My research on database management addresses how to build efficient query processing engines on modern hardware systems. Efficiency can be measured along several dimensions, including query processing time, space needed to store the data, energy needed to complete a query processing task, and the (amortized) monetary cost for performing a query workload. I have examined conventional multicore CPUs, nontraditional processors such as GPUs, and have also addressed the question of how one might design hardware for the specific task of database query processing. Taking advantage of the many kinds of processor parallelism is key to high performance, as is staging data to appropriate levels of the memory hierarchy to ensure fast response times for the current working data. My research on computational biology has examined genomic data for patterns associated with long tandem repeat sequences. My recent findings include an over-representation of such long repeats within genes coding for autoantigens in autoimmune disease. I continue to pursue hypotheses to explain autoimmunity.

Awards and Achievements

  • NSF Young Investigator Award ( 1994)