skip to main content

Title: Machine Learning at the Edge: Efficient Utilization of Limited CPU/GPU Resources by Multiplexing
Edge clouds can provide very responsive services for end-user devices that require more significant compute capabilities than they have. But edge cloud resources such as CPUs and accelerators such as GPUs are limited and must be shared across multiple concurrently running clients. However, multiplexing GPUs across applications is challenging. Further, edge servers are likely to require considerable amounts of streaming data to be processed. Getting that data from the network stream to the GPU can be a bottleneck, limiting the amount of work GPUs do. Finally, the lack of prompt notification of job completion from GPU also results in ineffective GPU utilization. We propose a framework that addresses these challenges in the following manner. We utilize spatial sharing of GPUs to multiplex the GPU more efficiently. While spatial sharing of GPU can increase GPU utilization, the uncontrolled spatial sharing currently available with state-of-the-art systems such as CUDA-MPS can cause interference between applications, resulting in unpredictable latency. Our framework utilizes controlled spatial sharing of GPU, which limits the interference across applications. Our framework uses the GPU DMA engine to offload data transfer to GPU, therefore preventing CPU from being bottleneck while transferring data from the network to GPU. Our framework uses the CUDA event library to have timely, low overhead GPU notifications. Preliminary experiments show that we can achieve low DNN inference latency more » and improve DNN inference throughput by a factor of ∼1.4. « less
Authors:
; ;
Award ID(s):
1763929
Publication Date:
NSF-PAR ID:
10299298
Journal Name:
Proc. of Riding with AI towards Mission-Critical Communications and Computing at the Edge (AIMCOM2) Workshop in IEEE ICNP 2020
Page Range or eLocation-ID:
1 to 6
Sponsoring Org:
National Science Foundation
More Like this
  1. Edge cloud data centers (Edge) are deployed to provide responsive services to the end-users. Edge can host more powerful CPUs and DNN accelerators such as GPUs and may be used for offloading tasks from end-user devices that require more significant compute capabilities. But Edge resources may also be limited and must be shared across multiple applications that process requests concurrently from several clients. However, multiplexing GPUs across applications is challenging. With edge cloud servers needing to process a lot of streaming and the advent of multi-GPU systems, getting that data from the network to the GPU can be a bottleneck, limiting the amount of work the GPU cluster can do. The lack of prompt notification of job completion from the GPU can also result in poor GPU utilization. We build on our recent work on controlled spatial sharing of a single GPU to expand to support multi-GPU systems and propose a framework that addresses these challenges. Unlike the state-of-the-art uncontrolled spatial sharing currently available with systems such as CUDA-MPS, our controlled spatial sharing approach uses each of the GPU in the cluster efficiently by removing interference between applications, resulting in much better, predictable, inference latency We also use each ofmore »the cluster GPU's DMA engines to offload data transfers to the GPU complex, thereby preventing the CPU from being the bottleneck. Finally, our framework uses the CUDA event library to give timely, low overhead GPU notifications. Our evaluations show we can achieve low DNN inference latency and improve DNN inference throughput by at least a factor of 2.« less
  2. Deep neural networks (DNNs) are increasingly used for real-time inference, requiring low latency, but require significant computational power as they continue to increase in complexity. Edge clouds promise to offer lower latency due to their proximity to end-users and having powerful accelerators like GPUs to provide the computation power needed for DNNs. But it is also important to ensure that the edge-cloud resources are utilized well. For this, multiplexing several DNN models through spatial sharing of the GPU can substantially improve edge-cloud resource usage. Typical GPU runtime environments have significant interactions with the CPU, to transfer data to the GPU, for CPU-GPU synchronization on inference task completions, etc. These result in overheads. We present a DNN inference framework with a set of software primitives that reduce the overhead for DNN inference, increase GPU utilization and improve performance, with lower latency and higher throughput. Our first primitive uses the GPU DMA effectively, reducing the CPU cycles spent to transfer the data to the GPU. A second primitive uses asynchronous ‘events’ for faster task completion notification. GPU runtimes typically preclude fine-grained user control on GPU resources, causing long GPU downtimes when adjusting resources. Our third primitive supports overlapping of model-loading and execution,more »thus allowing GPU resource re-allocation with very little GPU idle time. Our other primitives increase inference throughput by improving scheduling and processing more requests. Overall, our primitives decrease inference latency by more than 35% and increase DNN throughput by 2-3×.« less
  3. Real-time applications such as autonomous and connected cars, surveillance, and online learning applications have to train on streaming data. They require low-latency, high throughput machine learning (ML) functions resident in the network and in the cloud to perform learning and inference. NFV on edge cloud platforms can provide support for these applications by having heterogeneous computing including GPUs and other accelerators to offload ML-related computation. GPUs provide the necessary speedup for performing learning and inference to meet the needs of these latency sensitive real-time applications. Supporting ML inference and learning efficiently for streaming data in NFV platforms has several challenges. In this paper, we present a framework, NetML, that runs existing ML applications on an heterogeneous NFV platform that includes both CPUs and GPUs. NetML efficiently transfers the appropriate packet payload to the GPU, minimizing overheads, avoiding locks, and avoiding CPU-based data copies. Additionally, NetML minimizes latency by maximizing overlap between the data movement and GPU computation. We evaluate the efficiency of our approach for training and inference using popular object detection algorithms on our platform. NetML reduces the latency for inferring images by more than 20% and increases the training throughput by 30% while reducing CPU utilization compared tomore »other state-of-the-art alternatives.« less
  4. Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)
    The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3] as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should producemore »identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.« less
  5. Graphics Processing Units (GPUs) exploit large amounts of thread-level parallelism to provide high instruction throughput and to efficiently hide long-latency stalls. The resulting high throughput, along with continued programmability improvements, have made GPUs an essential computational resource in many domains. Applications from different domains can have vastly different compute and memory demands on the GPU. In a large-scale computing environment, to efficiently accommodate such wide-ranging demands without leaving GPU resources underutilized, multiple applications can share a single GPU, akin to how multiple applications execute concurrently on a CPU. Multi-application concurrency requires several support mechanisms in both hardware and software. One such key mechanism is virtual memory, which manages and protects the address space of each application. However, modern GPUs lack the extensive support for multi-application concurrency available in CPUs, and as a result suffer from high performance overheads when shared by multiple applications, as we demonstrate. We perform a detailed analysis of which multi-application concurrency support limitations hurt GPU performance the most. We find that the poor performance is largely a result of the virtual memory mechanisms employed in modern GPUs. In particular, poor address translation performance is a key obstacle to efficient GPU sharing. State-of-the-art address translation mechanisms, whichmore »were designed for single-application execution, experience significant inter-application interference when multiple applications spatially share the GPU. This contention leads to frequent misses in the shared translation lookaside buffer (TLB), where a single miss can induce long-latency stalls for hundreds of threads. As a result, the GPU often cannot schedule enough threads to successfully hide the stalls, which diminishes system throughput and becomes a first-order performance concern. Based on our analysis, we propose MASK, a new GPU framework that provides low-overhead virtual memory support for the concurrent execution of multiple applications. MASK consists of three novel address-translation-aware cache and memory management mechanisms that work together to largely reduce the overhead of address translation: (1) a token-based technique to reduce TLB contention, (2) a bypassing mechanism to improve the effectiveness of cached address translations, and (3) an application-aware memory scheduling scheme to reduce the interference between address translation and data requests. Our evaluations show that MASK restores much of the throughput lost to TLB contention. Relative to a state-of-the-art GPU TLB, MASK improves system throughput by 57.8%, improves IPC throughput by 43.4%, and reduces application-level unfairness by 22.4%. MASK's system throughput is within 23.2% of an ideal GPU system with no address translation overhead.« less