Hello, A change in allocation has been requested: Requester: norris (Boyana Norris) Project: pflotran Title: PFLOTRAN Performance Analysis and Tuning Description: PFLOTRAN is a massively parallel code developed at LANL for the accurate prediction of multiscale subsurface processes. PFLOTRAN has many applications and guides safer industrial techniques; for example, it can help geoscientists determine how carbon dioxide flows through aquifers and deep geologic formations during carbon-capture and storage. PFLOTRAN's performance has been studied extensively on Intrepid and Jaguar (Cray XT/5), but no performance studies on Intel-based clusters have been performed. The efficiency of the code is a small fraction of the peak on both BG/P and Cray XT/5. In addition to analyzing the parallel performance of two test cases, we will investigate applying autotuning tools we are developing as part of PERI to improve the single-node performance, as well as try to reduce the impact of global synchronizations. Current: undetermined amount Justification: Each simulation requires approximately 2 TB of memory and takes 10 minutes to 30 minutes on a Cray XT/5 on up to 16K cores. Thus, the largest-scale runs will require approximately 1280 processor-hours. Some autotuning approaches require the empirical exploration of a potentially large parameter space, so hundreds or thousands of runs may be required. While some of those runs would involve smaller isolated benchmarks, we will have to perform a large number of full simulation runs. We believe that we'd require between 500 and 1000 runs, taking varying times, with worst case of approximately 1280 processor-hours. Therefore we request 640,000 processor/hours for the year. Requested: 110000 A specific reason has been given: In the first year of this project, I focused mainly on analyzing and improving the performance of the sequential portions of key computational kernels (matrix-vector product, triangular linear solution, and some of the chemistry computations). During the next year, I plan to look at the lack of scalability of some of the linear solvers and the parallel imbalance between the flow and transport stages. This needs to be approved and the final allocation amount decided upon. Thank You, The LCRC Accounts System