اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAutomatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs
461
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Modern deep Convolutional Neural Networks (CNNs) are computationally demanding, yet real applications often require high throughput and low latency. To help tackle these problems, we propose Tomato, a framework designed to automate the process of generating efficient CNN accelerators. The generated design is pipelined and each convolution layer uses different arithmetics at various precisions. Using Tomato, we showcase state-of-the-art multi-precision multi-arithmetic networks, including MobileNet-V1, running on FPGAs. To our knowledge, this is the first multi-precision multi-arithmetic auto-generation framework for CNNs. In software, Tomato fine-tunes pretrained networks to use a mixture of short powers-of-2 and fixed-point weights with a minimal loss in classification accuracy. The fine-tuned parameters are combined with the templated hardware designs to automatically produce efficient inference circuits in FPGAs. We demonstrate how our approach significantly reduces model sizes and computation complexities, and permits us to pack a complete ImageNet network onto a single FPGA without accessing off-chip memories for the first time. Furthermore, we show how Tomato produces implementations of networks with various sizes running on single or multiple FPGAs. To the best of our knowledge, our automatically generated accelerators outperform closest FPGA-based competitors by at least 2-4x for lantency and throughput; the generated accelerator runs ImageNet classification at a rate of more than 3000 frames per second.
قيم البحث
اقرأ أيضاً
This study presents a novel method to recognize human physical activities using CNN followed by LSTM. Achieving high accuracy by traditional machine learning algorithms, (such as SVM, KNN and random forest method) is a challenging task because the da
ta acquired from the wearable sensors like accelerometer and gyroscope is a time-series data. So, to achieve high accuracy, we propose a multi-head CNN model comprising of three CNNs to extract features for the data acquired from different sensors and all three CNNs are then merged, which are followed by an LSTM layer and a dense layer. The configuration of all three CNNs is kept the same so that the same number of features are obtained for every input to CNN. By using the proposed method, we achieve state-of-the-art accuracy, which is comparable to traditional machine learning algorithms and other deep neural network algorithms.
Convolutional neural networks (CNN) recently gained notable attraction in a variety of machine learning tasks: including music classification and style tagging. In this work, we propose implementing intermediate connections to the CNN architecture to
facilitate the transfer of multi-scale/level knowledge between different layers. Our novel model for music tagging shows significant improvement in comparison to the proposed approaches in the literature, due to its ability to carry low-level timbral features to the last layer.
Single computation engines have become a popular design choice for FPGA-based convolutional neural networks (CNNs) enabling the deployment of diverse models without fabric reconfiguration. This flexibility, however, often comes with significantly red
uced performance on memory-bound layers and resource underutilisation due to suboptimal mapping of certain layers on the engines fixed configuration. In this work, we investigate the implications in terms of CNN engine design for a class of models that introduce a pre-convolution stage to decompress the weights at run time. We refer to these approaches as on-the-fly. To minimise the negative impact of limited bandwidth on memory-bound layers, we present a novel hardware component that enables the on-chip on-the-fly generation of weights. We further introduce an input selective processing element (PE) design that balances the load between PEs on suboptimally mapped layers. Finally, we present unzipFPGA, a framework to train on-the-fly models and traverse the design space to select the highest performing CNN engine configuration. Quantitative evaluation shows that unzipFPGA yields an average speedup of 2.14x and 71% over optimised status-quo and pruned CNN engines under constrained bandwidth and up to 3.69x higher performance density over the state-of-the-art FPGA-based CNN accelerators.
Distributed controllers are often necessary for a multi-agent system to satisfy safety properties such as collision avoidance. Communication and coordination are key requirements in the implementation of a distributed control protocol, but maintainin
g an all-to-all communication topology is unreasonable and not always necessary. Given a safety objective and a controller implementation, we consider the problem of identifying when agents need to communicate with one another and coordinate their actions to satisfy the safety constraint. We define a coordination-free controllable predecessor operator that is used to derive a subset of the state space that allows agents to act independently, without consulting other agents to double check that the action is safe. Applications are shown for identifying an upper bound on connection delays and a self-triggered coordination scheme. Examples are provided which showcase the potential for designers to visually interpret a systems ability to tolerate delays when initializing a network connection.
FPGAs are now used in public clouds to accelerate a wide range of applications, including many that operate on sensitive data such as financial and medical records. We present ShEF, a trusted execution environment (TEE) for cloud-based reconfigurable
accelerators. ShEF is independent from CPU-based TEEs and allows secure execution under a threat model where the adversary can control all software running on the CPU connected to the FPGA, has physical access to the FPGA, and can compromise the FPGA interface logic of the cloud provider. ShEF provides a secure boot and remote attestation process that relies solely on existing FPGA mechanisms for root of trust. It also includes a Shield component that provides secure access to data while the accelerator is in use. The Shield is highly customizable and extensible, allowing users to craft a bespoke security solution that fits their accelerators memory access patterns, bandwidth, and security requirements at minimum performance and area overheads. We describe a prototype implementation of ShEF for existing cloud FPGAs and measure the performance benefits of customizable security using five accelerator designs.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
