We published an unclassified unlimited release (UUR) paper.
Abstract
Two decades of experience with massively parallel supercomputing has given insight into the problem domains where these architectures are cost effective. Likewise experience with database machines and more recently massively parallel database appliances has shown where these architectures are valuable. Combining both architectures to simultaneously solve problems has received much less attention. In this paper, we describe a motivating application for economic modeling that requires both HPC and database capabilities. Then we discuss hardware and software integration issues related to a direct integration of a Cray XT supercomputer and a Netezza database appliance.
Publications
- Europar13 Paper Ron Oldfield, George Davidson, Craig Ulmer, and Andrew Wilson. "Investigating the Integration of Supercomputers and Data-Warehouse Appliances", Euro-Par 2013: Parallel Processing Workshops. Euro-Par 2013. Lecture Notes in Computer Science, vol 8374.
I have an unclassified unlimited release (UUR) talk at Salishan about our recent Key/Value store work in HPC.
Presentations
2012-09-11 Tue
fpga clusters
A team I was on won an NNSA Defense Program Award of Excellence.
2011-02-01 Tue
fpga ml security net pub bestof
We published unclassified unlimited release (UUR) papers on detecting web attacks in FPGA network filters via Bloom filter arrays.
Publications
- JPDC Paper Craig Ulmer, Maya Gokhale, Brian Gallagher, Philip Top, and Tina Eliassi-Rad, "Massively Parallel Acceleration of a Document Similarity Classifier to Detect Web Attacks", Journal of Parallel and Distributed Computing, February 2011.
- RAW Paper Craig Ulmer and Maya Gokhale, "A Configurable-Hardware Document Similarity Classifier to Detect Web Attacks", Reconfigurable Architectures Workshop, April 2010.
Presentations
- RAW Slides Presentation given at the Reconfigurable Architecture Workshop.
- Seminar Slides Presentation given on an early version of the work
2010-01-07 Thu
io mesh pub
We published an unclassified unlimited release (UUR) paper and technical report comparing different storage-focused analytic platforms.
Abstract
As scientific computing users migrate to petaflop platforms that promise to generate multi-terabyte datasets, there is a growing need in the community to be able to embed sophisticated data analysis algorithms in the storage systems for the computing platforms. Data Warehouse Appliances (DWAs) are an attractive option for this work, due to their ability to process massive datasets efficiently. While DWAs have been proven effective in data mining and informatics applications, there are relatively few examples of how DWAs can be integrated into the scientific computing workflow. In this paper we present our experiences in adapting two mesh analysis algorithms to function on two different DWAs: a SQL-based Netezza database appliance and a Map/Reduce-based Hadoop cluster. The main contribution of this work is insight into the differences between the two platforms' programming environments. In addition, we present performance measurements for entry-level DWAs to help provide a first-order comparison of the hardware.
Publications
- HICS Paper Craig Ulmer, Greg Bayer, Yung Ryn Choe, and Diana Roe, "Exploring Data Warehouse Appliances for Mesh Analysis Applications", Hawaii International Conference on System Sciences 2010.
- SAND Report Craig Ulmer, Greg Bayer, Yung Ryn Choe, and Diana Roe, "Scientific Data Analysis on Data-Parallel Platforms", Sandia Report SAND2010-7471.
