As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is post hoc feature attribution, a family of methods for giving each feature in an input a score corresponding to its influence on a model’s output. A major limitation of this family of explainers in practice is that they can disagree on which features are more important than others. Our contribution in this paper is a method of training models with this disagreement problem in mind. We do this by introducing a Post hoc Explainer Agreement Regularization (PEAR) loss term alongside the standard term corresponding to accuracy, an additional term that measures the difference in feature attribution between a pair of explainers. We observe on three datasets that we can train a model with this loss term to improve explanation consensus on unseen data, and see improved consensus between explainers other than those used in the loss term. We examine the trade-off between improved consensus and model performance. And finally, we study the influence our method has on feature attribution explanations.

The pace of advancement of the top-end supercomputers historically followed an exponential curve similar to (and driven in part by) Moore's Law. Shortly after hitting the petaflop mark, the community started looking ahead to the next milestone: Exascale. However, many obstacles were already looming on the horizon, such as the slowing of Moore's Law, and others like the end of Dennard Scaling had already arrived. Anticipating significant challenges for the overall high-performance computing (HPC) community to achieve the next 1000x improvement, the U.S. Department of Energy (DOE) launched the Exascale Computing Program to enable and accelerate fundamental research across the many technologies needed to achieve exascale computing.

On current Android mobile devices, DVFS is a key power management technique. Besides CPU, memory and GPU support DVFS as well. OS modules known as governors implement algorithms that dynamically adjust operating frequency for their respective hardware components to balance performance and power. However, the stock governors do not consider application characteristics, manager power instead of energy, and operate independently of each other, thus leading to energy inefficiency. In this paper, we present an application-specific approach to energy optimization targeting Android mobile devices. In this two-step approach, we first perform offline profiling of the target app to obtain its performance and power measurements under different DVFS settings. The profiling data are then used by a feedback loop based online controller to dynamically select energy-optimal DVFS settings for the app while trying to meet a performance target. In contrast with the default governors, our approach is application-specific, manages energy, and controls both CPU and memory in unison. Tested on a few mainstream applications, our solution achieves considerable energy savings with minimal performance loss. This paper describes the design and evaluation of the system in detail with a particular focus on problems related to the robustness of the approach.

Resource control in heterogeneous computers built with subsystems from different vendors is challenging. There is a tension between the need to quickly generate local decisions in each subsystem and the desire to coordinate the different subsystems for global optimization. In practice, global coordination among subsystems is considered hard, and current commercial systems use centralized controllers. The result is high response time and high design cost due to lack of modularity.

In this paper, we present a ferroelectric FET (FeFET) based power-efficient architecture to accelerate data-intensive applications such as deep neural networks (DNNs). We propose a cross-cutting solution combining emerging device technologies, circuit optimizations, and micro-architecture innovations. At device level, FeFET crossbar is utilized to perform vector-matrix multiplication (VMM). As a field effect device, FeFET significantly reduces the read/write energy compared with the resistive random-access memory (ReRAM). At circuit level, we propose an all-digital peripheral design, reducing the large overhead introduced by ADC and DAC in prior works. In terms of micro-architecture innovation, a dedicated hierarchical network-on-chip (H-NoC) is developed for input broadcasting and on-the-fly partial results processing, reducing the data transmission volume and latency. Speed, power, area and computing accuracy are evaluated based on detailed device characterization and system modeling. For DNN computing, our design achieves 254x and 9.7x gain in power efficiency (GOPS/W) compared to GPU and ReRAM based designs, respectively.

Energy management is a key issue for mobile devices. On current Android devices, power management relies heavily on OS modules known as governors. These modules are created for various hardware components, including the CPU, to support DVFS. They implement algorithms that attempt to balance performance and power consumption. In this paper we make the observation that the existing governors are (1) general-purpose by nature (2) focused on power reduction and (3) are not energy-optimal for many applications. We thus establish the need for an application-specific approach that could overcome these drawbacks and provide higher energy efficiency for suitable applications. We also show that existing methods manage power and performance in an independent and isolated fashion and that co-ordinated control of multiple components can save more energy. In addition, we note that on mobile devices, energy savings cannot be achieved at the expense of performance. Consequently, we propose a solution that minimizes energy consumption of specific applications while maintaining a user-specified performance target. Our solution consists of two stages: (1) offline profiling and (2) online controlling. Utilizing the offline profiling data of the target application, our control theory based online controller dynamically selects the optimal system configuration (in this paper, combination of CPU frequency and memory bandwidth) for the application, while it is running. Our energy management solution is tested on a Nexus 6 smartphone with 6 real-world applications. We achieve 4 - 31% better energy than default governors with a worst case performance loss of <; 1%.