Compilers: principles, techniques, and tools
Compilers: principles, techniques, and tools
Static scheduling of synchronous data flow programs for digital signal processing
IEEE Transactions on Computers
Computer architecture: a quantitative approach
Computer architecture: a quantitative approach
The Marion system for retargetable instruction scheduling
PLDI '91 Proceedings of the ACM SIGPLAN 1991 conference on Programming language design and implementation
Communications of the ACM
IEEE Spectrum
Complete Computer System Simulation: The SimOS Approach
IEEE Parallel & Distributed Technology: Systems & Technology
Retargetable estimation scheme for DSP architecture selection
ASP-DAC '00 Proceedings of the 2000 Asia and South Pacific Design Automation Conference
A Methodology to Design Programmable Embedded Systems - The Y-Chart Approach
Embedded Processor Design Challenges: Systems, Architectures, Modeling, and Simulation - SAMOS
A methodology to design programmble embedded systems: the Y-chart approach
Embedded processor design challenges
An Approach for Quantitative Analysis of Application-Specific Dataflow Architectures
ASAP '97 Proceedings of the IEEE International Conference on Application-Specific Systems, Architectures and Processors
Optimistic coalescing for heterogeneous register architectures
Proceedings of the 2007 ACM SIGPLAN/SIGBED conference on Languages, compilers, and tools for embedded systems
Register coalescing techniques for heterogeneous register architecture with copy sifting
ACM Transactions on Embedded Computing Systems (TECS)
Minimizing accumulative memory load cost on multi-core DSPs with multi-level memory
Journal of Systems Architecture: the EUROMICRO Journal
Hi-index | 0.00 |
In the paper the problem of processor/compiler codesign for digital signal processing and embedded systems is discussed. The main principle we follow is the top-down approach characterized by extensive simulation and quantitative performance evaluation of processor and compiler. Although well established in the design of state-of-the-art general purpose processors and compilers, this approach is rarely followed by leading producers of signal and embedded processors. As a consequence, the matching between the processor and the compiler is low. In the paper we focus on three main components of our exploration environment-benchmarking methodology (DSPstone), fast processor simulation (SuperSim), and machine description (LISA). Most of the paper is devoted to the technique of compiled processor simulation. The speedup obtained allows an exploration of a much larger design space than it was possible with standard processor simulators.