Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision

• URL: http://arxiv.org/abs/2403.12981v1
• Date: Sat, 2 Mar 2024 02:35:08 GMT
• Title: Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision
• Authors: Ahmed F. AbouElhamayed, Susanne Balle, Deshanand Singh, Mohamed S. Abdelfattah,
• Abstract summary: We evaluate computer vision inference requests performed on a throughput-optimized serving system. We quantify the performance impact of server overheads such as data movement, preprocessing, and message brokers. Our work identifies important performance bottlenecks in different application scenarios, achieves 2.25$times$ better throughput compared to prior work, and paves the way for more holistic deep learning system design.
• Score: 6.287928298762318
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural network (DNN) inference has become an important part of many data-center workloads. This has prompted focused efforts to design ever-faster deep learning accelerators such as GPUs and TPUs. However, an end-to-end DNN-based vision application contains more than just DNN inference, including input decompression, resizing, sampling, normalization, and data transfer. In this paper, we perform a thorough evaluation of computer vision inference requests performed on a throughput-optimized serving system. We quantify the performance impact of server overheads such as data movement, preprocessing, and message brokers between two DNNs producing outputs at different rates. Our empirical analysis encompasses many computer vision tasks including image classification, segmentation, detection, depth-estimation, and more complex processing pipelines with multiple DNNs. Our results consistently demonstrate that end-to-end application performance can easily be dominated by data processing and data movement functions (up to 56% of end-to-end latency in a medium-sized image, and $\sim$ 80% impact on system throughput in a large image), even though these functions have been conventionally overlooked in deep learning system design. Our work identifies important performance bottlenecks in different application scenarios, achieves 2.25$\times$ better throughput compared to prior work, and paves the way for more holistic deep learning system design.

Related papers

• DCP: Learning Accelerator Dataflow for Neural Network via Propagation [52.06154296196845]
  This work proposes an efficient data-centric approach, named Dataflow Code Propagation (DCP), to automatically find the optimal dataflow for DNN layers in seconds without human effort. DCP learns a neural predictor to efficiently update the dataflow codes towards the desired gradient directions to minimize various optimization objectives. For example, without using additional training data, DCP surpasses the GAMMA method that performs a full search using thousands of samples.
  arXiv  Detail & Related papers  (2024-10-09T05:16:44Z)
• Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN [8.613703056677457]
  Eye-tracking technology is integral to numerous consumer electronics applications, particularly in virtual and augmented reality (VR/AR) Yet, achieving optimal performance across all these fronts presents a formidable challenge. We tackle this challenge through a synergistic software/ hardware co-design of the system with an event camera. Our system achieves 81% p5 accuracy, 99.5% p10 accuracy, and 3.71 Meanean Distance with 0.7 ms latency while only consuming 2.29 mJ per inference.
  arXiv  Detail & Related papers  (2024-04-22T15:28:42Z)
• From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport [32.39176908225668]
  We introduce the concept of the non-linearity signature of DNN, the first theoretically sound solution for measuring the non-linearity of deep neural networks. We provide extensive experimental results that highlight the practical usefulness of the proposed non-linearity signature.
  arXiv  Detail & Related papers  (2023-10-17T17:50:22Z)
• Transferability of Convolutional Neural Networks in Stationary Learning Tasks [96.00428692404354]
  We introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems. We show that a CNN trained on small windows of such signals achieves a nearly performance on much larger windows without retraining. Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten.
  arXiv  Detail & Related papers  (2023-07-21T13:51:45Z)
• A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning [27.498927971861068]
  Deep neural networks (DNNs) are widely used in many industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. Prior work has shown the high accuracy of a DNN model does not imply high robustness because the input data and external environment are constantly changing.
  arXiv  Detail & Related papers  (2022-11-18T03:32:53Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• Dynamic Split Computing for Efficient Deep Edge Intelligence [78.4233915447056]
  We introduce dynamic split computing, where the optimal split location is dynamically selected based on the state of the communication channel. We show that dynamic split computing achieves faster inference in edge computing environments where the data rate and server load vary over time.
  arXiv  Detail & Related papers  (2022-05-23T12:35:18Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Scene Understanding for Autonomous Driving [0.0]
  We study the behaviour of different configurations of RetinaNet, Faster R-CNN and Mask R-CNN presented in Detectron2. We observe a significant improvement in performance after fine-tuning these models on the datasets of interest. We run inference in unusual situations using out of context datasets, and present interesting results.
  arXiv  Detail & Related papers  (2021-05-11T09:50:05Z)
• Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics [24.62486707803304]
  In this work, we examine end-to-end DNN execution in visual analytics systems on modern accelerators. To address the bottleneck of preprocessing, we introduce two optimizations for end-to-end visual analytics systems. We show that its optimizations can achieve up to 5.9x end-to-end throughput improvements at a fixed accuracy over recent work in visual analytics.
  arXiv  Detail & Related papers  (2020-07-25T20:26:05Z)
• Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey [77.99182201815763]
  Deep Neural Networks (DNNs) achieve state-of-the-art results in many different problem settings. DNNs are often treated as black box systems, which complicates their evaluation and validation. One promising field, inspired by the success of convolutional neural networks (CNNs) in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations.
  arXiv  Detail & Related papers  (2020-06-30T14:56:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.