• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.131-136
• /
• 2013

Multi-core processors can improve parallelism of application processes and thus can enhance the system throughput. Researchers have recently revealed that the processor affinity is an important factor to determine network I/O performance due to architectural characteristics of multi-core processors; thus, many researchers are trying to suggest a scheme to decide an optimal processor affinity. Existing schemes to dynamically decide the processor affinity are able to transparently adapt for system changes, such as modifications of application and upgrades of hardware, but these have limited access to characteristics of application behavior and run-time information that can be collected heuristically. Thus, these can provide only sub-optimal processor affinity. In this paper, we define meaningful system variables for determining optimal processor affinity and suggest a tool to gather such information. We show that the implemented tool can overcome limitations of existing schemes and can improve network bandwidth.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.3
• /
• pp.105-112
• /
• 1997

The performance of a shared memory multiprocessor system is very sensitive to process scheduling. w can enhance the performance of a whole system as well as of an individual process by taking the multiprocessor characteristics into account in the design of the process scheduler. In this paper, we proposed a general purpose scheduler for a shared memory multiprocessor, called the Two-Level Multi-Scan (TLMS) process scheduler, that considers the processor affinity loosely and decreases the interference among multiple processors greatly. The TLMS scheduler is composed of a local scheduler at each processor and a semi-global scheduler that balances the load among processors. In particular, the semi-global scheduler tries to minimize priority inversion, which is an important factor of the system performance. The TLMS scheduler also tries to reduce the number of resources to be shared and improves the processor utilization. to meet these requirements, th semi-global scheduler interacts with the operation of the local scheduler when a need arises, thus the name is loose processor-affinity. We also show that the proposed scheduling technique can be extended for other types of resources making it a general purpose resource management queue.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.309-319
• /
• 2000

The purpose of a parallel scheduling under a multiprocessor environment is to carry out the scheduling with the minimum synchronization overhead, and to perform load balance for a parallel application program. The processors calculate the chunk of iteration and are allocated to carry out the parallel iteration. At this time, it frequently accesses mutually exclusive global memory so that there are a lot of scheduling overhead and bottleneck imposed. And also, when the distribution of the parallel iteration in the allocated chunk to the processor is different, the different execution time of each chunk causes the load imbalance and badly affects the capability of the all scheduling. In the paper. we investigate the problems on the conventional algorithms in order to achieve the minimum scheduling overhead and load balance. we then present a new parallel loop scheduling algorithm, considering the locality of the data and processor affinity.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.968-972
• /
• 2009

The multi-core processors are being widely exploited by many high-end systems. With significant advances in processor architecture, the network band-width required on the high-end systems is increasing drastically. It is therefore highly desirable to manage multiple cores efficiently to achieve high network band-width with minimum resource requirements. Modern operating systems, however, still have significant design and optimization space to leverage the network performance over multi-core systems. In this paper, we suggest a novel networking process scheduling scheme, which decides the best processor affinity of networking processes based on the processor cache layout, communication intensiveness, and processor loads. The experimental results show that the scheduling scheme implemented in the Linux kernel can improve the network bandwidth and the effectiveness of processor utilization by 20% and 59%, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.65-67
• /
• 2013

The recent high-performance network equipment is required, and also require high network bandwidth utilization. It is a trend to develop increasingly using multi-core processors for high-performance network servers. Propose a method to improve the performance of the network sub-system, considering the characteristics of multi-core as a way to improve these high-performance and high network throughput. In this paper, we confirm through experiments on how to improve the communication performance, optimize performance and take full advantage of multi-core by Network communication process to improve the performance of the multi-core processor architecture, the process of concentration, the overhead for each core, based on network traffic according to the interrupt affinity in this process to determine the optimal core to give. The experiments were implemented in the Linux kernel, and experiments to improve the network throughput up to 30%, bringing reduces the Linux communication process to improve the performance of the processor overhead of up to 10%.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.124-131
• /
• 2017

The emerging next-generation manycore processors for high-performance computing are equipped with a high-bandwidth on-package memory along with the traditional host memory. The Multi-Channel DRAM (MCDRAM), for example, is the on-package memory of the Intel Xeon Phi Knights Landing (KNL) processor, and theoretically provides a four-times-higher bandwidth than the conventional DDR4 memory. In this paper, we suggest a mechanism to exploit MCDRAM for improving the performance of MPI intra-node communication. The experiment results show that the MPI intra-node communication performance can be improved by up to 272 % compared with the case where the DDR4 is utilized. Moreover, we analyze not only the performance impact of different MCDRAM-utilization mechanisms, but also that of core affinity for processes.

• 한국가시화정보학회:학술대회논문집
• /
• 2002.04a
• /
• pp.51-78
• /
• 2002

A number of research groups worldwide are studying electronic implants that can be mounted on retinal optic nerve/visual cortex to restore vision of patients suffering from retinal degeneration. The implants consist of a neural interface made of biocompatible materials, one or more integrated circuits for stimuli generation, a camera, an image processor, and a telemetric channel. The realization of these classes of neural prosthetic devices is largely due to the explosive development of micro- and nano-electronics technologies in the late $20^{th}$ century and biotechnologies more recently. Animal experiments showed promise and some human experiments are in progress to indicate that recognition of images can be obtained and improved over time. We, at NBS-ERC of SNU, have started our own retinal implant project in 2000. We have selected polyimide as the biomaterial for an epi-retinal stimulator. In-vitro and in-vivo biocompatibility studies have been performed on the electrode arrays. We have obtained good affinity to retinal pigment epithelial cells and no harmful effect. The implant also showed very good stability and safety in rabbit eye for 12 weeks. We have also demonstrated that through proper stimulation of inner retina, meaning vision can be obtained.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.8
• /
• pp.367-376
• /
• 2007

In this paper, we introduce an application-specific and adaptive power management technique for portable systems that support dynamic voltage scaling (DVS). We exploit both the idle time of multitasking systems running soft real-time tasks as well as memory- or CPU-bound code regions. Detailed power and execution time profiles guide an adaptive power manager (APM) that is linked to the operating system. A post-pass optimizer marks candidate regions for DVS by inserting calls to the APM. At runtime, the APM monitors the CPU's performance counters to dynamically determine the affinity of the each marked region. for each region, the APM computes the optimal voltage and frequency setting in terms of energy consumption and switches the CPU to that setting during the execution of the region. Idle time is exploited by monitoring system idle time and switching to the energy-wise most economical setting without prolonging execution. We show that our method is most effective for periodic workloads such as video or audio decoding. We have implemented our method in a multitasking operating system (Microsoft Windows CE) running on an Intel XScale-processor. We achieved up to 9% of total system power savings over the standard power management policy that puts the CPU in a low Power mode during idle periods.