High performance implementation of the inverse TFT

Abstract

The inverse truncated Fourier transform (ITFT) is a key component in the fast polynomial and large integer algorithms introduced by van der Hoeven. This paper reports a high performance implementation of the ITFT which poses additional challenges compared to that of the forward transform. A general-radix variant of the ITFT algorithm is developed to allow the implementation to automatically adapt to the memory hierarchy. Then a parallel ITFT algorithm is developed that trades off small arithmetic cost for full vectorization and improved multi-threaded parallelism. The algorithms are automatically generated and tuned to produce an arbitrary-size ITFT library. The new algorithms and the implementation smooths out the staircase performance associated with power-of-two modular FFT implementations, and provide significant performance improvement over zeropadding approaches even when high-performance FFT libraries are used.

A Novel Transfer Learning Method Based on Common Space Mapping and Weighted Domain Matching

“…Experiments show its advantages over some other methods. In the future, we will extend the proposed algorithm to various applications, such as computational mechanic [8], [9], [10], [11], [12], [13], multimedia [14], [15], [16], [17], [18], [19], [20], [21], [22], medical imaging [23], [24], [25], [26], [27], [28], [29], [30], [31], bioinformatics [32], [33], [34], [35], material science [36], [37], [38], high-performance computing [39], [40], [41], [42], [43], malicious websites detection [44], [45], [46], [47], biometrics [48], [49], [50], [51], etc. We will also consider using some other models to represent and construction the classifier, such as Bayesian network [52], [53],…”