An official website of the United States government
Accurate medical imaging segmentation is critical for precise and effective medi- cal interventions. However, despite the success of convolutional neural networks (CNNs) in medical image segmentation, they still face challenges in handling fine-scale features and variations in image scales. These challenges are particularly evident in complex and challenging segmentation tasks, such as the BraTS multi- label brain tumor segmentation challenge. In this task, accurately segmenting the various tumor sub-components, which vary significantly in size and shape, remains a significant challenge, with even state-of-the-art methods producing substantial errors. Therefore, we propose two architectures, FMG-Net and W-Net, that incor- porate the principles of geometric multigrid methods for solving linear systems of equations into CNNs to address these challenges. Our experiments on the BraTS 2020 dataset demonstrate that both FMG-Net and W-Net outperform the widely used U-Net architecture regarding tumor subcomponent segmentation accuracy and training efficiency. These findings highlight the potential of incorporating the principles of multigrid methods into CNNs to improve the accuracy and efficiency of medical imaging segmentation.
more »
« less
FlexCNN: An End-to-End Framework for Composing CNN Accelerators on FPGA
With reduced data reuse and parallelism, recent convolutional neural networks (CNNs) create new challenges for FPGA acceleration. Systolic arrays (SAs) are efficient, scalable architectures for convolutional layers, but without proper optimizations, their efficiency drops dramatically for reasons: 1) the different dimensions within same-type layers, 2) the different convolution layers especially transposed and dilated convolutions, and 3) CNN’s complex dataflow graph. Furthermore, significant overheads arise when integrating FPGAs into machine learning frameworks. Therefore, we present a flexible, composable architecture called FlexCNN, which delivers high computation efficiency by employing dynamic tiling, layer fusion, and data layout optimizations. Additionally, we implement a novel versatile SA to process normal, transposed, and dilated convolutions efficiently. FlexCNN also uses a fully-pipelined software-hardware integration that alleviates the software overheads. Moreover, with an automated compilation flow, FlexCNN takes a CNN in the ONNX representation, performs a design space exploration, and generates an FPGA accelerator. The framework is tested using three complex CNNs: OpenPose, U-Net, and E-Net. The architecture optimizations achieve 2.3 × performance improvement. Compared to a standard SA, the versatile SA achieves close-to-ideal speedups, with up to 15.98 × and 13.42 × for transposed and dilated convolutions, with a 6% average area overhead. The pipelined integration leads to a 5 × speedup for OpenPose.
more »
« less
- Award ID(s):
- 1719403
- PAR ID:
- 10399755
- Date Published:
- Journal Name:
- ACM Transactions on Reconfigurable Technology and Systems
- ISSN:
- 1936-7406
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear because of the growing demand on prediction accuracy and analysis quality. The wide and deep CNNs, however, require a large amount of computing resources and processing time. Many previous works have studied model pruning to improve inference performance, but little work has been done for effectively reducing training cost. In this paper, we propose ClickTrain: an efficient and accurate end-to-end training and pruning framework for CNNs. Different from the existing pruning-during-training work, ClickTrain provides higher model accuracy and compression ratio via fine-grained architecture-preserving pruning. By leveraging pattern-based pruning with our proposed novel accurate weight importance estimation, dynamic pattern generation and selection, and compiler-assisted computation optimizations, ClickTrain generates highly accurate and fast pruned CNN models for direct deployment without any extra time overhead, compared with the baseline training. ClickTrain also reduces the end-to-end time cost of the pruning-after-training method by up to 2.3X with comparable accuracy and compression ratio. Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.more » « less
-
null (Ed.)This paper presents the first 28 nm ASIC implementation of an accelerator for the post-quantum digital signature scheme XMSS. In particular, this paper presents an architecture for a novel, pipelined XMSS Leaf accelerator for accelerating the most compute-intensive step in the XMSS algorithm. This paper then presents the ASIC designs for both an existing non-pipelined accelerator architecture and the novel, pipelined XMSS Leaf accelerator. In addition, the performance of the28 nm ASIC is compared to the same designs on 28 nm Artix-7FPGAs. The novel pipelined XMSS Leaf accelerator is 25% faster compared to the non-pipelined version in the ASIC, and both accelerator architectures have a 10×lower power consumption than on the FPGAs. The evaluation shows that the pipelining increases the frequency by 1.7×on the FPGA but only 1.2×on the ASIC, due to the critical path in the ASIC being in the memory. The non-pipelined XMSS Leaf accelerator is shown to have a significantly better area-delay and energy-delay metric on the ASIC, while the pipelined accelerator wins out in these metrics on the FPGA. Consequently, this work shows the different architectural decisions that need to be made between FPGA and ASIC designs, when selecting how to best implement a post-quantum cryptographic accelerator in hardware.more » « less
-
The ending of Moore’s Law makes domain-specific architecture as the future of computing. The most representative is the emergence of various deep learning accelerators. Among the proposed solutions, resistive random access memory (ReRAM) based process-inmemory (PIM) architecture is anticipated as a promising candidate because ReRAM has the capability of both data storage and in-situ computation. However, we found that existing solutions are unable to efficiently support the computational needs required by the training of unsupervised generative adversarial networks (GANs), due to the lack of the following two features: 1) Computation efficiency: GAN utilizes a new operator, called transposed convolution. It inserts massive zeros in its input before a convolution operation, resulting in significant resource under-utilization; 2) Data traffic: The data intensive training process of GANs often incurs structural heavy data traffic as well as frequent massive data swaps. Our research follows the PIM strategy by leveraging the energy-efficiency of ReRAM arrays for vector-matrix multiplication to enhance the performance and energy efficiency. Specifically, we propose a novel computation deformation technique that can skip zero-insertions in transposed convolution for computation efficiency improvement. Moreover, we explore an efficient pipelined training procedure to reduce on-chip memory access. The implementation of related circuits and architecture is also discussed. At the end, we present our perspective on the future trend and opportunities of deep learning accelerators.more » « less
-
Efficient Process-in-Memory Architecture Design for Unsupervised GAN-based Deep Learning using ReRAMThe ending of Moore’s Law makes domain-specific architecture as the future of computing. The most representative is the emergence of various deep learning accelerators. Among the proposed solutions, resistive random access memory (ReRAM) based process-inmemory (PIM) architecture is anticipated as a promising candidate because ReRAM has the capability of both data storage and in-situ computation. However, we found that existing solutions are unable to efficiently support the computational needs required by the training of unsupervised generative adversarial networks (GANs), due to the lack of the following two features: 1) Computation efficiency: GAN utilizes a new operator, called transposed convolution. It inserts massive zeros in its input before a convolution operation, resulting in significant resource under-utilization; 2) Data traffic: The data intensive training process of GANs often incurs structural heavy data traffic as well as frequent massive data swaps. Our research follows the PIM strategy by leveraging the energy-efficiency of ReRAM arrays for vector-matrix multiplication to enhance the performance and energy efficiency. Specifically, we propose a novel computation deformation technique that can skip zero-insertions in transposed convolution for computation efficiency improvement. Moreover, we explore an efficient pipelined training procedure to reduce on-chip memory access. The implementation of related circuits and architecture is also discussed. At the end, we present our perspective on the future trend and opportunities of deep learning accelerators.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3570928
