Dynamic voltage and frequency scaling framework for low-power embedded GPUs

Graphics processor (GPU) architectures have evolved rapidly in recent years with increasing performance demanded by 3D graphics applications such as games. However, challenges exist in integrating complex GPUs into mobile devices because of power and energy constraints, motivating the need for energy efficiency in GPUs. While a significant amount of power optimisation research effort has concentrated on the CPU system, GPU power efficiency is a relatively new and important area because the power consumed by GPUs is similar in magnitude to CPU power. Power and energy efficiency can be introduced into GPUs at many different levels: 1) Hardware component level - queue structures, caches, filter arithmetic units, interconnection networks, processor cores, etc., can be optimised for power. 2) Algorithm level - the deep and complex graphics processing computation pipeline can be modified to be energy aware. Shader programs written by the user can be transformed to be energy aware. 3) System level - co-ordination at the level of task allocation, voltage and frequency scaling, etc., requires knowledge and control of several different GPU system components We outline two strategies for applying energy optimisations at different levels of granularity in a GPU: (1) Texture Filter Memory (TFM) - an energy-efficient addition to the texture memory hierarchy component; and (2) an overall system level Dynamic Voltage and Frequency Scaling (DVFS) based energy reduction strategy based on an accurate tile-level slack prediction. Texture Filter Memory is an augmentation of the standard GPU texture cache hierarchy. Instead of a regular data cache hierarchy, we employ a small first level register based structure that is optimised for the relatively predictable memory access stream in the texture filtering computation. Predictability of the memory access patterns leads us to reduce power by using a simpler register access structure. Power is saved by avoiding the expensive tag lookup and comparisons present in regular caches. Further, the texture filter memory is a very small structure, whose access energy is much smaller than a data cache of similar performance. Dynamic Voltage and Frequency Scaling, an established energy management technique, can be applied in GPUs by first predicting the workload in a given frame, and, where sufficient slack exists, lowering the voltage and frequency levels so as to save energy while still completing the work within the frame rendering deadline. We apply DVFS in a tiled graphics renderer, where the workload prediction and voltage/frequency adjustment is performed at a tile-level of granularity, which creates opportunities for on-the-fly correction of prediction inaccuracies, ensuring high frame rates while still delivering low power. Tile-level energy management schemes are distinctly superior to schemes that work at the granularity of the entire frame in terms of energy saving and quality of the rendering measured in terms of frames rendered per second. The prediction mechanism relies both on the history - workload observed for the tile in recent frames, as well as rank - a quantification of the tile workload based on the frame structure, consisting of geometry, pixel shading, texture, and raster operations workloads.

Dynamic Voltage and Frequency Scaling (DVFS) approach is proposed to control the power consumption in devices of different types like from a small mobile device to a huge server. This paper aims to study the effect of parallel execution of two benchmark applications, one the Stanford Single Source benchmarks (lightweight parallel code) and, Stanford Parallel Applications for Shared Memory (SPLASH-2) programs (heavy real-time data streaming parallel applications that run on multi -core clusters) on DVFS for dark silicon ameliorating. Both these benchmarks executed on a gem5 Full System simulator, booting a linaro based linux kernel. To get a holistic big picture of the power and thermal properties of systems that run on DVFS, in addition to the control feature present in gem 5, a power-estimation framework used for the evaluation of the efficiency of various DVFS policies, the MCPAT and Hotspot is also employed. Based on the execution of Stanford workloads DVFS model is analyzed in terms of memory footprint and on other critical processor performance metrics, like running time per core, bus latency, number of read, writes, access time, cache hit or miss. The gem5 is extended with full DVFS support by the addition of a framework in which easy power-model integration can be done.

Dynamic Voltage and Frequency Scaling (DVFS) is widely used in today's mobile devices. Commonly adopted OS level DVFS policies usually operate with high sampling and adjustment frequency in order to compensate for the lack of information from applications. In this paper, we consider the application of video decoding and propose a method that enables DVFS at a coarse time granularity by taking advantage of application level semantics. Using machine learning, we build a prediction model for the choice of CPU frequency based on the estimated workload and the progress of execution. We show that with our method, the system is able to perform DVFS with a frequency of only around 1 Hz, abiding by the practical constraints imposed by existing operating systems, but still saves an average of 40.1% in energy consumption compared with the execution at nominal speed. Further, we argue that the law of diminishing returns applies if we increase the frequency at which DVFS operates, and thus it may be costly and impractical to perform application level DVFS at a very fine time granularity.

The surge in demand for energy-efficient computing has spurred the exploration of cutting-edge techniques to optimize power consumption in modern computing systems. Though the traditional implementation of Dynamic Voltage and Frequency Scaling (DVFS) has proven effective, their traditional implementations lack adaptability, limiting their ability to fully exploit dynamic workload variations. This research presents an innovative solution by integrating proposed Reinforcement Learning (RL) algorithms into DVFS, addressing the limitations of conventional methods. The proposed RL algorithm employs Q-Iearning, a model-free RL technique, to iteratively learn the optimal policy for adjusting CPU voltage and frequency. Our customized algorithm enables autonomous real-time adjustments of voltage and frequency levels, showcasing a remarkable 20% power saving compared to conventional DVFS. The model's adaptability is evident in its capacity to achieve optimal configurations across diverse workloads, emphasizing RL's potential for enhancing energy efficiency in computing systems. As energy efficiency gains paramount importance, this research underscores the pivotal role of RL, in achieving sustainable and optimal performance in computing systems.

In designing information communication devices such as real-time embedded systems, it is quite important to maximize the system performance under some hard energy constraints. As a useful technology to reduce the energy consumption in computer-based systems, the dynamic voltage and frequency scaling (DVFS) is becoming very popular. In this paper, we consider an optimal DVFS allocation problem by maximizing the system reliability subject to the hard real-time and energy constraints. More specifically, we formulate a reliability maximization problem when the task processing is probabilistic and is described by a discrete-time Markov chain. Two approximate formulas are proposed to calculate the system reliability efficiently. We perform the sensitivity analysis of model parameters in numerical examples, and also give a case study to design a Wi-Fi subsystem in terms of the DVFS allocation.

The functionality of embedded systems is ever growing. The computational power of embedded systems is growing to match this demand, with embedded multiprocessor systems becoming more common. The limitations of embedded systems are not always related to chip size but are commonly due to energy and/or power constraints. While it can be possible to embed a more powerful Multiprocessor System on Chip (MPSoC), it is not always possible to provide an energy or power supply that meets its demands within the device’s size and weight requirements. Power management through Dynamic Voltage and Frequency Scaling (DVFS) enables the device to be run at less than its maximum voltage and frequency, allowing high computational capability when necessary while conserving power at other times. Embedded systems commonly perform real-time functionality. A real-time application has an associated formal model to verify that it meets its timing requirements. This formal model is used to perform a worst-case timing analysis to ensure that the application meets its requirements. These models incorporate the worst-case timing of the application’s computation and communication. Timing changes due to power management must also be taken into account, complicating the verification process. The drive for evermore functionality has led to mixed time-criticality systems, in which multiple applications of various timing criticalities share the same (hardware) resources. This complicates the verification process further as the timing interference due to shared resource contention must be taken into account. A monolithic verification effort is therefore traditionally required after system integration and must be carried out again if any modifications are made that affect the timing of any of the applications. The problem that we aim to solve in this work is to enable real-time applications to perform independent execution and power management without violating their timing requirements or invalidating the timing verification of concurrently executing applications. To solve this problem, we contribute the Composable and Predictable Microkernel (CoMik) to composably and predictably virtualise processors. When used in combination with composable and predictable memory controllers and interconnect (as provided by the Composable and Predictable System-on-Chip (CompSOC) platform), these virtual processors cannot interfere with each other’s timing by even a single cycle. If whatever executes on the virtual processors (e.g. an Operating System (OS) or an application directly) has a real-time requirement, it can be verified independently of whatever executes on the concurrent virtual processors and other virtual resources. To enable formally analysable application execution, we contribute the Predictable Operating System (POSe) that enables dataflow applications to be executed on the (virtualised) processor. We contribute a combined application and platform dataflow graph, including an algorithm to automate this process. When annotated with worst-case timings, the combined application and system graph is then used to verify that the application meets its timing requirement. If the application’s performance is better than its requirement (e.g. when the input or platform behaviour are better than worst case), its performance can be reduced using DVFS to achieve a reduction in power consumption. We contribute an off-line convex optimisation that uses the combined application and platform dataflow model to derive static run-time operating frequency levels to achieve low power consumption. The off-line technique is able to exploit static slack in the schedule, but not dynamic run-time slack due to variations in task execution times. Before dynamic slack can be used it must be possible to observe it. For this purpose, CoMik provides independent power, energy and timing accounting per virtual processor. This enables each virtual processor to be assigned individual power and energy budgets and POSe applications to be assigned timing budgets. We contribute a description and model of how energy and power budgets can be distributed between multiple virtual processors, enabling whatever executes on the virtual processor to perform composable independent power-management without affecting the ability of other virtual processors from using their entire budget allocation. Using CoMik’s accounting infrastructure, we also demonstrate how the quality of applications can be dynamically scaled to assist meeting timing, energy or power requirements. We further contribute a distributed dynamic power management policy that enables dataflow applications that are mapped onto multiple (virtual) processors to make distributed dynamic slack observations and local power-management decisions. We demonstrate the applicability of the presented techniques on an implemented Field Programmable Gate Array (FPGA) prototype of a CompSOC hardware platform instance, using an H.263 decoder as a case-study application. We show that our techniques do not only work in theory, but that they are also implementable and implemented.

With growing integration, power consumption is becoming a major issue for multi-core chips. At system level, per-core Dynamic Voltage and Frequency scaling (DVFS) is expected to save substantial energy provided an adapted control. In this paper we propose a local on-line optimization technique to reduce energy in data-flow architecture, thanks to a Local Power Manager (LPM) using Vdd-Hopping for efficient local DVFS. The proposed control is a hybrid global and local scheme which respects throughput and latency constraints. The approach has been fully validated on a real Multiple Input Multiple Output (MIMO) Telecom application using a SystemC platform instrumented with power estimates. Local DVFS brings 45% power reduction compared to idle mode. When local on-line optimization benefit from computation time variations, 30% extra energy savings can be achieved.

Dynamic voltage and frequency scaling (DVFS) is a means to adjust the computing capacity and power consumption of computing systems to the application demands. DVFS is generally useful to provide a compromise between computing demands and power consumption, especially in the areas of resource-constrained computing systems. Many modern processors support some form of DVFS. In this article, we focus on the development of an execution framework that provides lightweight DVFS support for reactive stream processing systems (RSPS). RSPs are a common form of embedded control systems, operating in direct response to inputs from their environment. At the execution framework, we focus on support for many-core scheduling for parallel execution of concurrent programs. We provide a DVFS strategy for RSPs that is simple and lightweight, to be used for dynamic adaptation of the power consumption at runtime. The simplicity of the DVFS strategy became possible by the sole focus on the application domain of RSPs. The presented DVFS strategy does not require specific assumptions about the message arrival rate or the underlying scheduling method. While DVFS is a very active field, in contrast to most existing research, our approach works also for platforms like many-core processors, where the power settings typically cannot be controlled individually for each computational unit. We also support dynamic scheduling with variable workload. While many research results are provided with simulators, in our approach, we present a parallel execution framework with experiments conducted on real hardware, using the single-chip cloud computer many-core processor. The results of our experimental evaluation confirm that our simple DVFS strategy provides potential for significant energy saving on RSPs.

Parallel structures may be used to increase a system processing speed in case of large amount of data or highly complex calculations. Dynamic Voltage and Frequency Scaling (DVFS) may be used for simpler calculations in order to decrease the system voltage or frequency and achieve lower power consumption. Combining these two mechanisms may lead to higher efficiency and lower power consumption. In this paper, we introduce a parallel decoding process with Digital Signal Processing (DSP) for power efficiency in a heterogeneous multi-core embedded system. We describe a parallel low-power design on the system level. Under the condition of preserving the original decoding process, we manage the size of the system's multimedia buffer by considering the spontaneous streaming transfer and tuning the decoding process scheduling time by using the DVFS system in order to decrease the multimedia data dependency and achieve a multi-core embedded system with accurate and low-power detection mechanism.

The power consumption has become a critical issue since the multi-core chip has been used widely in embedded systems. The battery life is determined by the amount of power consumption and there are design challenges for low power and high performance microprocessors. To achieve our objective, we first distribute a workload uniformly and then apply dynamic voltage and frequency scaling (DVFS) to reduce power consumption dynamically. According to workload of the multi-threaded application, we can adjust the number of core to execute before we run the application. Besides, our approach can reassign workload to alive cores if some cores crash. For this case, if a core breaks down at run time, the power management unit will send a trap to OS, then pthread scheduler will dynamically reassign the workload to alive cores. To evaluate the proposed approach, we perform experiments for our own multicore. The result shows that our approach can work well for various cases.

Dynamic voltage and frequency scaling (DVFS) is heavily used for power management in real-time environments. Although the schemes leveraging DVFS provide significant power reduction, adverse effects on chip reliability are possible. Alternate increase and decrease in operating voltage and frequency leads to thermal cycling. Increasing transistor packing density leads to a larger range of possible operating temperatures, exacerbating the thermal cycling problem. Also, the chip reliability quantification process does not include and represent the effects of small scale thermal cycles. A good number of in-field chip failures are attributed to the consequences of these. Thus, it is imperative to include their effects into the processor voltage and frequency selection process. Our work develops an integrated processor thermal and performance management technique centered on novel polynomial time scheduling algorithms that lead to lowering of thermal cycles in soft real time environments. Our technique leverages application awareness and runtime monitoring for improving chip lifetime, while achieving considerable energy savings. We show that a significant reduction in thermal cycles and peaks is possible, leading to longer chip life expectations.

This paper presents a system level dynamic voltage and frequency scaling (DVFS) technique targeted toward non realtime applications running on a portable embedded system with multiple frequency-adjustable components. The key idea is to balance the frequency of processor core and memory. Some applications may be I/O bound, some may be CPU bound, and the others may be Memory bound. The proposed DVFS technique relies on pre-collected statistical information of different applications to calculate the expected workload for each coming time slice, and then, it adjusts the frequency of processor core, memory, and system bus to meet the timing constraints(with acceptable penalty) and achieves the maximum energy saving. The proposed technique has been tested on the PXA27x (XScale based) [8] embedded platform and the result was exciting, the processor energy saving can achieve up to 70% in memory bound applications, and the timing performance degradation was less than 5%. In CPU bound applications, the energy saving is relatively small, about 20~40%.

The use of power management techniques is mandatory in embedded devices, which must provide high performance with low energy consumption. Due to the high variability present in the applications workload executed by these devices, this management should be executed dynamically. The use of traditional dynamic voltage and frequency scaling (DVFS) techniques proved to be useful in several scenarios to save energy. Nonetheless, due to technology scaling that limits the voltage variation and slow response of the DVFS schemes, the use of such technique may become inadequate. As alternative, the use of dynamic frequency scaling (DFS) may provide a good trade-off between power savings and power overhead. This paper proposes a distributed DFS scheme for NoC-based MPSoCs. Both NoC and PEs have an individual controlling scheme. The DFS scheme for PEs takes into account its computation and communication load to dynamically change the operating frequency. In the NoC, the DFS controller uses packet information to decide the router operating frequency. Real and synthetic applications were used to evaluate the proposed scheme. Results show that the number of executed instructions is reduced up to 41%, with an execution time overhead up to 18%. The power dissipation is reduced in PEs up to 26% and in the NoC up to 76%.

As the popularity of graphics processing units (GPUs) grows rapidly in recent years, it becomes very critical to study and understand the security implications imposed by them. In this paper, we show that modern GPUs can “broadcast” sensitive information over the air to make a number of attacks practical. Specifically, we present a new electromagnetic (EM) side-channel vulnerability that we have discovered in many GPUs of both NVIDIA and AMD. We show that this vulnerability can be exploited to mount realistic attacks through two case studies, which are website fingerprinting and keystroke timing inference attacks. Our investigation recognizes the commonly used dynamic voltage and frequency scaling (DVFS) feature in GPU as the root cause of this vulnerability. Nevertheless, we also show that simply disabling DVFS may not be an effective countermeasure since it will introduce another highly exploitable EM side-channel vulnerability. To the best of our knowledge, this is the first work that studies realistic physical side-channel attacks on non-shared GPUs at a distance.

Contemporary mobile platforms employ embedded graphic processing units (GPUs) for graphics-intensive games, and dynamic voltage and frequency scaling (DVFS) policies are used to save energy without sacrificing quality. However, current GPU DVFS policies result in unnecessary power waste due to defective workload estimations of embedded GPUs during game play. In this paper, we propose the Frame-Complexity Model (FCM), a fine-grained estimation of the GPU workload in a game frame, to quantify the GPU workload with the real runtime demand for GPU computing resources of a game frame. In FCM, three constituents of a game frame (i.e., structure, textures and computation) are quantified without modification of mobile games. Preliminary experiments show that, compared with the default policy, the FCM-directed GPU DVFS policy can reduce more power consumption of games (11.3% to 25.8%) with good Quality of Service (QoS).