The computation for today's intelligent personal assistants such as Apple Siri, Google Now, and Microsoft Cortana, is performed in the cloud. This cloud-only approach requires significant amounts of data to be sent to the cloud over the wireless network and puts significant computational pressure on the datacenter. However, as the computational resources in mobile devices become more powerful and energy efficient, questions arise as to whether this cloud-only processing is desirable moving forward, and what are the implications of pushing some or all of this compute to the mobile devices on the edge.In this paper, we examine the status quo approach of cloud-only processing and investigate computation partitioning strategies that effectively leverage both the cycles in the cloud and on the mobile device to achieve low latency, low energy consumption, and high datacenter throughput for this class of intelligent applications. Our study uses 8 intelligent applications spanning computer vision, speech, and natural language domains, all employing state-of-the-art Deep Neural Networks (DNNs) as the core machine learning technique. We find that given the characteristics of DNN algorithms, a fine-grained, layer-level computation partitioning strategy based on the data and computation variations of each layer within a DNN has significant latency and energy advantages over the status quo approach.Using this insight, we design Neurosurgeon, a lightweight scheduler to automatically partition DNN computation between mobile devices and datacenters at the granularity of neural network layers. Neurosurgeon does not require per-application profiling. It adapts to various DNN architectures, hardware platforms, wireless networks, and server load levels, intelligently partitioning computation for best latency or best mobile energy. We evaluate Neurosurgeon on a state-of-the-art mobile development platform and show that it improves end-to-end latency by 3.1X on average and up to 40.7X, reduces mobile energy consumption by 59.5% on average and up to 94.7%, and improves datacenter throughput by 1.5X on average and up to 6.7X.

https://dl.acm.org/doi/pdf/10.1145/3037697.3037698

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

User-facing, latency-sensitive services, such as websearch, underutilize their computing resources during daily periods of low traffic. Reusing those resources for other tasks is rarely done in production services since the contention for shared resources can cause latency spikes that violate the service-level objectives of latency-sensitive tasks. The resulting under-utilization hurts both the affordability and energy-efficiency of large-scale datacenters. With technology scaling slowing down, it becomes important to address this opportunity. We present Heracles, a feedback-based controller that enables the safe colocation of best-effort tasks alongside a latency-critical service. Heracles dynamically manages multiple hardware and software isolation mechanisms, such as CPU, memory, and network isolation, to ensure that the latency-sensitive job meets latency targets while maximizing the resources given to best-effort tasks. We evaluate Heracles using production latency-critical and batch workloads from Google and demonstrate average server utilizations of 90% without latency violations across all the load and colocation scenarios that we evaluated.

/pdf/heracles-improving-resource-efficiency-at-scale-1h8f9wo1qk.pdf

Heracles: improving resource efficiency at scale

Deep Neural Networks (DNNs) are compute-intensive learning models with growing applicability in a wide range of domains. FPGAs are an attractive choice for DNNs since they offer a programmable substrate for acceleration and are becoming available across different market segments. However, obtaining both performance and energy efficiency with FPGAs is a laborious task even for expert hardware designers. Furthermore, the large memory footprint of DNNs, coupled with the FPGAs' limited on-chip storage makes DNN acceleration using FPGAs more challenging. This work tackles these challenges by devising DnnWeaver, a framework that automatically generates a synthesizable accelerator for a given (DNN, FPGA) pair from a high-level specification in Caffe [1]. To achieve large benefits while preserving automation, DNNWEAVER generates accelerators using hand-optimized design templates. First, DnnWeaver translates a given high-level DNN specification to its novel ISA that represents a macro dataflow graph of the DNN. The DnnWeaver compiler is equipped with our optimization algorithm that tiles, schedules, and batches DNN operations to maximize data reuse and best utilize target FPGA's memory and other resources. The final result is a custom synthesizable accelerator that best matches the needs of the DNN while providing high performance and efficiency gains for the target FPGA. We use DnnWeaver to generate accelerators for a set of eight different DNN models and three different FPGAs, Xilinx Zynq, Altera Stratix V, and Altera Arria 10. We use hardware measurements to compare the generated accelerators to both multicore CPUs (ARM Cortex A15 and Xeon E3) and many-core GPUs (Tegra K1, GTX 650Ti, and Tesla K40). In comparison, the generated accelerators deliver superior performance and efficiency without requiring the programmers to participate in the arduous task of hardware design.

From high-level deep neural models to FPGAs

Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory, and computing resources, limiting their adoption for resource-constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.

/pdf/wireless-network-intelligence-at-the-edge-36kakqk6fq.pdf

Wireless Network Intelligence at the Edge

A recent trend in DNN development is to extend the reach of deep learning applications to platforms that are more resource and energy constrained, e.g., mobile devices. These endeavors aim to reduce the DNN model size and improve the hardware processing efficiency, and have resulted in DNNs that are much more compact in their structures and/or have high data sparsity. These compact or sparse models are different from the traditional large ones in that there is much more variation in their layer shapes and sizes, and often require specialized hardware to exploit sparsity for performance improvement. Thus, many DNN accelerators designed for large DNNs do not perform well on these models. In this work, we present Eyeriss v2, a DNN accelerator architecture designed for running compact and sparse DNNs. To deal with the widely varying layer shapes and sizes, it introduces a highly flexible on-chip network, called hierarchical mesh, that can adapt to the different amounts of data reuse and bandwidth requirements of different data types, which improves the utilization of the computation resources. Furthermore, Eyeriss v2 can process sparse data directly in the compressed domain for both weights and activations, and therefore is able to improve both processing speed and energy efficiency with sparse models. Overall, with sparse MobileNet, Eyeriss v2 in a 65nm CMOS process achieves a throughput of 1470.6 inferences/sec and 2560.3 inferences/J at a batch size of 1, which is 12.6x faster and 2.5x more energy efficient than the original Eyeriss running MobileNet. We also present an analysis methodology called Eyexam that provides a systematic way of understanding the performance limits for DNN processors as a function of specific characteristics of the DNN model and accelerator design; it applies these characteristics as sequential steps to increasingly tighten the bound on the performance limits.

Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices

Autonomous driving systems have attracted a significant amount of interest recently, and many industry leaders, such as Google, Uber, Tesla, and Mobileye, have invested a large amount of capital and engineering power on developing such systems. Building autonomous driving systems is particularly challenging due to stringent performance requirements in terms of both making the safe operational decisions and finishing processing at real-time. Despite the recent advancements in technology, such systems are still largely under experimentation and architecting end-to-end autonomous driving systems remains an open research question. To investigate this question, we first present and formalize the design constraints for building an autonomous driving system in terms of performance, predictability, storage, thermal and power. We then build an end-to-end autonomous driving system using state-of-the-art award-winning algorithms to understand the design trade-offs for building such systems. In our real-system characterization, we identify three computational bottlenecks, which conventional multicore CPUs are incapable of processing under the identified design constraints. To meet these constraints, we accelerate these algorithms using three accelerator platforms including GPUs, FPGAs, and ASICs, which can reduce the tail latency of the system by 169x, 10x, and 93x respectively. With accelerator-based designs, we are able to build an end-to-end autonomous driving system that meets all the design constraints, and explore the trade-offs among performance, power and the higher accuracy enabled by higher resolution cameras.

https://dl.acm.org/doi/pdf/10.1145/3173162.3173191

The Architectural Implications of Autonomous Driving: Constraints and Acceleration

As user demand scales for intelligent personal assistants (IPAs) such as Apple's Siri, Google's Google Now, and Microsoft's Cortana, we are approaching the computational limits of current datacenter architectures. It is an open question how future server architectures should evolve to enable this emerging class of applications, and the lack of an open-source IPA workload is an obstacle in addressing this question. In this paper, we present the design of Sirius, an open end-to-end IPA web-service application that accepts queries in the form of voice and images, and responds with natural language. We then use this workload to investigate the implications of four points in the design space of future accelerator-based server architectures spanning traditional CPUs, GPUs, manycore throughput co-processors, and FPGAs. To investigate future server designs for Sirius, we decompose Sirius into a suite of 7 benchmarks (Sirius Suite) comprising the computationally intensive bottlenecks of Sirius. We port Sirius Suite to a spectrum of accelerator platforms and use the performance and power trade-offs across these platforms to perform a total cost of ownership (TCO) analysis of various server design points. In our study, we find that accelerators are critical for the future scalability of IPA services. Our results show that GPU- and FPGA-accelerated servers improve the query latency on average by 10x and 16x. For a given throughput, GPU- and FPGA-accelerated servers can reduce the TCO of datacenters by 2.6x and 1.4x, respectively.

http://www.crosslayers.org/sirius-clone/wp-content/papercite-data/pdf/hauswald15asplos.pdf

Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers

One of the key challenges for improving efficiency in warehouse scale computers (WSCs) is to improve server utilization while guaranteeing the quality of service (QoS) of latency-sensitive applications. To this end, prior work has proposed techniques to precisely predict performance and QoS interference to identify 'safe' application co-locations. However, such techniques are only applicable to resources shared across cores. Achieving such precise interference prediction on real-system simultaneous multithreading (SMT) architectures has been a significantly challenging open problem due to the complexity introduced by sharing resources within a core. In this paper, we demonstrate through a real-system investigation that the fundamental difference between resource sharing behaviors on CMP and SMT architectures calls for a redesign of the way we model interference. For SMT servers, the interference on different shared resources, including private caches, memory ports, as well as integer and floating-point functional units, do not correlate with each other. This insight suggests the necessity of decoupling interference into multiple resource sharing dimensions. In this work, we propose SMiTe, a methodology that enables precise performance prediction for SMT co-location on real-system commodity processors. With a set of Rulers, which are carefully designed software stressors that apply pressure to a multidimensional space of shared resources, we quantify application sensitivity and contentiousness in a decoupled manner. We then establish a regression model to combine the sensitivity and contentiousness in different dimensions to predict performance interference. Using this methodology, we are able to precisely predict the performance interference in SMT co-location with an average error of 2.80% on SPEC CPU2006 and 1.79% on Cloud Suite. Our evaluation shows that SMiTe allows us to improve the utilization of WSCs by up to 42.57% while enforcing an application's QoS requirements.

/pdf/smite-precise-qos-prediction-on-real-system-smt-processors-54gs8jkw1x.pdf

SMiTe: Precise QoS Prediction on Real-System SMT Processors to Improve Utilization in Warehouse Scale Computers

Reducing the long tail of the query latency distribution in modern warehouse scale computers is critical for improving performance and quality of service of workloads such as Web Search and Memcached. Traditional turbo boost increases a processor's voltage and frequency during a coarse-grain sliding window, boosting all queries that are processed during that window. However, the inability of such a technique to pinpoint tail queries for boosting limits its tail reduction benefit. In this work, we propose Adrenaline, an approach to leverage finer granularity, 10's of nanoseconds, voltage boosting to effectively rein in the tail latency with query-level precision. Two key insights underlie this work. First, emerging finer granularity voltage/frequency boosting is an enabling mechanism for intelligent allocation of the power budget to precisely boost only the queries that contribute to the tail latency; and second, per-query characteristics can be used to design indicators for proactively pinpointing these queries, triggering boosting accordingly. Based on these insights, Adrenaline effectively pinpoints and boosts queries that are likely to increase the tail distribution and can reap more benefit from the voltage/frequency boost. By evaluating under various workload configurations, we demonstrate the effectiveness of our methodology. We achieve up to a 2.50x tail latency improvement for Memcached and up to a 3.03x for Web Search over coarse-grained DVFS given a fixed boosting power budget. When optimizing for energy reduction, Adrenaline achieves up to a 1.81x improvement for Memcached and up to a 1.99x for Web Search over coarse-grained DVFS.

/pdf/adrenaline-pinpointing-and-reining-in-tail-queries-with-3nxer7q0yv.pdf

Adrenaline: Pinpointing and reining in tail queries with quick voltage boosting

Heterogeneous multicore architectures have the potential to improve energy efficiency by integrating power-efficient wimpy cores with high-performing brawny cores. However, it is an open question as how to deliver energy reduction while ensuring the quality of service (QoS) of latency-sensitive web-services running on such heterogeneous multicores in warehouse-scale computers (WSCs). In this work, we first investigate the implications of heterogeneous multicores in WSCs and show that directly adopting heterogeneous multicores without re-designing the software stack to provide QoS management leads to significant QoS violations. We then present Octopus-Man, a novel QoS-aware task management solution that dynamically maps latency-sensitive tasks to the least power-hungry processing resources that are sufficient to meet the QoS requirements. Using carefully-designed feedback-control mechanisms, Octopus-Man addresses critical challenges that emerge due to uncertainties in workload fluctuations and adaptation dynamics in a real system. Our evaluation using web-search and memcached running on a real-system Intel heterogeneous prototype demonstrates that Octopus-Man improves energy efficiency by up to 41% (CPU power) and up to 15% (system power) over an all-brawny WSC design while adhering to specified QoS targets.

/pdf/octopus-man-qos-driven-task-management-for-heterogeneous-1c5m3tunfk.pdf

Yunqi Zhang

Papers

The Architectural Implications of Autonomous Driving: Constraints and Acceleration

Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers

SMiTe: Precise QoS Prediction on Real-System SMT Processors to Improve Utilization in Warehouse Scale Computers

Adrenaline: Pinpointing and reining in tail queries with quick voltage boosting

Octopus-Man: QoS-driven task management for heterogeneous multicores in warehouse-scale computers