A unified framework for optimizing locality, parallelism, andcommunication in out-of-core computations

This paper presents a unified framework that optimizes out-of-core programs by exploiting locality and parallelism, and reducing communication overhead. For out-of-core problems where the data set sizes far exceed the size of the available in-core memory, it is particularly important to exploit the memory hierarchy by optimizing the I/O accesses. We present algorithms that consider both iteration space (loop) and data space (file layout) transformations in a unified framework. We show that the performance of an out-of-core loop nest containing references to out-of-core arrays can be improved by using a suitable combination of file layout choices and loop restructuring transformations. Our approach considers array references one-by-one and attempts to optimize each reference for parallelism and locality. When there are references for which parallelism optimizations do not work, communication is vectorized so that data transfer can be performed before the innermost loop. Results from hand-compiles on IBM SP-2 and Inter Paragon distributed-memory message-passing architectures show that this approach reduces the execution times and improves the overall speedups. In addition, we extend the base algorithm to work with file layout constraints and show how it is useful for optimizing programs that consist of multiple loop nests     

A High-Throughput Distributed Shared-Buffer NoC Router

Microarchitectural configurations of buffers in routers have a significant impact on the overall performance of an on-chip network (NoC). This buffering can be at the inputs or the outputs of a router, corresponding to an input-buffered router (IBR) or an output-buffered router (OBR). OBRs are attractive because they have higher throughput and lower queuing delays under high loads than IBRs. However, a direct implementation of OBRs requires a router speedup equal to the number of ports, making such a design prohibitive given the aggressive clocking and power budgets of most NoC applications. In this letter, we propose a new router design that aims to emulate an OBR practically based on a distributed shared-buffer (DSB) router architecture. We introduce innovations to address the unique constraints of NoCs, including efficient pipelining and novel flow control. Our DSB design can achieve significantly higher bandwidth at saturation, with an improvement of up to 20% when compared to a state-of-the-art pipelined IBR with the same amount of buffering, and our proposed microarchitecture can achieve up to 94% of the ideal saturation throughput.     

Photoinduced circular anisotropy in side-chain azobenzene polyesters

We report for the first time the inducing of large circular anisotropy in previously unoriented films of side-chain azobenzene polyesters on illumination with circularly polarized light at a wavelength of 488 nm. The circular dichroism and optical activity are measured simultaneously in real time at two wavelengths, 488 nm and 633 nm. The photoinduced optical activity has been measured to be 10⁴ deg/cm and the circular dichroism has been found to be on the order of 0.3.     

EFFECTS OF GRINDING AIDS VIBRATION MILLING OF ALUMINUM

Fine aluminum powder is widely used in making paints, printing inks, slurry explosives, pyrotechnic chemicals etc. Hence the production of aluminum powder is highly important. In this paper the effect of grinding aids on the grinding characteristics of aluminum in a vibration mill under an inert atmosphere of nitrogen has been investigated. It is found that the use of grinding aids is essential in grinding of atomized aluminum. Among four different grinding aids, stearic acid appears to be the best grinding aid.     

Comments on "Wide-band diffraction improved dual-shaped reflectors"

It is pointed out that the procedure mentioned in the above paper need not be followed for dual-reflector systems using small subreflectors. In addition, a uniform procedure suitable for both large and small subreflector systems, is presented.     

GTD analysis of the radiation patterns of a prime focus paraboloid with shroud

The uniform geometrical theory of diffraction (UGTD) is employed to analyze the far-field radiation patterns of a prime focus paraboloid with a cylindrical shroud. The blockage of the aperture illumination of the dish by the gooseneck and the primary feed is also taken into account in the analysis. Far-field radiation patterns (for0degleqTheta leq 180deg), calculated for a typical prime focus paraboloid with 2 m aperture diameter, designed and fabricated, are compared with the experimentally derived patterns at 8.8 GHz in theE- andH-planes. There is a satisfactory agreement between the two results.     

Zinc Tin Oxide (ZTO) electron transporting buffer layer in inverted organic solar cell

Solution processed, high electron mobility and highly transparent Zinc Tin Oxide (ZTO) was successfully exploited as electron transporting buffer layer in an inverted organic solar cell. The device configuration of FTO/ZTO/P3HT:PCBM/WO₃/Ag was employed. For comparison, an identical device using a sol–gel derived TiO_x electron extracting layer was also fabricated. Increased short-circuit density (J_sc) and open-circuit voltage (V_oc) were generated in the devices with ZTO layer in comparison to the ones with TiO_x layer. It is attributed to a better electron transporting, hole blocking capacities and reduced recombination probabilities at electron collecting electrode with ZTO layer. A power conversion efficiency of 3.05% was achieved with ZTO devices.     

Analytical model for time to cover cracking in RC structures due to rebar corrosion

The structural degradation of concrete structures due to reinforcement corrosion is a major worldwide problem. Reinforcement corrosion causes a volume increase due to the oxidation of metallic iron, which is mainly responsible for exerting the expansive radial pressure at the steel–concrete interface and development of hoop tensile stresses in the surrounding concrete. Cracking occurs, once the maximum hoop tensile stress exceeds the tensile strength of the concrete. The cracking begins at the steel–concrete interface and propagates outwards and eventually results in the thorough cracking of the cover concrete and this would indicate the loss of service life for the corrosion affected structures. An analytical model is proposed to predict the time required for cover cracking and the weight loss of reinforcing bar in corrosion affected reinforced concrete structures. The modelling aspects of the residual strength of cracked concrete and the stiffness contribution from the combination of reinforcement and expansive corrosion products have also been incorporated in the model. The problem is modeled as a boundary value problem and the governing equations are expressed in terms of the radial displacement. The analytical solutions are presented considering a simple two-zone model for the cover concrete, viz. cracked or uncracked. Reasonable estimation of the various parameters in the model related to the composition and properties of expansive corrosion products based on the available published experimental data has also been discussed. The performance of the proposed corrosion cracking model is then investigated through its ability to reproduce available experimental trends. Reasonably good agreement between experimental results and the analytical predictions has been obtained. It has also been found that tensile strength and initial tangent modulus of cover concrete, annual mean corrosion rate and modulus of elasticity of reinforcement plus corrosion products combined significantly influence predicted time to cover cracking. The analytical predictions of the proposed model have also been found to be in line with those of the other reported published data.