An official website of the United States government
‘‘Extreme edge”1devices, such as smart sensors, are a uniquely challenging environment for the deployment of machine learning. The tiny energy budgets of these devices lie beyond what is feasible for conventional deep neural networks, particularly in high-throughput scenarios, requiring us to rethink how we approach edge inference. In this work, we propose ULEEN, a model and FPGA-based accelerator architecture based on weightless neural networks (WNNs). WNNs eliminate energy-intensive arithmetic operations, instead using table lookups to perform computation, which makes them theoretically well-suited for edge inference. However, WNNs have historically suffered from poor accuracy and excessive memory usage. ULEEN incorporates algorithmic improvements and a novel training strategy inspired by binary neural networks (BNNs) to make significant strides in addressing these issues. We compare ULEEN against BNNs in software and hardware using the four MLPerf Tiny datasets and MNIST. Our FPGA implementations of ULEEN accomplish classification at 4.0–14.3 million inferences per second, improving area-normalized throughput by an average of 3.6× and steady-state energy efficiency by an average of 7.1× compared to the FPGA-based Xilinx FINN BNN inference platform. While ULEEN is not a universally applicable machine learning model, we demonstrate that it can be an excellent choice for certain applications in energy- and latency-critical edge environments.
more »
« less
This content will become publicly available on March 31, 2026
PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration
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
- Award ID(s):
- 2303626
- PAR ID:
- 10580577
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Transactions on Reconfigurable Technology and Systems
- Volume:
- 18
- Issue:
- 1
- ISSN:
- 1936-7406
- Page Range / eLocation ID:
- 1 to 29
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Accelerating machine learning inference has been an active research area in recent years. In this context, field-programmable gate arrays (FPGAs) have demonstrated compelling performance by providing massive parallelism in deep neural networks (DNNs). Neural networks (NNs) are computationally intensive during inference, as they require massive amounts of multiplication and addition, which makes their implementations costly. Numerous studies have recently addressed this challenge to some extent using a combination of sparsity induction, quantization, and transformation of neurons or sub-networks into lookup tables (LUTs) on FPGAs. Gradient boosted decision trees (GBDTs) are a high-accuracy alternative to DNNs in a wide range of regression and classification tasks, particularly for tabular datasets. The basic building block of GBDTs is a decision tree, which resembles the structure of binary decision diagrams. FPGA design flows are heavily optimized to implement such a structure efficiently. In addition to decision trees, GBDTs perform simple operations during inference, including comparison and addition. We present TreeLUT as an open-source tool for implementing GBDTs using an efficient quantization scheme, hardware architecture, and pipelining strategy. It primarily utilizes LUTs with no BRAMs or DSPs on FPGAs, resulting in high efficiency. We show the effectiveness of TreeLUT using multiple classification datasets, commonly used to evaluate ultra-low area and latency architectures. Using these benchmarks, we compare our implementation results with existing DNN and GBDT methods, such as DWN, PolyLUT-Add, NeuraLUT, LogicNets, FINN, hls4ml, and others. Our results show that TreeLUT significantly improves hardware utilization, latency, and throughput at competitive accuracy compared to previous works. For instance, it achieves an accuracy of around 97% on the MNIST dataset while delivering around 4 to 101 times lower hardware cost in terms of area-delay product than recent LUT-based NNs.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
-
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
-
Latest algorithmic development has brought competitive classification accuracy for neural networks despite constraining the network parameters to ternary or binary representations. These findings show significant optimization opportunities to replace computationally-intensive convolution operations (based on multiplication) with more efficient and less complex operations such as addition. In hardware implementation domain, processing-in-memory architecture is becoming a promising solution to alleviate enormous energy-hungry data communication between memory and processing units, bringing considerable improvement for system performance and energy efficiency while running such large networks. In this paper, we review several of our recent works regarding Processing-in-Memory (PIM) accelerator based on Magnetic Random Access Memory computational sub-arrays to accelerate the inference mode of quantized neural networks using digital non-volatile memory rather than using analog crossbar operation. In this way, we investigate the performance of two distinct in-memory addition schemes compared to other digital methods based on processing-in-DRAM/GPU/ASIC design to tackle DNN power and memory wall bottleneck.more » « less
