Idle CPUs may enter power-saving hardware sleeps by, for instance, lowering the operating voltage and flushing the caches. However, wakeup delays that reach one hundred μSecs or more are disrupting the operations of fast devices like solid-state disks and tightly integrated accelerators. On the other hand, maximal power savings on modern multicores are only realized through continuous, simultan...

This paper explores the system-level power-performance tradeoffs of dynamically varying CPU speed. Previous work in CPU speed-setting considered only the power of the CPU and only CPUs that vary supply voltage with frequency. This work takes a broader approach, considering total system power, battery capacity, and main memory bandwidth. The results, which are up to a factor of four less than id...

Over the past few years there has been an increasing focus on the development of features for resource management within the Linux kernel. The addition of the fair group scheduler has enabled the provisioning of proportional CPU time through the specification of group weights. Since the scheduler is inherently workconserving in nature, a task or a group can consume excess CPU share in an otherw...

In this paper we present a hybrid rendering approach that generates fast real time images of a scene by the GPU and then progressively improves quality by selective ray tracing. The GPU solution is used to guide the ray tracing towards error prone areas. We describe the interplay between these two passes for the generation of high quality hard and soft shadows, anti-aliasing, and reflections an...

This paper discusses the use of the CPU cache when the processor is being used to manipulate stream data, in particular isochronous media such as as video. The principal idea is to enable data to avoid main memory and ow directly into a portion of the cache. When used with a \cache aware" operating system this method is shown to provide a rich support environment for multimedia manipulation. Ex...

There are several CPU scheduling algorithms like FCFS, SRTN,RR , priority etc. Scheduling decision of these algorithms are based on parameters which are assumed to be crisp. However, in many circumstances these parameters are vague. The vagueness of these parameters suggests that scheduler should use fuzzy logic in scheduling the jobs. A fuzzy priority CPU scheduling algorithm has been proposed...

This paper addresses the question of CPU performance emulation, which allows experimenters to evaluate applications under a wide range of reproducible experimental conditions. Specifically, we propose Fracas, a CPU emulator that leverages the Linux Completely Fair Scheduler to achieve performance emulation of homogeneous or heterogeneous multi-core systems. Several benchmarks reproducing differ...

In this paper, we propose a way to distribute the video analytics workload into both the CPU and GPU, with a performance prediction model including characteristics of feature extraction from the video stream data. That is, we estimate the total execution time of a CPU-GPU hybrid computing system with the performance prediction model, and determine the optimal workload ratio and how to use the C...

Virtualization-based cloud computing platforms allow multiple virtual machines (VMs) running on the same physical machine. Efficient allocation of limited underlying resources has been a key issue. This paper presents an efficient CPU resources dynamic allocation scheme (CRDA). CRDA uses the allocated credits and consumed credits to diagnose the CPU resources requirements of VMs and dynamically...

Emerging data-intensive applications are creating non-uniform CPU and I/O workloads which impose the requirement to consider both CPU and I/O effects in the power management strategies. Current approaches focus on scaling down the CPU frequency based on CPU busy/idle ratio without taking I/O into consideration. Therefore, they do not fully exploit the opportunities in power conservation. In thi...