A: Innovative claims

• Development of novel technology (Application Emulators/HLAM/PetaSIM) to support rapid prototyping of new computer architectures and new system software. This process will make it possible to provide reasonable estimates of the performance that will result from running realistic applications on future very high end architectures, such as those contemplated in the PetaFlop initiative. In order to support the need for rapid prototyping, the process will be robust and relatively fast.

• Development of application emulators that will be used to predict how targeted classes of leading edge applications will perform on very high end architectures. Application emulators will be produced for two large and crucial application classes: 1) adaptive irregular computational science and engineering applications and 2) applications that carry out data analysis, data exploration and data fusion.
• Development and formal specification of Hierarchical High Level Application Modeling Framework (HLAM). The HLAM will include mechanisms to allow users to provide: a) hierarchical description of applications, b) high level specification of a target machine, c) procedures to define how the hierarchical application description is mapped to the machine model and d) cost model to be used in performance estimation.
• Development of a simulation framework (PetaSIM) to generate performance predictions for application emulators using information provided by the high level application modeling framework HLAM. Will include support for the generation and use of data parallel aggregates as building blocks for specifying modules. PetaSIM will achieve high performance even on large applications by using event driven simulations for the coarse grain task parallel parts of an application, and by exploiting the loosely synchronous structure of SPMD data parallel components. Parallel implementation of PetaSIM will make use of optimizations pioneered by the PIs under previous DARPA contracts.
• Detailed simulation tools will be used to define the cost model for HLAM (especially in I/O area) and to selectively validate the results of PetaSIM.
• The HLAM machine description will be a basis for future extensions to current parallel programming environments, such as HPF and MPI, which currently embody a simple two level (on-processor and off-processor) view of memory.
• The development of HLAM and PetaSIM performance prediction technologies will, in future work, make it possible to develop standardized and highly efficient computational steering systems.
• Technology transfer to several HPCC communities, including commercial and academic designers of new machines and software, the PetaFlop initiative and the large HPCC education and training enterprise, who will be able to use the pedagogical value of our high level descriptions. A General Dynamics/Raytheon/SAIC team will use project technology in developing the new ship design code LAMP.