Novel dynamic partial reconfiguration implementations of the support vector machine classifier on FPGA

Abstract

Abstract:The support vector machine (SVM) is one of the highly powerful classifiers that have been shown to be capable of dealing with high-dimensional data. However, its complexity increases requirements of computational power. Recent technologies including the postgenome data of high-dimensional nature add further complexity to the construction of SVM classifiers. In order to overcome this problem, hardware implementations of the SVM classifier have been proposed to benefit from parallelism to accelerate the SVM. On the other hand, those implementations offer limited flexibility in terms of changing parameters and require the reconfiguration of the whole device. The latter interrupts the operation of other tasks placed on the hardware device. In this work, two flexible hardware implementations of the SVM classifier are proposed, namely A1 and A2 classifiers with successful applications in a microarray dataset. In addition, two dynamically and partially reconfigurable (DPR) architectures of the SVM classifier are presented. The A1 and A2 architectures have achieved up to 61 × and 49 × speed-up, respectively, over the equivalent general purpose processor. Furthermore, the DPR implementations achieved at least ∼ 8 × reduction in reconfiguration time compared to non-DPR implementation. This is a significant achievement that can be easily adapted in other application domains of a similar nature.

FPGA Implementations of SVM Classifiers: A Review

“…In addition, different implementations of systolic array architecture of PEs that is responsible for the complicated matrix multiplication required for the kernel computation are presented in [35][36][37][38]. Besides gaining advantages from using the systolic architecture, these implementations use an additional hardware technique, the partial reconfiguration technology (to be presented in the following category).…”

FPGA Dynamic and Partial Reconfiguration

“…Another example is applications with adaptive data clustering (K-means clustering, support vector machines (SVMs), etc.) where kernels are selectively modified with multiple kernels hosted in the same FPGA [Hussain et al 2012[Hussain et al , 2014. Concurrent implementation of multiple classifiers improves overall system performance.…”

Hardware Acceleration of SVM-Based Classifier for Melanoma Images

“…Many work exploit the FPGA-based parallel systolic array architecture in their implementations [6,7,8,9,10], resulting in good results of classification speedups that mostly outperformed implementations on GPPs/CPUs. In addition, other work employed the Dynamic Partially Reconfiguration (DPR) technique [7], [11], achieving higher flexibility and design space expansion besides gaining speedups.…”