Voltage over-scaling:A cross-layer design perspective for energy efficient systems

Today's multi-media electronic era is driven by the increasing demand for small multifunctional devices able to support diverse services. Unfortunately, the high levels of transistor integration and performance required by such devices lead to an unprecedented increase of on-chip power that significantly limits the battery lifetime and even poses reliability concerns. Several techniques have been developed to address the power increase, but voltage over-scaling (VOS) is considered to be one of the most effective ones due to the quadratic dependence of voltage on dynamic power consumption. However, VOS may not always be applicable since it increases the delay in all paths of a system and may limit high performance required by today's complex applications. In addition, application of VOS is further complicated since it increases the variations in transistor characteristics imposed by their tiny size which can lead to large delay and leakage variations, making it difficult to meet delay and power budgets. This paper presents a review of various cross-layer design options that can provide solutions for dynamic voltage over-scaling and can potentially assist in meeting the strict power budgets and yield/quality requirements of future systems. © 2011 IEEE.

Performance and Fault Tolerance of Preconditioned Iterative Solvers on Low-Power ARM Architectures

As the complexity of computing systems grows, reliability and energy are two crucial challenges asking for holistic solutions. In this paper, we investigate the interplay among concurrency, power dissipation, energy consumption and voltage-frequency scaling for a key numerical kernel for the solution of sparse linear systems. Concretely, we leverage a task-parallel implementation of the Conjugate Gradient method, equipped with an state-of-the-art pre-conditioner embedded in the ILUPACK software, and target a low-power multi core processor from ARM.In addition, we perform a theoretical analysis on the impact of a technique like Near Threshold Voltage Computing (NTVC) from the points of view of increased hardware concurrency and error rate.

Strategies for Energy-Efficient Resource Management of Hybrid Programming Models

Many scientific applications are programmed using hybrid programming models that use both message passing and shared memory, due to the increasing prevalence of large-scale systems with multicore, multisocket nodes. Previous work has shown that energy efficiency can be improved using software-controlled execution schemes that consider both the programming model and the power-aware execution capabilities of the system. However, such approaches have focused on identifying optimal resource utilization for one programming model, either shared memory or message passing, in isolation. The potential solution space, thus the challenge, increases substantially when optimizing hybrid models since the possible resource configurations increase exponentially. Nonetheless, with the accelerating adoption of hybrid programming models, we increasingly need improved energy efficiency in hybrid parallel applications on large-scale systems. In this work, we present new software-controlled execution schemes that consider the effects of dynamic concurrency throttling (DCT) and dynamic voltage and frequency scaling (DVFS) in the context of hybrid programming models. Specifically, we present predictive models and novel algorithms based on statistical analysis that anticipate application power and time requirements under different concurrency and frequency configurations. We apply our models and methods to the NPB MZ benchmarks and selected applications from the ASC Sequoia codes. Overall, we achieve substantial energy savings (8.74 percent on average and up to 13.8 percent) with some performance gain (up to 7.5 percent) or negligible performance loss.

On the potential of significance-driven execution for energy-aware HPC

Dynamic Voltage and Frequency Scaling (DVFS) exhibits fundamental limitations as a method to reduce energy consumption in computing systems. In the HPC domain, where performance is of highest priority and codes are heavily optimized to minimize idle time, DVFS has limited opportunity to achieve substantial energy savings. This paper explores if operating processors Near the transistor Threshold Volt- age (NTV) is a better alternative to DVFS for break- ing the power wall in HPC. NTV presents challenges, since it compromises both performance and reliability to reduce power consumption. We present a first of its kind study of a significance-driven execution paradigm that selectively uses NTV and algorithmic error tolerance to reduce energy consumption in performance- constrained HPC environments. Using an iterative algorithm as a use case, we present an adaptive execution scheme that switches between near-threshold execution on many cores and above-threshold execution on one core, as the computational significance of iterations in the algorithm evolves over time. Using this scheme on state-of-the-art hardware, we demonstrate energy savings ranging between 35% to 67%, while compromising neither correctness nor performance.

TProf: An energy profiler for task-parallel programs

We present TProf, an energy profiling tool for OpenMP-like task-parallel programs. To compute the energy consumed by each task in a parallel application, TProf dynamically traces the parallel execution and uses a novel technique to estimate the per-task energy consumption. To achieve this estimation, TProf apportions the total processor energy among cores and overcomes the limitation of current works which would otherwise make parallel accounting impossible to achieve. We demonstrate the value of TProf by characterizing a set of task parallel programs, where we find that data locality, memory access patterns and task working sets are responsible for significant variance in energy consumption between seemingly homogeneous tasks. In addition, we identify opportunities for fine-grain energy optimization by applying per-task Dynamic Voltage and Frequency Scaling (DVFS).

Power-Capped DVFS and Thread Allocation with ANN Models on Modern NUMA Systems

Abstract—Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory
access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement
the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to
67.1%, under a power cap.

Power Modeling and Capping for Heterogeneous ARM/FPGA SoCs

Low-power processors and accelerators that were originally designed for the embedded systems market are emerging as building blocks for servers. Power capping has been actively explored as a technique to reduce the energy footprint of high-performance processors. The opportunities and limitations of power capping on the new low-power processor and accelerator ecosystem are less understood. This paper presents an efficient power capping and management infrastructure for heterogeneous SoCs based on hybrid ARM/FPGA designs. The infrastructure coordinates dynamic voltage and frequency scaling with task allocation on a customised Linux system for the Xilinx Zynq SoC. We present a compiler-assisted power model to guide voltage and frequency scaling, in conjunction with workload allocation between the ARM cores and the FPGA, under given power caps. The model achieves less than 5% estimation bias to mean power consumption. In an FFT case study, the proposed power capping schemes achieve on average 97.5% of the performance of the optimal execution and match the optimal execution in 87.5% of the cases, while always meeting power constraints.

A quality-scalable and energy-efficient approach for spectral analysis of heart rate variability

Today there is a growing interest in the integration of health monitoring applications in portable devices necessitating the development of methods that improve the energy efficiency of such systems. In this paper, we present a systematic approach that enables energy-quality trade-offs in spectral analysis systems for bio-signals, which are useful in monitoring various health conditions as those associated with the heart-rate. To enable such trade-offs, the processed signals are expressed initially in a basis in which significant components that carry most of the relevant information can be easily distinguished from the parts that influence the output to a lesser extent. Such a classification allows the pruning of operations associated with the less significant signal components leading to power savings with minor quality loss since only less useful parts are pruned under the given requirements. To exploit the attributes of the modified spectral analysis system, thresholding rules are determined and adopted at design- and run-time, allowing the static or dynamic pruning of less-useful operations based on the accuracy and energy requirements. The proposed algorithm is implemented on a typical sensor node simulator and results show up-to 82% energy savings when static pruning is combined with voltage and frequency scaling, compared to the conventional algorithm in which such trade-offs were not available. In addition, experiments with numerous cardiac samples of various patients show that such energy savings come with a 4.9% average accuracy loss, which does not affect the system detection capability of sinus-arrhythmia which was used as a test case. 

Energy Optimization of Memory Intensive Parallel Workloads

Energy consumption is an important concern in modern multicore processors. The energy consumed by a multicore processor during the execution of an application can be minimized by tuning the hardware state utilizing knobs such as frequency, voltage etc. The existing theoretical work on energy minimization using Global DVFS (Dynamic Voltage and Frequency Scaling), despite being thorough, ignores the time and the energy consumed by the CPU on memory accesses and the dynamic energy consumed by the idle cores. This article presents an analytical energy-performance model for parallel workloads that accounts for the time and the energy consumed by the CPU chip on memory accesses in addition to the time and energy consumed by the CPU on CPU instructions. In addition, the model we present also accounts for the dynamic energy consumed by the idle cores. The existing work on global DVFS for parallel workloads shows that using a single frequency for the entire duration of a parallel application is not energy optimal and that varying the frequency according to the changes in the parallelism of the workload can save energy. We present an analytical framework around our energy-performance model to predict the operating frequencies (that depend upon the amount of parallelism) for global DVFS that minimize the overall CPU energy consumption. We show how the optimal frequencies in our model differ from the optimal frequencies in a model that does not account for memory accesses. We further show how the memory intensity of an application affects the optimal frequencies.

Effect of Loading, Voltage Difference and Phase Angle on the Synchronisation of a Small Alternator

Synchronisation of small distributed generation, 30 kVA–2 MVA, employing salient-pole synchronous machines is normally performed within a narrow range of tolerances for voltage, frequency and phase angle. However, there are situations when the ability to synchronise with non-ideal conditions would be beneficial. Such applications include power system islanding and rapid generator start-up. The physical process and effect of out-of-phase synchronisation is investigated both through simulation and experimental tests on a salient-pole alternator. There are many factors that affect synchronisation, but particular attention is given to synchronisation angle, voltage difference and, as generators will be loaded during islanding, the load angle. The results suggest that it would be acceptable for the maximum synchronisation angle of distributed generation to exceed that of current practice. Interesting observations on the nature of out-of-phase synchronisation are made, including some specific to small salient-pole synchronous machines. Furthermore, recommendations are made for synchronisation under different system conditions.

System level DSP synthesis using voltage overscaling, unequal error protection & adaptive quality tuning

In this paper, we propose a system level design approach considering voltage over-scaling (VOS) that achieves error resiliency using unequal error protection of different computation elements, while incurring minor quality degradation. Depending on user specifications and severity of process variations/channel noise, the degree of VOS in each block of the system is adaptively tuned to ensure minimum system power while providing "just-the-right" amount of quality and robustness. This is achieved, by taking into consideration system level interactions and ensuring that under any change of operating conditions only the "lesscrucial" computations, that contribute less to block/system output quality, are affected. The design methodology applied to a DCT/IDCT system shows large power benefits (up to 69%) at reasonable image quality while tolerating errors induced by varying operating conditions (VOS, process variations, channel noise). Interestingly, the proposed IDCT scheme conceals channel noise at scaled voltages. ©2009 IEEE.

Significance Driven Computation: A Voltage-Scalable, Variation-Aware, Quality-Tuning Motion Estimator

In this paper we present a design methodology for algorithm/architecture co-design of a voltage-scalable, process variation aware motion estimator based on significance driven computation. The fundamental premise of our approach lies in the fact that all computations are not equally significant in shaping the output response of video systems. We use a statistical technique to intelligently identify these significant/not-so-significant computations at the algorithmic level and subsequently change the underlying architecture such that the significant computations are computed in an error free manner under voltage over-scaling. Furthermore, our design includes an adaptive quality compensation (AQC) block which "tunes" the algorithm and architecture depending on the magnitude of voltage over-scaling and severity of process variations. Simulation results show average power savings of similar to 33% for the proposed architecture when compared to conventional implementation in the 90 nm CMOS technology. The maximum output quality loss in terms of Peak Signal to Noise Ratio (PSNR) was similar to 1 dB without incurring any throughput penalty.

Logic and Memory Design Based on Unequal Error Protection for Voltage-scalable, Robust and Adaptive DSP Systems

In this paper, we propose a system level design approach considering voltage over-scaling (VOS) that achieves error resiliency using unequal error protection of different computation elements, while incurring minor quality degradation. Depending on user specifications and severity of process variations/channel noise, the degree of VOS in each block of the system is adaptively tuned to ensure minimum system power while providing "just-the-right" amount of quality and robustness. This is achieved, by taking into consideration block level interactions and ensuring that under any change of operating conditions, only the "less-crucial" computations, that contribute less to block/system output quality, are affected. The proposed approach applies unequal error protection to various blocks of a system-logic and memory-and spans multiple layers of design hierarchy-algorithm, architecture and circuit. The design methodology when applied to a multimedia subsystem shows large power benefits ( up to 69% improvement in power consumption) at reasonable image quality while tolerating errors introduced due to VOS, process variations, and channel noise.

Evaluating fault tolerance on asymmetric multicore systems-on-chip using iso-metrics

The end of Dennard scaling has promoted low power consumption into a firstorder concern for computing systems. However, conventional power conservation schemes such as voltage and frequency scaling are reaching their limits when used in performance-constrained environments. New technologies are required to break the power wall while sustaining performance on future processors. Low-power embedded processors and near-threshold voltage computing (NTVC) have been proposed as viable solutions to tackle the power wall in future computing systems. Unfortunately, these technologies may also compromise per-core performance and, in the case of NTVC, xreliability. These limitations would make them unsuitable for HPC systems and datacenters. In order to demonstrate that emerging low-power processing technologies can effectively replace conventional technologies, this study relies on ARM’s big.LITTLE processors as both an actual and emulation platform, and state-of-the-art implementations of the CG solver. For NTVC in particular, the paper describes how efficient algorithm-based fault tolerance schemes preserve the power and energy benefits of very low voltage operation.

Stability of 71 degrees stripe domains in epitaxial BiFeO3 films upon repeated electrical switching

The 71 degrees stripe domain patterns of epitaxial BiFeO3 thin films are frequently being explored to achieve new functional properties, dissimilar from the BiFeO3 bulk properties. We show that in-plane switching and out-of-plane switching of these domains behave very differently. In the in-plane configuration the domains are very stable, whereas in the out-of-plane configuration the domains change their size and patterns, depending on the applied switching voltage frequency.