• JSTS:Journal of Semiconductor Technology and Science
• /
• v.9 no.2
• /
• pp.80-84
• /
• 2009

Dynamic voltage and frequency scaling (DVFS) is an effective method to achieve low power design. In our work, we present an analytical DVFS method which judiciously exploits correlation information in runtime distribution while satisfying deadline constraints. The proposed method overcomes the previous distribution-aware DVFS method [2] which has pessimistic assumption on which runtime distributions are independent. Experimental results show the correlation-aware DVFS offers 13.3% energy reduction compared to existing distribution-aware DVFS [2].

• Journal of information and communication convergence engineering
• /
• v.18 no.4
• /
• pp.222-229
• /
• 2020

Recent multi-core processors for smart devices use per-core dynamic voltage and frequency scaling (DVFS) that enables independent voltage and frequency control of cores. However, because the conventional task scheduler was originally designed for per-core DVFS disabled processors, it cannot effectively utilize the per-core DVFS and simply allocates tasks evenly across all cores to core utilization with the same CPU frequency. Hence, we propose a novel task scheduler to effectively utilize percore DVFS, which enables each core to have the appropriate frequency, thereby improving performance and decreasing energy consumption. The proposed scheduler classifies applications into two types, based on performance-sensitivity and allows a performance-sensitive application to have a dedicated core, which maximizes core utilization. The experimental evaluations with a real off-the-shelf smart device showed that the proposed task scheduler reduced 13.6% of CPU energy (up to 28.3%) and 3.4% of execution time (up to 24.5%) on average, as compared to the conventional task scheduler.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.512-515
• /
• 2009

A 90-nm CMOS motion estimation (ME) processor was developed by employing dynamic voltage and frequency scaling (DVFS) to greatly reduce the dynamic power. To make full use of the advantages of DVFS, a fast ME algorithm and a small on-chip DC/DC converter were also developed. The fast ME algorithm can adaptively predict the optimum supply voltage ($V_D$) and the optimum clock frequency ($f_c$) before each block matching process starts. Power dissipation of the ME processor, which contained an absolute difference accumulator as well as the on-chip DC/DC converter and DVFS controller, was reduced to $31.5{\mu}W$, which was only 2.8% that of a conventional ME processor.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.849-858
• /
• 2022

Dynamic voltage frequency scaling (DVFS) has been widely adopted for runtime power management of various processing units. In the case of neural processing units (NPUs), power management of neural network applications is required to adjust the frequency and voltage every layer to consider the power behavior and performance of each layer. Unfortunately, DVFS is inappropriate for layer-wise run-time power management of NPUs due to the long latency of voltage scaling compared with each layer execution time. Because the frequency scaling is fast enough to keep up with each layer, we propose a layerwise dynamic frequency scaling (DFS) technique for an NPU. Our proposed DFS exploits the highest frequency under the power limit of an NPU for each layer. To determine the highest allowable frequency, we build a power model to predict the power consumption of an NPU based on a real measurement on the fabricated NPU. Our evaluation results show that our proposed DFS improves frame per second (FPS) by 33% and saves energy by 14% on average, compared with DVFS.

• KIISE Transactions on Computing Practices
• /
• v.20 no.9
• /
• pp.483-491
• /
• 2014

Contemporary computer systems exploits DVFS (Dynamic Voltage/Frequency Scaling) technology for balancing performance and power consumption. The efficiency of DVFS depends on how much performance we get for larger power consumption due to elevated CPU frequency. Especially for memory-bounded applications, higher CPU frequency often does not result in higher performance. In this paper, we present an upper bound of CPU frequency scaling based on memory accesses. It is observed that the performance gain due to higher CPU frequency is limited by memory accesses (last level cache misses) per instructions by experiments. Using the results, we present the CPU frequency upper bound with little performance gain. Experimental results show that for a memory-bounded application, applying the frequency upper bound enhances the energy efficiency of the application by above 30%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2401-2409
• /
• 2016

Android CPU governors exploit the DVFS (Dynamic Voltage Frequency Scaling) technique. The DVFS is a power management technique where the CPU operating frequency is decreased to allow a corresponding reduction in the CPU supply voltage. The power consumed by a CPU is approximately proportional to the square of the CPU supply voltage. Therefore, lower CPU operating frequency allows the CPU supply voltage to be lowered. This helps to reduce the CPU power consumption. However, lower CPU operating frequency increases a task's execution time. Such an increase in the task's execution time makes the task's response time longer and makes the task's deadline miss occur. This finally leads to degrading the quality of service provided by the task. In this paper, we evaluated the performance of Android CPU governors in terms of the power consumption, tasks's response time and deadline miss ratio.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.9B
• /
• pp.1082-1091
• /
• 2011

Power-reduction techniques based on DVFS(Dynamic Voltage and Frequency Scaling) are crucial for lengthening operating times of battery powered mobile systems. This paper proposes an optimal DVFS scheduling algorithm for decoders with memory size limitation on display buffer, which is realistic constraints not properly touched in the previous works. Furthermore, we mathematically prove that the proposed algorithm is optimal in the limited display buffer and limited clock frequency model, and also can be used for feasibility check. Simulation results show the proposed algorithm outperformed the previous heuristic algorithms by 7% in average, and the performance of all algorithms using display buffers saturates at about 10 frame size.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.854-857
• /
• 2015

As the number of devices integrated on system-on-chip(SoC) increases exponentially, energy reduction technology is essential. Dynamic Voltage and Frequency Scaling (DVFS) is a very effective technique for reducing power consumption. Since it requires complex voltage regulators and PLL circuits, DVFS tends to have significant overheads. In this paper, we propose a new voltage selection algorithm to minimize transition overhead for multiprocessor SoC (MPSoC). Simulation results show that proposed algorithm appears less energy consumption with transition overhead even though maintains performance.

• Journal of Information Processing Systems
• /
• v.5 no.4
• /
• pp.175-186
• /
• 2009

Power consumed by modern computer systems, particularly servers in data centers has almost reached an unacceptable level. However, their energy consumption is often not justifiable when their utilization is considered; that is, they tend to consume more energy than needed for their computing related jobs. Task scheduling in distributed computing systems (DCSs) can play a crucial role in increasing utilization; this will lead to the reduction in energy consumption. In this paper, we address the problem of scheduling precedence-constrained parallel applications in DCSs, and present two energy- conscious scheduling algorithms. Our scheduling algorithms adopt dynamic voltage and frequency scaling (DVFS) to minimize energy consumption. DVFS, as an efficient power management technology, has been increasingly integrated into many recent commodity processors. DVFS enables these processors to operate with different voltage supply levels at the expense of sacrificing clock frequencies. In the context of scheduling, this multiple voltage facility implies that there is a trade-off between the quality of schedules and energy consumption. Our algorithms effectively balance these two performance goals using a novel objective function and its variant, which take into account both goals; this claim is verified by the results obtained from our extensive comparative evaluation study.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.296-303
• /
• 2016

Mobile real-time systems with limited system resources and a limited power source need to fully utilize the system resources when the workload is heavy and reduce energy consumption when the workload is light. EDZL (Earliest Deadline until Zero Laxity), a multiprocessor real-time scheduling algorithm, can provide high system utilization, but little work has been done aimed at reducing its energy consumption. This paper tackles the problem of DVFS (Dynamic Voltage/Frequency Scaling) in EDZL scheduling. It proposes a technique to compute a uniform speed on full-chip DVFS platforms and individual speeds of tasks on per-core DVFS platforms. This technique, which is based on the EDZL schedulability test, is a simple but effective one for determining the speeds of tasks offline. We also show through simulation that the proposed technique is useful in reducing energy consumption.