Abstract-We consider the problem of mitigating a highly varying wireless channel between a transmitting ground node and receivers on a small, low-altitude unmanned aerial vehicle (UAV) in a 802.11 wireless mesh network. One approach is to use multiple transmitter and receiver nodes that exploit the channel's spatial/temporal diversity and that cooperate to improve overall packet reception. We present a series of measurement results from a real-world testbed that characterize the resulting wireless channel. We show that the correlation between receiver nodes on the airplane is poor at small time scales so receiver diversity can be exploited. Our measurements suggest that using several receiver nodes simultaneously can boost packet delivery rates substantially. Lastly, we show that similar results apply to transmitter selection diversity as well.

Abstract-Compressive sensing has gained momentum in recent years as an exciting new theory in signal processing with several useful applications. It states that signals known to have a sparse representation may be encoded and later reconstructed using a small number of measurements, approximately proportional to the signal's sparsity rather than its size. This paper addresses a critical problem that arises when scaling compressive sensing to signals of large length: that the time required for decoding becomes prohibitively long, and that decoding is not easily parallelized.We describe a method for partitioned compressive sensing, by which we divide a large signal into smaller blocks that may be decoded in parallel. However, since this process requires a significant increase in the number of measurements needed for exact signal reconstruction, we focus on mitigating artifacts that arise due to partitioning in approximately reconstructed signals. Given an error-prone partitioned decoding, we use large magnitude components that are detected with highest accuracy to influence the decoding of neighboring blocks, and call this approach neighbor-weighted decoding. We show that, for applications with a predefined error threshold, our method can be used in conjunction with partitioned compressive sensing to improve decoding speed, requiring fewer additional measurements than unweighted or locally-weighted decoding.

Abstract-We apply hierarchical sparse coding, a form of deep learning, to model user-driven workloads based on on-chip hardware performance counters. We then predict periods of low instruction throughput, during which frequency and voltage can be scaled to reclaim power. Using a multi-layer coding structure, our method progressively codes counter values in terms of a few prominent features learned from data, and passes them to a Support Vector Machine (SVM) classifier where they act as signatures for predicting future workload states. We show that prediction accuracy and look-ahead range improve significantly over linear regression modeling, giving more time to adjust power management settings. Our method relies on learning and feature extraction algorithms that can discover and exploit hidden statistical invariances specific to workloads. We argue that, in addition to achieving superior prediction performance, our method is fast enough for practical use. To our knowledge, we are the first to use deep learning at the instruction level for workload prediction and on-chip power adaptation.

Modern branch predictors predict the vast majority of conditional branch instructions with near-perfect accuracy, allowing superscalar, out-of-order processors to maximize speculative efficiency and thus performance. However, this impressive overall effectiveness belies a substantial missed opportunity in single-threaded instructions per cycle (IPC). For example, we show that correcting the mispredictions made by the state-ofthe-art TAGE-SC-L branch predictor on SPECint 2017 would improve IPC by margins similar to an advance in process technology node.In this work, we measure and characterize these mispredictions. We find that they categorically arise from either (1) a small number of systematically hard-to-predict (H2P) branches; or (2) rare branches with low dynamic execution counts. Using data from SPECint 2017 and additional large code footprint applications, we quantify the occurrence and IPC impact of these two categories. We then demonstrate that increasing the resources afforded to existing branch predictors does not alone address the root causes of most mispredictions. This leads us to reexamine basic assumptions in branch prediction and to propose new research directions that, for example, deploy machine learning to improve pattern matching for H2Ps, and use on-chip phase learning to track long-term statistics for rare branches.