An official website of the United States government
Deep neural networks (DNNs) have experienced unprecedented success in a variety of cognitive tasks due to which there has been a move to deploy DNNs in edge devices. DNNs are usually comprised of multiply-and-accumulate (MAC) operations and are both data and compute intensive. In-memory computing (IMC) methodologies have shown significant energy efficiency and throughput benefits for DNN workloads by reducing data movement and eliminating memory reads. Weight pruning in DNNs can further improve the energy/throughput of DNN hardware through reduced storage and compute. Recent IMC works [1]–[3], [6] have not explored such sparse compression techniques unlike ASIC counterparts to enable storage benefits and compute skipping. A recent work [4] attempted to exploit this by compressing weights using a binary map and a custom compression format. This is sub-optimal because the implementation requires a complex routing mechanism (butterfly routing), additional compute to decode compressed weights and has limited flexibility in supporting different sparse encodings. Fig. 1 illustrates our motivations and the challenges for implementing weight compression in digital IMC designs and the need for a new methodology to enable sparse compute directly on compressed weights. In this work, we present a novel sparsity-integrated IMC (SP-IMC) macro in 28nm CMOS which, for the first time, utilizes three popular sparse compression formats, i.e., coordinate representation (COO), run length encoding (RL) and N:m sparsity [7] all along the matrix column direction with tunable precisions. SP-IMC stores and directly processes the sparse compressed weights in the macro, achieving higher storage density, reduction in re-write operations to the macro and higher overall energy efficiency.
more »
« less
SmartDeal: Remodeling Deep Network Weights for Efficient Inference and Training
The record-breaking performance of deep neural networks (DNNs) comes with heavy parameter budgets, which leads to external dynamic random access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it nontrivial for DNN deployment on resource-constrained devices, calling for minimizing the movements of weights and data in order to improve the energy efficiency. Driven by this critical bottleneck, we present SmartDeal, a hardware-friendly algorithm framework to trade higher-cost memory storage/access for lower-cost computation, in order to aggressively boost the storage and energy efficiency, for both DNN inference and training. The core technique of SmartDeal is a novel DNN weight matrix decomposition framework with respective structural constraints on each matrix factor, carefully crafted to unleash the hardware-aware efficiency potential. Specifically, we decompose each weight tensor as the product of a small basis matrix and a large structurally sparse coefficient matrix whose nonzero elements are readily quantized to the power-of-2. The resulting sparse and readily quantized DNNs enjoy greatly reduced energy consumption in data movement as well as weight storage, while incurring minimal overhead to recover the original weights thanks to the required sparse bit-operations and cost-favorable computations. Beyond inference, we take another leap to embrace energy-efficient training, by introducing several customized techniques to address the unique roadblocks arising in training while preserving the SmartDeal structures. We also design a dedicated hardware accelerator to fully utilize the new weight structure to improve the real energy efficiency and latency performance. We conduct experiments on both vision and language tasks, with nine models, four datasets, and three settings (inference-only, adaptation, and fine-tuning). Our extensive results show that 1) being applied to inference, SmartDeal achieves up to 2.44x improvement in energy efficiency as evaluated using real hardware implementations and 2) being applied to training, SmartDeal can lead to 10.56x and 4.48x reduction in the storage and the training energy cost, respectively, with usually negligible accuracy loss, compared to state-of-the-art training baselines. Our source codes are available at: https://github.com/VITA-Group/SmartDeal.
more »
« less
- Award ID(s):
- 1937592
- PAR ID:
- 10358518
- Date Published:
- Journal Name:
- IEEE Transactions on Neural Networks and Learning Systems
- ISSN:
- 2162-237X
- Page Range / eLocation ID:
- 1 to 15
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep neural networks (DNNs) have emerged as the most powerful machine learning technique in numerous artificial intelligent applications. However, the large sizes of DNNs make themselves both computation and memory intensive, thereby limiting the hardware performance of dedicated DNN accelerators. In this paper, we propose a holistic framework for energy-efficient high-performance highly-compressed DNN hardware design. First, we propose block-circulant matrix-based DNN training and inference schemes, which theoretically guarantee Big-O complexity reduction in both computational cost (from O(n2) to O(n log n)) and storage requirement (from O(n2) to O(n)) of DNNs. Second, we dedicatedly optimize the hardware architecture, especially on the key fast Fourier transform (FFT) module, to improve the overall performance in terms of energy efficiency, computation performance and resource cost. Third, we propose a design flow to perform hardware-software co-optimization with the purpose of achieving good balance between test accuracy and hardware performance of DNNs. Based on the proposed design flow, two block-circulant matrix-based DNNs on two different datasets are implemented and evaluated on FPGA. The fixed-point quantization and the proposed block-circulant matrix-based inference scheme enables the network to achieve as high as 3.5 TOPS computation performance and 3.69 TOPS/W energy efficiency while the memory is saved by 108X ~ 116X with negligible accuracy degradation.more » « less
-
Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning, which affects performance and throughput; 2) the increased training complexity; and 3) the lack of rigirous guarantee of compression ratio and inference accuracy. To overcome these limitations, this paper proposes CirCNN, a principled approach to represent weights and process neural networks using block-circulant matrices. CirCNN utilizes the Fast Fourier Transform (FFT)-based fast multiplication, simultaneously reducing the computational complexity (both in inference and training) from O(n2) to O(n log n) and the storage complexity from O(n2) to O(n), with negligible accuracy loss. Compared to other approaches, CirCNN is distinct due to its mathematical rigor: the DNNs based on CirCNN can converge to the same "effectiveness" as DNNs without compression. We propose the CirCNN architecture, a universal DNN inference engine that can be implemented in various hardware/software platforms with configurable network architecture (e.g., layer type, size, scales, etc.). In CirCNN architecture: 1) Due to the recursive property, FFT can be used as the key computing kernel, which ensures universal and small-footprint implementations. 2) The compressed but regular network structure avoids the pitfalls of the network pruning and facilitates high performance and throughput with highly pipelined and parallel design. To demonstrate the performance and energy efficiency, we test CirCNN in FPGA, ASIC and embedded processors. Our results show that CirCNN architecture achieves very high energy efficiency and performance with a small hardware footprint. Based on the FPGA implementation and ASIC synthesis results, CirCNN achieves 6 - 102X energy efficiency improvements compared with the best state-of-the-art results.more » « less
-
Sparse deep neural networks (DNNs) have the potential to deliver compelling performance and energy efficiency without significant accuracy loss. However, their benefits can quickly diminish if their training is oblivious to the target hardware. For example, fewer critical connections can have a significant overhead if they translate into long-distance communication on the target hardware. Therefore, hardware-aware sparse training is needed to leverage the full potential of sparse DNNs. To this end, we propose a novel and comprehensive communication-aware sparse DNN optimization framework for tile-based in-memory computing (IMC) architectures. The proposed technique, CANNON first maps the DNN layers onto the tiles of the target architecture. Then, it replaces the fully connected and convolutional layers with communication-aware sparse connections. After that, CANNON optimizes the communication cost with minimal impact on the DNN accuracy. Extensive experimental evaluations with a wide range of DNNs and datasets show up to 3.0× lower communication energy, 3.1× lower communication latency, and 6.8× lower energy-delay product compared to state-of-the-art pruning approaches with a negligible impact on the classification accuracy on IMC-based machine learning accelerators.more » « less
-
Conventional multiply-accumulate (MAC) operations have long dominated computation time for deep neural networks (DNNs), especially convolutional neural networks (CNNs). Recently, product quantization (PQ) has been applied to these workloads, replacing MACs with memory lookups to pre-computed dot products. To better understand the efficiency tradeoffs of product-quantized DNNs (PQ-DNNs), we create a custom hardware accelerator to parallelize and accelerate nearest-neighbor search and dot-product lookups. Additionally, we perform an empirical study to investigate the efficiency–accuracy tradeoffs of different PQ parameterizations and training methods. We identify PQ configurations that improve performance-per-area for ResNet20 by up to 3.1×, even when compared to a highly optimized conventional DNN accelerator, with similar improvements on two additional compact DNNs. When comparing to recent PQ solutions, we outperform prior work by 4× in terms of performance-per-area with a 0.6% accuracy degradation. Finally, we reduce the bitwidth of PQ operations to investigate the impact on both hardware efficiency and accuracy. With only 2–6-bit precision on three compact DNNs, we were able to maintain DNN accuracy eliminating the need for DSPs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TNNLS.2021.3138056
