Power efficient big data analytics algorithms through low-level operations

We present an empirical performance evaluation of algorithms that replace arithmetic operations with low-level bit operations for power-aware Big Data processing. Specifically, we compare two different data structures in terms of both execution time and power efficiency: (a) a baseline design using arrays, and (b) a design using bit-slice indexing (BSI) and distributed BSI arithmetic. We evaluate two types of queries popular in Big Data analytics: aggregations and top-k. These queries were implemented using each of the two data structure designs on Apache Spark running on a server cluster that was instrumented with specialized hardware for synchronized real-time power measurement for each server in the cluster. We performed a series of experiments running the above queries on several different datasets. These experiments show that the bit-slicing algorithm consistently outperforms the array algorithm in both power efficiency and execution time. An interesting observation is that the power efficiency improvement of the bit-slicing algorithm over the array method is comparable to or greater than the improvement in execution time for both queries evaluated.