ALgorithm parallelization for Multicore Architectures Faster time-to-market for embedded multicore systems with less application development effort Application Test Case FEATURES IEEE 802.16e PHY Layer in NT x NR MIMO Configuration State-of-the-art WiMAX wireless communication Develop algorithms and tools to: Scilab Input Language ALMA subset of the Scilab language Extended by Variables declaration Static types specification Maximum size of vector/matrix data type definition Automatic parallelization of high-level Scilab algorithms to embedded MPSoCs Matrix Frontend (MFE) Hide hardware complexity from the software developer Translate Scilab intermediate representation Generates static C code optimized for parallelization Constant and data type propagation Iterative Optimization Provide target-agnostic parallelization tools Simulation and Performance Analysis of intermediate results Performance metric feedback-loop Iterative performance estimation and optimizations RESULTS Automatic conversion from Scilab to embedded C Code Automatic parallelization to 4 processing cores Minimization of sequential code Equal Workload distribution x2.4 application speedup ALMA www.alma-project.eu Coordinator Jürgen Becker (KIT) Contact [email protected] Budget 3.200.000 € Start Date 01/09/2011 Duration 41 Months Algorithm Parallelization Fine-grain parallelization Loop optimization Floating- to fixed Point conversion SIMD/SWP vectorization Coarse-grain parallelization Increases available CG parallelism Use hierarchical task graphs Parallel task mapping and scheduling Architecture Description Enables target independence of the toolchain Structural specification annotated with behavioural information Parallel Code Generation Map Scilab variables to memory locations Insert and optimize communication Generates target-specific MPI-like C code This work is co-funded by the European Union under the 7th Framework Programme under grant agreement ICT-287733.
© Copyright 2024