| Sumario: | The article discusses how using a high-level language to hardware-description-language compiler with the Jacobi and conjugate gradient methods can be used to aid reconfigurable supercomputing and produce at least a twofold speedup. The authors tested both the Jacobi and conjugate gradient (CG) methods in computers that combine general purpose processors with field-programmable gate arrays (FPGA) and those that run software only versions. They found that except for one instance, the FPGA-augmented version of CG and Jacobi outperformed the software. They believe because they used the same compiler, code and algorithm, run on the same platform, and use the same input sets, the comparisons show that the acceleration in processing speed is due to the FPGA.
|
|---|