Memory Architecture Exploration Framework for Cache Based Embedded SoC

Today's feature-rich multimedia products require embedded system solution with complex System-on-Chip (SoC) to meet market expectations of high performance at a low cost and lower energy consumption. The memory architecture of the embedded system strongly influences critical system design objectives like area, power and performance. Hence the embedded system designer performs a complete memory architecture exploration to custom design a memory architecture for a given set of applications. Further, the designer would be interested in multiple optimal design points to address various market segments. However, tight time-to-market constraints enforces short design cycle time. In this paper we address the multi-level multi-objective memory architecture exploration problem through a combination of exhaustive-search based memory exploration at the outer level and a two step based integrated data layout for SPRAM-Cache based architectures at the inner level. We present a two step integrated approach for data layout for SPRAM-Cache based hybrid architectures with the first step as data-partitioning that partitions data between SPRAM and Cache, and the second step is the cache conscious data layout. We formulate the cache-conscious data layout as a graph partitioning problem and show that our approach gives up to 34% improvement over an existing approach and also optimizes the off-chip memory address space. We experimented our approach with 3 embedded multimedia applications and our approach explores several hundred memory configurations for each application, yielding several optimal design points in a few hours of computation on a standard desktop.

MAX: A Multi Objective Memory Architecture eXploration Framework for Embedded Systems-on-Chip

Today's feature-rich multimedia products require embedded system solution with complex System-on-Chip (SoC) to meet market expectations of high performance at a low cost and lower energy consumption. The memory architecture of the embedded system strongly influences these parameters. Hence the embedded system designer performs a complete memory architecture exploration. This problem is a multi-objective optimization problem and can be tackled as a two-level optimization problem. The outer level explores various memory architecture while the inner level explores placement of data sections (data layout problem) to minimize memory stalls. Further, the designer would be interested in multiple optimal design points to address various market segments. However, tight time-to-market constraints enforces short design cycle time. In this paper we address the multi-level multi-objective memory architecture exploration problem through a combination of Multi-objective Genetic Algorithm (Memory Architecture exploration) and an efficient heuristic data placement algorithm. At the outer level the memory architecture exploration is done by picking memory modules directly from a ASIC memory Library. This helps in performing the memory architecture exploration in a integrated framework, where the memory allocation, memory exploration and data layout works in a tightly coupled way to yield optimal design points with respect to area, power and performance. We experimented our approach for 3 embedded applications and our approach explores several thousand memory architecture for each application, yielding a few hundred optimal design points in a few hours of computation time on a standard desktop.

Moore meets maxwell

Moore's Law has driven the semiconductor revolution enabling over four decades of scaling in frequency, size, complexity, and power. However, the limits of physics are preventing further scaling of speed, forcing a paradigm shift towards multicore computing and parallelization. In effect, the system is taking over the role that the single CPU was playing: high-speed signals running through chips but also packages and boards connect ever more complex systems. High-speed signals making their way through the entire system cause new challenges in the design of computing hardware. Inductance, phase shifts and velocity of light effects, material resonances, and wave behavior become not only prevalent but need to be calculated accurately and rapidly to enable short design cycle times. In essence, to continue scaling with Moore's Law requires the incorporation of Maxwell's equations in the design process. Incorporating Maxwell's equations into the design flow is only possible through the combined power that new algorithms, parallelization and high-speed computing provide. At the same time, incorporation of Maxwell-based models into circuit and system-level simulation presents a massive accuracy, passivity, and scalability challenge. In this tutorial, we navigate through the often confusing terminology and concepts behind field solvers, show how advances in field solvers enable integration into EDA flows, present novel methods for model generation and passivity assurance in large systems, and demonstrate the power of cloud computing in enabling the next generation of scalable Maxwell solvers and the next generation of Moore's Law scaling of systems. We intend to show the truly symbiotic growing relationship between Maxwell and Moore!

Structural Behavior of Story-High Cement-Stabilized Rammed-Earth Walls under Compression

A rammed-earth wall is a monolithic construction made by compacting processed soil in progressive layers in a rigid formwork. There is a growing interest in using this low-embodied-carbon building material in buildings. The paper investigates the strength and structural behavior of story-high cement-stabilized rammed-earth (CSRE) walls, reviews literature on the strength of CSRE, and discusses results of the compressive strength of CSRE prisms, wallettes, and story-high walls. The strength of the story-high wall was compared with the strength of wallettes and prisms. There is a nearly 30% reduction in strength as the height-to-thickness ratio increases from about 5 to 20. The ultimate compressive strength of CSRE walls predicted using the tangent modulus theory is in close agreement with the experimental values. The shear failures noticed in the story-high walls resemble the shear failures of short-height prism and wallette specimens. The paper ends with a discussion of structural design and characteristic compressive strength of CSRE walls. DOI: 10.1061/(ASCE)MT.1943-5533.0000155. (C) 2011 American Society of Civil Engineers.

Context dependent splicing functions of Bud31/Ycr063w define its role in budding and cell cycle progression

The yeast Bud31 protein, a Prp19 complex (NTC) member, aids spliceosome assembly and thus promotes efficient pre-mRNA splicing. The bud31 null cells show mild budding abnormalities at optimal growth temperatures and, at higher temperatures, have growth defects with aberrant budding. Here we have assessed cell cycle transitions which require Bud31. We find Bud31 facilitates passage through G1-S regulatory point (Start) but is not needed for G2-M transition or for exit from mitosis. To co-relate Bud31 functions in cell division with splicing, we studied the splicing status of transcripts that encode proteins involved in budding. We find Bud31 promotes efficient splicing of only some of these pre-mRNAs, for example, ARP2 and SRC1. Wild type cells have a long and a short isoform of SRC1 mRNA and protein, out of which the shorter mRNA splice variant is predominant. bud31 Delta cells show inefficient SRC1 splicing and entirely lack the shorter SRC1 spliced mRNA isoform. Yeast PRP17, another NTC sub-complex member, is also required for G1-S and G2-M cell cycle transitions. We examined genetic interactions between BUD31 and PRP17. While both factors were needed for efficient cell cycle dependent gene expression, our data indicate that distinct pre-mRNAs depend on each of these non-essential splicing factors.

TURBULENT PUMPING OF MAGNETIC FLUX REDUCES SOLAR CYCLE MEMORY AND THUS IMPACTS PREDICTABILITY OF THE SUN'S ACTIVITY

Prediction of the Sun's magnetic activity is important because of its effect on space environment and climate. However, recent efforts to predict the amplitude of the solar cycle have resulted in diverging forecasts with no consensus. Yeates et al. have shown that the dynamical memory of the solar dynamo mechanism governs predictability, and this memory is different for advection- and diffusion-dominated solar convection zones. By utilizing stochastically forced, kinematic dynamo simulations, we demonstrate that the inclusion of downward turbulent pumping of magnetic flux reduces the memory of both advection- and diffusion-dominated solar dynamos to only one cycle; stronger pumping degrades this memory further. Thus, our results reconcile the diverging dynamo-model-based forecasts for the amplitude of solar cycle 24. We conclude that reliable predictions for the maximum of solar activity can be made only at the preceding minimum-allowing about five years of advance planning for space weather. For more accurate predictions, sequential data assimilation would be necessary in forecasting models to account for the Sun's short memory.

A Modified Sum-Product Algorithm over Graphs with Isolated Short Cycles

We investigate into the limitations of the sum-product algorithm in the probability domain over graphs with isolated short cycles. By considering the statistical dependency of messages passed in a cycle of length 4, we modify the update equations for the beliefs at the variable and check nodes. We highlight an approximate log domain algebra for the modified variable node update to ensure numerical stability. At higher signal-to-noise ratios (SNR), the performance of decoding over graphs with isolated short cycles using the modified algorithm is improved compared to the original message passing algorithm (MPA).

IFN-gamma inhibits growth of WISH cells in a cell cycle phase-specific manner

Treatment of WISH (human amnion) cells with interferon-gamma (IFN-gamma) inhibits their growth. Release of the cells from IFN-gamma-mediated growth inhibition led to a rapid and significant increase in DNA synthesis, followed by doubling of cell numbers. The DNA synthesis profile was strikingly similar to that shown by WISH cells released from growth arrest by the G(1)/S phase inhibitor, aphidicolin, This strongly suggested that IFN-gamma treatment leads to growth inhibition of WISH cells at the G(1)/S boundary of the cell cycle. In contrast, IFN-alpha blocked growth of these cells at the G(0)/G(1) boundary.

High temperature time-dependent low cycle fatigue behaviour of a type 316L(N) stainless steel

Total strain controlled low cycle fatigue tests on 316L(N) stainless steel have been conducted in air at various strain rates in the temperature range of 773-873 K to identify the operative time-dependent mechanisms and to understand their influence on the cyclic deformation and fracture behaviour of the alloy. The cyclic stress response at all the testing conditions was marked by an initial hardening followed by stress saturation. A negative strain rate stress response is observed under specific testing conditions which is attributed to dynamic strain ageing (DSA). Transmission electron microscopy studies reveal that there is an increase in the dislocation density and enhanced slip planarity in the DSA regime. Fatigue life is found to decrease with a decrease in strain rate. The degradation in fatigue resistance is attributed to the detrimental effects associated with DSA and oxidation. Quantitative measurement of secondary cracks indicate that both transgranular and intergranular cracking are accelerated predominantly under conditions conducive to DSA.

Short-lived triplets of aliphatic thioketenes

The photophysical behavior of the triplets of three aliphatic thioketenes, namely di-tert-butylthioketene (1), 2,6-di-tert-butylcyclohexylthioketene (2) and 2,2,6,6-tetramethylcyclohexylthioketene, has been studied in fluid solutions at room temperature by nanosecond laser flash photolysis. Upon 532 nm laser excitation into the S1 state, the thioketenes in concentrated benzene solutions produce very short-lived transient absorptions (τ < 5 ns; λmax ≈ 450 nm) attributable to their triplets. The photogeneration of the latter under S1 excitation has also been established by energy transfer to all-trans-1,6-diphenyl-1,3,5-hexatriene. The factors which render the triplet lifetimes short are shown to be intrinsic in origin (rather than self-quenching). Unlike thiocarbonyl compounds in general, the thioketenes posses low intersystem crossing yields (less than 0.1 in benzene). From the kinetics of the quenching of a series of sensitizer triplets by 1 and 2, the thioketene triplet energies are estimated to be 43 – 44 kcal mol−1.

On the short-range order in Al-Mn quasicrystals during low-temperature ageing

We report the evolution of diffuse intensity during the low-temperature ageing of Al-Mn quasicrystals. This is taken as evidence of short-range order in the icosahedral phase prior to its decomposition. The implication of these diffuse intensities is discussed.

Dependence of low-lying energy eigenvalues on the short- and long-range parts of confining potentials

The potential description of a quark-antiquark system seems to work very well in describing a number of hadronic properties. However, the precise form of the potential is unknown. The changes in the low-lying eigenvalues as a result of changes in the long-range part of the potential are investigated in a non-perturbative manner. It is shown by considering a variety of examples that the low-lying eigenvalues are insensitive to the long-range part of the potential.

Spool valve mechanism used in a 20 K Gifford-McMahon cycle cryorefrigerator and its effect on the P-V diagram

The design and fabrication of a spool valve for a two-stage Gifford-McMahon cycle cryorefrigerator is described. The effect of this valve on the P-V diagram and practical methods of reducing the P-V degradation are also discussed.

A low cost demagnetizer with controllable cycle and adjustable level

Demagnetization to zero remanent value or to a predetermined value is of interest to magnet manufacturers and material users. Conventional methods of demagnetization using a varying alternating demagnetizing field, under a damped oscillatory or conveyor system, result in either high cost for demagnetization or large power dissipation. A simple technique using thyristors is presented for demagnetizing the material. Power consumption is mainly in the first two half-cycles of applied voltage. Hence power dissipation is very much reduced. An optimum value calculation for a thyristor triggering angle for demagnetizing high coercive materials is also presented.