• Publications
  • Influence
PIPE: a VLSI decoupled architecture
The architecture and its implementation ofAbsm~-PIPE (Parallel Instructions and Pipelined Execution) is a research vehicle for high performance VLSI architectures and organizations and makes extensive use of architectural queues.
Characteristics of production database workloads and the TPC benchmarks
This analysis suggests that the TPC benchmarks tend to exercise the following aspects of the system differently than the production workloads: concurrency control mechanism, workload-adaptive techniques, scheduling and resource allocation policies, and I/O optimizations for temporary and index files.
Using Segmented Right-Deep Trees for the Execution of Pipelined Hash Joins
This paper derives an analytical model for the execution of a pipeline segment, and develops heuristic schemes to determine the query execution plan based on a segmented right-deep tree so that the query can be efficiently executed.
I/O reference behavior of production database workloads and the TPC benchmarks—an analysis at the logical level
A comprehensive analysis of the logical I/O reference behavior of the peak productiondatabase workloads from ten of the world's largest corporations, focusing on how these workloads respond to different techniques for caching, prefetching, and write buffering.
The automatic improvement of locality in storage systems
It is demonstrated that ALIS considerably outperforms prior techniques, improving the average read performance by up to 50% for server workloads and by about 15% for personal computer workloads, and that the performance improvement persists as disk technology evolves.
A Symmetric Fragment and Replicate Algorithm for Distributed Joins
  • J. Stamos, H. Young
  • Computer Science
    IEEE Trans. Parallel Distributed Syst.
  • 1 December 1993
It is claimed that SFR improves the worst-case cost for a distributed join, but it will not displace specialized distributed join algorithms when the later are applicable.
A General Multidimensional Data Allocation Method for Multicomputer Database Systems
This paper introduces a new technique which is flexible, and performs well for general queries, which is proposed to address the problems of multidimensional data declustering in shared-nothing parallel database systems.
Multi-Join Optimization for Symmetric Multiprocessors
Experimental results show that, while dynamic programming produces the be& plans, simple heuristics often do nearly as well as dynamic programming, and the advantages of bushy execution trees over more restricted tree shapes are highlighted.
A Low Communication Sort Algorithm for a Parallel Database Machine
This work proposes a novel algorithm that exhibits complete parallelism during the sort, merge, and return-tohost phases, and decreases the amou@ of inter-processor communication compared to existing parallel sort algorithms.
Projecting the performance of decision support workloads on systems with smart storage (SmartSTOR)
A general smart storage (SmartSTOR) architecture in which a processing unit that is coupled to one or more disks can be used to perform off-loaded processing, and suggests that there is a definite performance advantage in using fewer but more powerful processors.