Chih-Yuan Cheng

A multimedia storage system for on-demand playback

This paper presents the design of a multimedia storage system for on-demand playback. The design stresses effective utilization of disk bandwidth with minimal data buffer to minimize overall system costs. The design procedure is most distinctive in the following two aspects: it bases on a tight upper bound of the lumped disk seek time for the Scan disk scheduling algorithm to achieve effective utilization of the disk bandwidth; and it starts with a general two-level hierarchical disk array structure to derive the optimal configuration for specific requirements. >

Design of multimedia storage systems for on-demand playback

This paper presents a comprehensive procedure to design multimedia storage systems for on-demand playback. The design stresses effective utilization of disk bandwidth with minimal data buffer to minimize overall system costs. The design procedure is most distinctive in the following two aspects: it bases on a tight upper bound of the lumped disk seek time for the Scan disk scheduling algorithm to achieve effective utilization of disk bandwidth; it starts with a general two-level hierarchical disk array structure to derive the optimal configuration for specific requirements.<<ETX>>

Designing a fully interactive video-on-demand server with a novel data placement and retrieval scheme

The paper discusses the design of a video-on-demand server that supports fully interactive operations such as play, fast forward search, and fast backward search, with a novel data placement and retrieval scheme. The main distinctions of this scheme are that (1) it requires neither extra disk bandwidth nor extra memory to support fast forward and fast backward searches; (2) it is based on a general two-level disk array architecture that exploits both parallelism and concurrency offered by fine-grain and coarse-grain disk array structures. >

The M 2 hierarchical multiprocessor

Abstract This paper discusses the design and development of a bus-based hierarchical multiprocessor named M 2 . The primary design goal of the M 2 is to derive a multiprocessor architecture that features much higher degree of scalability than the shared-memory shared-bus architecture to meet the ever increasing processing power demanded by large database/knowledgebase computing and transaction processing. If compared with other hierarchical multiprocessors, the M 2 is distinctive in its memory configuration, which is aimed at avoiding severe inter-CPU interference due to page-swapping events. If compared with a group of multiprocessors connected by a local area network, the M 2 enjoys higher scalability due to higher bandwidth of the backplane bus.

Guaranteeing quality of service in interactive video-on-demand servers

One of the main challenges in disk system design for interactive VOD servers is how to achieve a good quality of service (QoS) guarantee. This paper proposes a queueing model for analyzing the I/O bandwidth required in order to achieve a certain level of QoS for a disk system design scheme that provides VCR emulation. The disk system design scheme employs a practice that requests no extra bandwidth to support interactive operations such as fast forward search and fast backward search. The proposed queueing model provides a complete analysis tool for pinning down the resource requirement issue and its validity is verified through simulation.

Disk and file system design for MPEG-2 video-on-demand servers

This paper proposes a disk and file system design scheme that achieves effective utilization of disk bandwidth for retrieving MPEG-2 programs in a video-on-demand server. The scheme is based on a general two-level disk array architecture that exploits both parallelism and concurrency offered by fine-grain and coarse-grain disk array structures. This paper also presents a design procedure to figure out the optimal disk system configuration for specific requirements.

Effective utilization of disk bandwidth for supporting interactive video-on-demand

This paper proposes a novel data retrieval scheme that achieves effective utilization of disk bandwidth for designing fully interactive video-on-demand systems. The main distinctions of the proposed data retrieval scheme are (1) it requires no extra disk bandwidth to support interactive features such as fast forward search and fast backward search; and (2) it is based on a data placement scheme that can effectively utilize disk bandwidth during normal-speed playback.

Disk system design for guaranteeing quality of service in interactive video-on-demand systems

This paper discusses disk system design that supports VCR-like interactive video-on-demand (VOD) with a good quality-of- service (QoS) guarantee. The guarantee of QoS is based on a practice that requires no higher data bandwidth to support a stream switching from the normal playback mode to a fast search mode while providing VCR-like visual feeling. The main issue studied in this paper is how to figure out the I/O bandwidth required in order to achieve a certain level of QoS. This paper presents a queueing model to tackle this problem and uses simulation to verify the validity of the queueing model. This paper also addresses the related implementation issues.

Design of a Video Storage System for Interactive Video-on-Demand

This paper discusses the design of a video-on-demand server that supports filly interactive operations such as play, fast forward search, and fast backward search, with a novel data placement and retrieval scheme. The main distinction of this scheme is that it is based on a general two-level disk array drchitecture that exploits both parallelism and concurrency offered by various levels of disk array structures. The proposed scheme requires no extra disk bandwidth to support interactive operations as many previously proposed schemes do. This nature, in turn, means more eflective utilimtion of disk bandwidth.

Conditional annulling for superscalar processors

This paper proposes an architectural feature for superscalar processors called conditional annulling. The conditional annulling mechanism achieves both the effects of conditional execution and speculative execution without incurring a significant increase of hardware complexity and cost. All effectiveness evaluation carried out in this paper shows the conditional annulling mechanism is effective in improving superscalar processor instruction scheduling.<<ETX>>