Title | ||
---|---|---|
Performance estimation framework for automated exploration of CPU-accelerator architectures |
Abstract | ||
---|---|---|
In this paper we present a fast and fully automated approach for studying the design space when interfacing reconfigurable accelerators with a CPU. Our challenge is, that a reasonable evaluation of architecture parameters requires a hardware/software partitioning that makes best use of each given architecture configuration. Therefore we developed a framework based on the LLVM infrastructure that performs this partitioning with high-level estimation of the runtime on the target architecture utilizing profiling information and code analysis. By making use of program characteristics also during the partitioning process, we improve previous results for various benchmarks and especially for growing interface latencies between CPU and accelerator. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1145/1950413.1950448 | FPGA |
Keywords | Field | DocType |
architecture parameter,design space,code analysis,automated exploration,llvm infrastructure,partitioning process,target architecture,best use,architecture configuration,performance estimation framework,cpu-accelerator architecture,software partitioning,automated approach | Static program analysis,Computer science,Profiling (computer programming),Performance estimation,Interfacing,Real-time computing,Software,Design space,Architecture,Computer architecture,Parallel computing,Design space exploration,Embedded system | Conference |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tobias Kenter | 1 | 13 | 6.07 |
Christian Plessl | 2 | 297 | 35.98 |
Marco Platzner | 3 | 1188 | 116.17 |
Michael Kauschke | 4 | 27 | 1.74 |