oil the multiple CPU cores and the Streaming Multiprocessors (SMs) of the GPU. The software pipelining algorithm orchestrates the execution between CPU cores and the GPU by emitting the code for the CPU and the GPU, and the code for the required data transfers. Our experiments on a platform with 8 CPU cores and a GeForce 8800 GTS 512 GPU show a geometric mean speedup of 6.94X with it maximum of 51.96X over it single threaded CPU execution across the StreamIt benchmarks. This is a 18.9% improvement over it partitioning strategy that maps only the filters that cannot be executed oil the GPU - the filters with state that is persistent across firings - onto the CPU.

Origin of activation of Lattice Oxygen and Synergistic Interaction in Bimetal-Ionic Ce0.89Fe0.1Pd0.01O2-delta Catalyst

Flourite-type nanocrystalline Ce0.9Fe0.1O2-delta and Ce0.89Fe0.1Pd0.01O2-delta solid solutions have been synthesized by solution combustion method,'.which show higher oxygen storage/release property (OSC) compared to CeO2 and Ce0.8Zr0.2O2. Temperature programmed reduction an XPS study reveal that the presence of Pd ion in Ce0.9Fe0.1O2-delta facilitates complete reduction of Fe3+ to Fe2+ state and partial reduction of Ce4+ to Ce3+ state at.temperatures as low as 105 degrees C compared to 400 degrees C for monometal-ionic Ce0.9Fe0.1O2-delta. Fe3+ ion is reduced to Fe2+ and not to Feo due to favorable redox potential for Ce4+ + Fe2+ -> Ce3+ + Fe3+ reaction. Using first-principles density functional theory calculation we determine M-O (M = Pd, Fe, Ce) bond lengths, and find that bond lengths vary from shorter (2.16 angstrom) to longer (2.9 angstrom) bond distances compared to mean Ce-O bond distance of 2.34 angstrom. for CeO2. Using these results in bond valence analysis, we show that oxygen with bond valences as low as -1.55 are created, leading to activation of lattice oxygen in the bimetal ionic catalyst. Temperatures of CO oxidation and NO reduction by CO/H-2 are lower with the bimetalionic Ce0.89Fe0.1Pd0.01O2-delta catalyst compared to monometal-ionic Ce0.9Fe0.1O2-delta and Ce0.99Pd0.01O2-delta catalysts. From XPS studies of Pd impregnated on CeO2 and Fe2O3 oxides, we show that the synergism leading to low temperature activation of lattice oxygen in bimetal-ionic catalyst Ce0.89Fe0.1Pd0.01O2-delta is due to low-temperature reduction of Pd2+ to Pd-0, followed by Pd-0 + 2Fe(3+) -> Pd2+ + 2Fe(2+), Pd-0 + 2Ce(4+) -> Pd2+ + 2Ce(3+) redox reaction.

Synergistic effects of UdgB and Ung in mutation prevention and protection against commonly encountered DNA damaging agents in Mycobacterium smegmatis

The incorporation of dUMP during replication or the deamination of cytosine in DNA results in the occurrence of uracils in genomes. To maintain genomic integrity, uracil DNA glycosylases (UDGs) excise uracil from DNA and initiate the base-excision repair pathway. Here, we cloned, purified and biochemically characterized a family 5 UDG, UdgB, from Mycobacterium smegmatis to allow us to use it as a model organism to investigate the physiological significance of the novel enzyme. Studies with knockout strains showed that compared with the wild-type parent, the mutation rate of the udgB(-) strain was approximately twofold higher, whereas the mutation rate of a strain deficient in the family 1 UDG (ung(-)) was found to be similar to 8.4-fold higher. Interestingly, the mutation rate of the double-knockout (ung(-)ludgB(-)) strain was remarkably high, at similar to 19.6-fold. While CG to TA mutations predominated in the ung(-) and ung(-)/udgb(-) strains, AT to GC mutations were enhanced in the udgB(-) strain. The ung(-)/udgB(-) strain was notably more sensitive to acidified nitrite and hydrogen peroxide stresses compared with the single knockouts (ung(-) or udgB(-)). These observations reveal a synergistic effect of UdgB and Ung in DNA repair, and could have implications for the generation of attenuated strains of Mycobacterium tuberculosis.

Chemical Aspects of the Synergistic Hypergolic Ignition in Hybrid Systems with N2O4 as Oxidizer

Synergistic hypergolic ignition with nitrogen tetroxide ( N2O4) as oxidizer has been observed in hybrid systems comprising of a mixture of magnesium and Schiff bases as fuels. The ignition delays (IDs) measured using a modified device, have been compared with those of magnesium-Schiff base-WFNA systems under identical conditions. The ID has been found to vary with the nature of the substitution in both the benzene rings. A linear relationship emerges when the ignition delays are plotted against the Hammett substitution constants (σ). The preignition products of the reaction of N2O4 with magnesium and benzylidineaniline have been analysed to be Mg(NO3)2, benzenediazonium salt and benzaldehyde. Based on the preignition products isolated, a probable reaction mechanism has been proposed. The previously proposed preignition mechanism for the Schiff base-magnesium-WFNA system has been further supported from the present ignition delay data.

Synergistic use of thermogravimetric and electrochemical techniques for thermodynamic study of TiOx (1.67 <= x <= 2.0) at 1573 K

A thermodynamic study of the Ti-O system at 1573 K has been conducted using a combination of thermogravimetric and emf techniques. The results indicate that the variation of oxygen potential with the nonstoichiometric parameter delta in stability domain of TiO2-delta with rutile structure can be represented by the relation, Delta mu o(2) = -6RT In delta - 711970(+/-1600) J/mol. The corresponding relation between non-stoichiometric parameter delta and partial pressure of oxygen across the whole stability range of TiO2-delta at 1573 K is delta proportional to P-O2(-1/6). It is therefore evident that the oxygen deficient behavior of nonstoichiometric TiO2-delta is dominated by the presence of doubly charged oxygen vacancies and free electrons. The high-precision measurements enabled the resolution of oxygen potential steps corresponding to the different Magneli phases (Ti-n O2n-1) up to n = 15. Beyond this value of n, the oxygen potential steps were too small to be resolved. Based on composition of the Magneli phase in equilibrium with TiO2-delta, the maximum value of n is estimated to be 28. The chemical potential of titanium was derived as a function of composition using the Gibbs-Duhem relation. Gibbs energies of formation of the Magneli phases were derived from the chemical potentials of oxygen and titanium. The values of -2441.8(+/-5.8) kJ/mol for Ti4O7 and -1775.4(+/-4.3) kJ/mol for Ti3O5 Obtained in this study refine values of -2436.2(+/-26.1) kJ/mol and-1771.3(+/-6.9) kJ/mol, respectively, given in the JANAF thermochemical tables.

Synergistic interaction between particular X-chromosome deletions andSex-lethal causes female lethality inDrosophila melanogaster

We studied the effect on female viability of trans-heterozygous combinations of X-chromosome deficiencies and Sxt-(fl), a null allele of Sex-lethal. Twentyfive deficiencies, which together covered 80% of the X chromosome, were tested. Seven of these trans-heterozygous combinations caused significant levels of female lethality. Two of the seven interacting deficiencies include the previously known sex determination genes sans fille and sisterless-a. Four of the remaining uncover X-chromosomal regions that were not hitherto known to contain sex determination genes. These newly identified regions are defined by deficiencies Df(1)RA2 (7D10; 8A4-5), Df(1)KA14 (7F1-2; 8C6), Df(1)C52 (8E; 9C-D) and Df(1)N19 (17A1; 18A2). These four deficiencies were characterized further to determine whether it was the maternal or zygotic dosage that was primarily responsible for the observed lethality of female embryos, daughterless and extra macrochaetae, two known regulators of Sxl, influence the interaction of these deficiencies with Sxl.

Ultrafast Microwave-Assisted Route to Surfactant-Free Ultrafine Pt Nanoparticles on Graphene: Synergistic Co-reduction Mechanism and High Catalytic Activity

We demonstrate an ultrafast method for the formation of, graphene supported Pt catalysts by the co-reduction of graphene oxide and Pt salt using ethylene glycol under microwave irradiation conditions. Detailed analysis of the mechanism of formation of the hybrids indicates a synergistic co-reduction mechanism whereby the presence of the Pt ions leads to a faster reduction of GO and the presence of the defect sites on the reduced GO serves as anchor points for the heterogeneous nucleation of Pt. The resulting hybrid consists of ultrafine nanoparticles of Pt uniformly distributed on the reduced GO susbtrate. We have shown that the hybrid exhibits good catalytic activity for methanol oxidation and hydrogen conversion reactions. The mechanism is general and applicable for the synthesis of other multifunctional hybrids based on graphene.

Synergistic effect of UVB radiation and age on HMPS enzymes in rat lens homogenate

The behaviour of rat lenticular enzymes, glucose-6-phosphate dehydrogena.se (G6PD, EC: 1.1.1.49) and 6-phosphogluconate dehydrogenase (6PGD, EC: 1.1.1.44) as a function of age and UVB irradiation (in vitro) was investigated by irradiating the lens homogenate from 3-and 12-month-old rats at 300 nm (100 μW cm 2). In the 3-month-old group the specific activities of G6PD and 6PGD were reduced by 26% and 42%, respectively, after 24 h of irradiation, whereas in the 12-month-old group the decrease was 38% and 49% respectively, which suggests that the susceptibility of HMPS enzymes to UVB damage is higher in older lenses. The decrease in specitic activity was associated with a change in apparent Km and Vmax (marginal in 3 months and significant in 12 months) of these enzymes due to UVB irradiation. UVB irradiation also decreased the levels of NADPH and NADPH/NADP ratio. These changes, altered activities of G6PD and 6PGD and altered levels of NADPH. may in turn have a bearing on lens transparency.

Automatic Compilation of MATLAB Programs for Synergistic Execution on Heterogeneous Processors

MATLAB is an array language, initially popular for rapid prototyping, but is now being increasingly used to develop production code for numerical and scientific applications. Typical MATLAB programs have abundant data parallelism. These programs also have control flow dominated scalar regions that have an impact on the program's execution time. Today's computer systems have tremendous computing power in the form of traditional CPU cores and throughput oriented accelerators such as graphics processing units(GPUs). Thus, an approach that maps the control flow dominated regions to the CPU and the data parallel regions to the GPU can significantly improve program performance. In this paper, we present the design and implementation of MEGHA, a compiler that automatically compiles MATLAB programs to enable synergistic execution on heterogeneous processors. Our solution is fully automated and does not require programmer input for identifying data parallel regions. We propose a set of compiler optimizations tailored for MATLAB. Our compiler identifies data parallel regions of the program and composes them into kernels. The problem of combining statements into kernels is formulated as a constrained graph clustering problem. Heuristics are presented to map identified kernels to either the CPU or GPU so that kernel execution on the CPU and the GPU happens synergistically and the amount of data transfer needed is minimized. In order to ensure required data movement for dependencies across basic blocks, we propose a data flow analysis and edge splitting strategy. Thus our compiler automatically handles composition of kernels, mapping of kernels to CPU and GPU, scheduling and insertion of required data transfer. The proposed compiler was implemented and experimental evaluation using a set of MATLAB benchmarks shows that our approach achieves a geometric mean speedup of 19.8X for data parallel benchmarks over native execution of MATLAB.

ZnO/Ag nanohybrid: synthesis, characterization, synergistic antibacterial activity and its mechanism

A highly homogeneous ZnO/Ag nanohybrid has been synthesized by a novel route, employing chitosan as mediator by purely electrostatic interaction. By employing various techniques such as powder XRD, UV-visible, IR spectroscopy and electron (SEM, TEM) microscopy, the formation of the nanohybrid has been established. The synergistic antibacterial effect of ZnO/Ag nanohybrid on Gram-positive and Gram-negative bacteria is found to be more effective, compared to the individual components (ZnO and Ag). Cytotoxicity experiments are carried out and the results are correlated to the solubility of the nanohybrid. A possible mechanism has been proposed for the antibacterial activity of ZnO/Ag nanohybrid, based on TEM studies on bacteria, carried out by employing the microtome technique and by EPR measurements on the hybrid.

Approaching theoretical strengths by synergistic internal and external size refinement

Refinement of the internal grain size leads to strengthening by retarding dislocation motion. There have also been recent reports that a reduction in external diameter enhances the strength of single crystal pillars. Here we show, in a hitherto unexplored domain, a synergistic increase in strength by a combined reduction in internal (0.5 mu m) and external (20-50 mu m) dimensions, with strengths at failure approaching the theoretical value. (c) 2012 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Automatic compilation of MATLAB programs for synergistic execution on heterogeneous processors

MATLAB is an array language, initially popular for rapid prototyping, but is now being increasingly used to develop production code for numerical and scientific applications. Typical MATLAB programs have abundant data parallelism. These programs also have control flow dominated scalar regions that have an impact on the program's execution time. Today's computer systems have tremendous computing power in the form of traditional CPU cores and throughput oriented accelerators such as graphics processing units(GPUs). Thus, an approach that maps the control flow dominated regions to the CPU and the data parallel regions to the GPU can significantly improve program performance. In this paper, we present the design and implementation of MEGHA, a compiler that automatically compiles MATLAB programs to enable synergistic execution on heterogeneous processors. Our solution is fully automated and does not require programmer input for identifying data parallel regions. We propose a set of compiler optimizations tailored for MATLAB. Our compiler identifies data parallel regions of the program and composes them into kernels. The problem of combining statements into kernels is formulated as a constrained graph clustering problem. Heuristics are presented to map identified kernels to either the CPU or GPU so that kernel execution on the CPU and the GPU happens synergistically and the amount of data transfer needed is minimized. In order to ensure required data movement for dependencies across basic blocks, we propose a data flow analysis and edge splitting strategy. Thus our compiler automatically handles composition of kernels, mapping of kernels to CPU and GPU, scheduling and insertion of required data transfer. The proposed compiler was implemented and experimental evaluation using a set of MATLAB benchmarks shows that our approach achieves a geometric mean speedup of 19.8X for data parallel benchmarks over native execution of MATLAB.

Synergistic effect of reactor chemistry and compressive stress on dislocation bending during GaN growth

The synergistic effect of compressive growth stresses and reactor chemistry, silane presence, on dislocation bending at the very early stages of GaN growth has been studied using in-situ stress measurements and cross-sectional transmission electron microscopy. A single 100 nm Si-doped GaN layer is found to be more effective than a 1 mu m linearly graded AlGaN buffer layer in reducing dislocation density and preventing the subsequent layer from transitioning to a tensile stress. 1 mu m crack-free GaN layers with a dislocation density of 7 x 10(8)/cm(2), with 0.13 nm surface roughness and no enhancement in n-type background are demonstrated over 2 inch substrates using this simple transition scheme. (C) 2013 AIP Publishing LLC.

Employing synergistic interactions between few-layer WS2 and reduced graphene oxide to improve lithium storage, cyclability and rate capability of Li-ion batteries

The aim of the contribution is to introduce a high performance anode alternative to graphite for lithium-ion batteries (LiBs). A simple process was employed to synthesize uniform graphene-like few-layer tungsten sulfide (WS2) supported on reduced graphene oxide (RGO) through a hydrothermal synthesis route. The WS2-RGO (80:20 and 70:30) composites exhibited good enhanced electrochemical performance and excellent rate capability performance when used as anode materials for lithium-ion batteries. The specific capacity of the WS2-RGO composite delivered a capacity of 400-450 mAh g(-1) after 50 cycles when cycled at a current density of 100 mA g(-1). At 4000 mA g(-1), the composites showed a stable capacity of approximately 180-240 mAh g(-1), respectively. The noteworthy electrochemical performance of the composite is not additive, rather it is synergistic in the sense that the electrochemical performance is much superior compared to both WS2 and RGO. As the observed lithiation/delithiation for WS2-RGO is at a voltage 1.0 V (approximate to 0.1 V for graphite, Li* /Li), the lithium-ion battery with WS2-RGO is expected to possess high interface stability, safety and management of electrical energy is expected to be more efficient and economic. (C) 2013 Elsevier Ltd. All rights reserved.

Synergistic Lewis base and anion-binding catalysis for the enantioselective vinylogous addition of deconjugated butenolides to allenoates

An enantioselective vinylogous umpolung addition of deconjugated butenolides to allenoates has been developed for the first time with the help of synergistic combination of an achiral phosphine and a chiral squaramide, and represents the first example of a catalytic enantioselective C gamma-C gamma bond formation between two different carbonyl partners.