Supervised high-level synthesis (HLS) is a new class of design problems where exploration strategies play the role of supervisor for tuning an HLS engine. The complexity of the problem is increased due to the large set of tunable parameters exposed by the “new wave” of HLS tools that include not only architectural alternatives but also compiler transformations. In this paper, we developed a novel exploration approach, called spectral-aware Pareto iterative refinement, that exploits response surface models (RSMs) and spectral analysis for predicting the quality of the design points without resorting to costly architectural synthesis procedures. We show that the target solution space can be accurately modeled through RSMs, thus enabling a speedup of the overall exploration without compromising the quality of results. Furthermore, we introduce the usage of spectral techniques to find high variance regions of the design space that require analysis for improving the RSMs prediction accuracy.
SPIRIT: Spectral-Aware Pareto Iterative Refinement Optimization for Supervised High-Level Synthesis
PALERMO, GIANLUCA;ZACCARIA, VITTORIO;SILVANO, CRISTINA
2015-01-01
Abstract
Supervised high-level synthesis (HLS) is a new class of design problems where exploration strategies play the role of supervisor for tuning an HLS engine. The complexity of the problem is increased due to the large set of tunable parameters exposed by the “new wave” of HLS tools that include not only architectural alternatives but also compiler transformations. In this paper, we developed a novel exploration approach, called spectral-aware Pareto iterative refinement, that exploits response surface models (RSMs) and spectral analysis for predicting the quality of the design points without resorting to costly architectural synthesis procedures. We show that the target solution space can be accurately modeled through RSMs, thus enabling a speedup of the overall exploration without compromising the quality of results. Furthermore, we introduce the usage of spectral techniques to find high variance regions of the design space that require analysis for improving the RSMs prediction accuracy.File | Dimensione | Formato | |
---|---|---|---|
06930749.pdf
Accesso riservato
:
Publisher’s version
Dimensione
865.64 kB
Formato
Adobe PDF
|
865.64 kB | Adobe PDF | Visualizza/Apri |
SPIRIT-Spectral-Aware Pareto Iterative Refinement Optimization_11311-892555_Zaccaria.pdf
accesso aperto
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
852.62 kB
Formato
Adobe PDF
|
852.62 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.