Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userunzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
414
0
0.0
(
0
)
Added by
Stylianos Venieris
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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 reduced 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.
rate research
Read More
Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using methods such as distributed synchronous SGD. Among the issues with this approach is that to make the distributed cluster work with high utilization, the workload distributed to each node must be large, which implies nontrivial growth in the SGD mini-batch size. In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer parallelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is a fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation. As a result, storage demand is reduced to the point where only on-chip memory is used for the convolution layers. We evaluate FPDeep with the Alexnet, VGG-16, and VGG-19 benchmarks. Experimental results show that FPDeep has good scalability to a large number of FPGAs, with the limiting factor being the FPGA-to-FPGA bandwidth. With 6 transceivers per FPGA, FPDeep shows linearity up to 83 FPGAs. Energy efficiency is evaluated with respect to GOPs/J. FPDeep provides, on average, 6.36x higher energy efficiency than comparable GPU servers.
Image feature extraction and matching is a fundamental but computation intensive task in machine vision. This paper proposes a novel FPGA-based embedded system to accelerate feature extraction and matching. It implements SURF feature point detection and BRIEF feature descriptor construction and matching. For binocular stereo vision, feature matching includes both tracking matching and stereo matching, which simultaneously provide feature point correspondences and parallax information. Our system is evaluated on a ZYNQ XC7Z045 FPGA. The result demonstrates that it can process binocular video data at a high frame rate (640$times$480 @ 162fps). Moreover, an extensive test proves our system has robustness for image compression, blurring and illumination.
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.
We describe the hardwired implementation of algorithms for Monte Carlo simulations of a large class of spin models. We have implemented these algorithms as VHDL codes and we have mapped them onto a dedicated processor based on a large FPGA device. The measured performance on one such processor is comparable to O(100) carefully programmed high-end PCs: it turns out to be even better for some selected spin models. We describe here codes that we are currently executing on the IANUS massively parallel FPGA-based system.
The increasing application of deep learning technology drives the need for an efficient parallel computing architecture for Convolutional Neural Networks (CNNs). A significant challenge faced when designing a many-core CNN accelerator is to handle the data movement between the processing elements. The CNN workload introduces many-to-one traffic in addition to one-to-one and one-to-many traffic. As the de-facto standard for on-chip communication, Network-on-Chip (NoC) can support various unicast and multicast traffic. For many-to-one traffic, repetitive unicast is employed which is not an efficient way. In this paper, we propose to use the gather packet on mesh-based NoCs employing output stationary systolic array in support of many-to-one traffic. The gather packet will collect the data from the intermediate nodes eventually leading to the destination efficiently. This method is evaluated using the traffic traces generated from the convolution layer of AlexNet and VGG-16 with improvement in the latency and power than the repetitive unicast method.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
