Robert Adolf, Saketh Rama, Brandon Reagen, Gu Wei, and David Brooks. 8/23/2016. “
Fathom: Reference Workloads for Modern Deep Learning Methods.” In IEEE International Symposium on Workload Characterization.
Publisher's VersionAbstractDeep learning has been popularized by its recent successes on challenging artificial intelligence problems. One of the reasons for its dominance is also an ongoing challenge: the need for immense amounts of computational power. Hardware architects have responded by proposing a wide array of promising ideas, but to date, the majority of the work has focused on specific algorithms in somewhat narrow application domains. While their specificity does not diminish these approaches, there is a clear need for more flexible solutions. We believe the first step is to examine the characteristics of cutting edge models from across the deep learning community. Consequently, we have assembled Fathom: a collection of eight archetypal deep learning workloads for study. Each of these models comes from a seminal work in the deep learning community, ranging from the familiar deep convolutional neural network of Krizhevsky et al., to the more exotic memory networks from Facebook’s AI research group. Fathom has been released online, and this paper focuses on understanding the fundamental performance characteristics of each model. We use a set of application-level modeling tools built around the TensorFlow deep learning framework in order to analyze the behavior of the Fathom workloads. We present a breakdown of where time is spent, the similarities between the performance profiles of our models, an analysis of behavior in inference and training, and the effects of parallelism on scaling.
Fathom: Reference Workloads for Modern Deep Learning Methods Brandon Reagen, Paul Whatmough, Robert Adolf, Saketh Rama, Hyunkwang Lee, Sae Kyu Lee, José Hernández-Lobato, Gu Wei, and David Brooks. 6/18/2016. “
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators.” In International Symposium on Computer Architecture (ISCA). Seoul, Korea (South).
Publisher's VersionAbstractThe continued success of Deep Neural Networks (DNNs) in classification tasks has sparked a trend of accelerating their execution with specialized hardware. While published designs easily give an order of magnitude improvement over general-purpose hardware, few look beyond an initial implementation. This paper presents Minerva, a highly automated co-design approach across the algorithm, architecture, and circuit levels to optimize DNN hardware accelerators. Compared to an established fixed-point accelerator baseline, we show that fine-grained, heterogeneous datatype optimization reduces power by 1.5×; aggressive, inline predication and pruning of small activity values further reduces power by 2.0×; and active hardware fault detection coupled with domain-aware error mitigation eliminates an additional 2.7× through lowering SRAM voltages. Across five datasets, these optimizations provide a collective average of 8.1× power reduction over an accelerator baseline without compromising DNN model accuracy. Minerva enables highly accurate, ultra-low power DNN accelerators (in the range of tens of milliwatts), making it feasible to deploy DNNs in power-constrained IoT and mobile devices.
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators José Lobato, Michael A Gelbart, Brandon Reagen, Robert Adolf, Daniel Hernández-Lobato, Paul N Whatmough, David Brooks, Gu-Yeon Wei, and Ryan P Adams. 2016. “
Designing neural network hardware accelerators with decoupled objective evaluations.” In NIPS workshop on Bayesian Optimization, Pp. 10.
Publisher's VersionAbstractSoftware-based implementations of deep neural network predictions consume large amounts of energy, limiting their deployment in power-constrained environments. Hardware acceleration is a promising alternative. However, it is challenging to efficiently design accelerators that have both low prediction error and low energy consumption. Bayesian optimization can be used to accelerate the design problem. However, most of the existing techniques collect data in a coupled way by always evaluating the two objectives (energy and error) jointly at the same input, which is inefficient. Instead, in this work we consider a decoupled approach in which, at each iteration, we choose which objective to evaluate next and at which input. We show that considering decoupled evaluations produces better solutions when computational resources are limited. Our results also indicate that evaluating the prediction error is more important than evaluating the energy consumption.
Designing neural network hardware accelerators with decoupled objective evaluations