skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A Survey on Sparsity Exploration in Transformer-Based Accelerators
Transformer models have emerged as the state-of-the-art in many natural language processing and computer vision applications due to their capability of attending to longer sequences of tokens and supporting parallel processing more efficiently. Nevertheless, the training and inference of transformer models are computationally expensive and memory intensive. Meanwhile, utilizing the sparsity in deep learning models has proven to be an effective approach to alleviate the computation challenge as well as help to fit large models in edge devices. As high-performance CPUs and GPUs are generally not flexible enough to explore low-level sparsity, a number of specialized hardware accelerators have been proposed for transformer models. This paper provides a comprehensive review of hardware transformer accelerators that have been proposed to explore sparsity for computation and memory optimizations. We classify existing works based on the strategies of utilizing sparsity and identify their pros and cons in those strategies. Based on our analysis, we point out promising directions and recommendations for future works on improving the effective sparse execution of transformer hardware accelerators.  more » « less
Award ID(s):
2223483
PAR ID:
10462263
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Electronics
Volume:
12
Issue:
10
ISSN:
2079-9292
Page Range / eLocation ID:
2299
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, IEEE/ACM International Symposium on Microarchitecture)
    null (Ed.)
    The ever-growing parameter size and computation cost of Convolutional Neural Network (CNN) models hinder their deployment onto resource-constrained platforms. Network pruning techniques are proposed to remove the redundancy in CNN parameters and produce a sparse model. Sparse-aware accelerators are also proposed to reduce the computation cost and memory bandwidth requirements of inference by leveraging the model sparsity. The irregularity of sparse patterns, however, limits the efficiency of those designs. Researchers proposed to address this issue by creating a regular sparsity pattern through hardware-aware pruning algorithms. However, the pruning rate of these solutions is largely limited by the enforced sparsity patterns. This limitation motivates us to explore other compression methods beyond pruning. With two decoupled computation stages, we found that kernel decomposition could potentially take the processing of the sparse pattern off from the critical path of inference and achieve a high compression ratio without enforcing the sparse patterns. To exploit these advantages, we propose ESCALATE, an algorithm-hardware co-design approach based on kernel decomposition. At algorithm level, ESCALATE reorganizes the two computation stages of the decomposed convolution to enable a stream processing of the intermediate feature map. We proposed a hybrid quantization to exploit the different reuse frequency of each part of the decomposed weight. At architecture level, ESCALATE proposes a novel ‘Basis-First’ dataflow and its corresponding microarchitecture design to maximize the benefits brought by the decomposed convolution. 
    more » « less
  2. ; ; (, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems)
    Graph neural networks (GNNs) have emerged as a powerful tool to process graph-based data in fields like communication networks, molecular interactions, chemistry, social networks, and neuroscience. GNNs are characterized by the ultra-sparse nature of their adjacency matrix that necessitates the development of dedicated hardware beyond general-purpose sparse matrix multipliers. While there has been extensive research on designing dedicated hardware accelerators for GNNs, few have extensively explored the impact of the sparse storage format on the efficiency of the GNN accelerators. This paper proposes SCV-GNN with the novel sparse compressed vectors (SCV) format optimized for the aggregation operation. We use Z-Morton ordering to derive a data-locality-based computation ordering and partitioning scheme. The paper also presents how the proposed SCV-GNN is scalable on a vector processing system. Experimental results over various datasets show that the proposed method achieves a geometric mean speedup of 7.96× and 7.04× over CSC and CSR aggregation operations, respectively. The proposed method also reduces the memory traffic by a factor of 3.29× and 4.37× over compressed sparse column (CSC) and compressed sparse row (CSR), respectively. Thus, the proposed novel aggregation format reduces the latency and memory access for GNN inference. 
    more » « less
  3. ; ; ; ; (, ACM Transactions on Cyber-Physical Systems)
    null (Ed.)
    The invention of Transformer model structure boosts the performance of Neural Machine Translation (NMT) tasks to an unprecedented level. Many previous works have been done to make the Transformer model more execution-friendly on resource-constrained platforms. These researches can be categorized into three key fields: Model Pruning, Transfer Learning, and Efficient Transformer Variants. The family of model pruning methods are popular for their simplicity in practice and promising compression rate and have achieved great success in the field of convolution neural networks (CNNs) for many vision tasks. Nonetheless, previous Transformer pruning works did not perform a thorough model analysis and evaluation on each Transformer component on off-the-shelf mobile devices. In this work, we analyze and prune transformer models at the line-wise granularity and also implement our pruning method on real mobile platforms. We explore the properties of all Transformer components as well as their sparsity features, which are leveraged to guide Transformer model pruning. We name our whole Transformer analysis and pruning pipeline as TPrune. In TPrune, we first propose Block-wise Structured Sparsity Learning (BSSL) to analyze Transformer model property. Then, based on the characters derived from BSSL, we apply Structured Hoyer Square (SHS) to derive the final pruned models. Comparing with the state-of-the-art Transformer pruning methods, TPrune is able to achieve a higher model compression rate with less performance degradation. Experimental results show that our pruned models achieve 1.16×–1.92× speedup on mobile devices with 0%–8% BLEU score degradation compared with the original Transformer model. 
    more » « less
  4. ; ; ; ; (, ACM Transactions on Embedded Computing Systems)
    null (Ed.)
    PIM (processing-in-memory) based hardware accelerators have shown great potentials in addressing the computation and memory access intensity of modern CNNs (convolutional neural networks). While adopting NVM (non-volatile memory) helps to further mitigate the storage and energy consumption overhead, adopting quantization, e.g., shift-based quantization, helps to tradeoff the computation overhead and the accuracy loss, integrating both NVM and quantization in hardware accelerators leads to sub-optimal acceleration. In this paper, we exploit the natural shift property of DWM (domain wall memory) to devise DWMAcc, a DWM-based accelerator with asymmetrical storage of weight and input data, to speed up the inference phase of shift-based CNNs. DWMAcc supports flexible shift operations to enable fast processing with low performance and area overhead. We then optimize it with zero-sharing , input-reuse , and weight-share schemes. Our experimental results show that, on average, DWMAcc achieves 16.6× performance improvement and 85.6× energy consumption reduction over a state-of-the-art SRAM based design. 
    more » « less
  5. ; ; ; ; (, IEEE International Symposium on High Performance Computer Architecture (HPCA))
    Graph processing recently received intensive interests in light of a wide range of needs to understand relationships. It is well-known for the poor locality and high memory bandwidth requirement. In conventional architectures, they incur a significant amount of data movements and energy consumption which motivates several hardware graph processing accelerators. The current graph processing accelerators rely on memory access optimizations or placing computation logics close to memory. Distinct from all existing approaches, we leverage an emerging memory technology to accelerate graph processing with analog computation. This paper presents GRAPHR, the first ReRAM-based graph processing accelerator. GRAPHR follows the principle of near-data processing and explores the opportunity of performing massive parallel analog operations with low hardware and energy cost. The analog computation is suitable for graph processing because: 1) The algorithms are iterative and could inherently tolerate the imprecision; 2) Both probability calculation (e.g., PageRank and Collaborative Filtering) and typical graph algorithms involving integers (e.g., BFS/SSSP) are resilient to errors. The key insight of GRAPHR is that if a vertex program of a graph algorithm can be expressed in sparse matrix vector multiplication (SpMV), it can be efficiently performed by ReRAM crossbar. We show that this assumption is generally true for a large set of graph algorithms. GRAPHR is a novel accelerator architecture consisting of two components: memory ReRAM and graph engine (GE). The core graph computations are performed in sparse matrix format in GEs (ReRAM crossbars). The vector/matrix-based graph computation is not new, but ReRAM offers the unique opportunity to realize the massive parallelism with unprecedented energy efficiency and low hardware cost. With small subgraphs processed by GEs, the gain of performing parallel operations overshadows the wastes due to sparsity. The experiment results show that GRAPHR achieves a 16.01X (up to 132.67X) speedup and a 33.82X energy saving on geometric mean compared to a CPU baseline system. Compared to GPU, GRAPHR achieves 1.69X to 2.19X speedup and consumes 4.77X to 8.91X less energy. GRAPHR gains a speedup of 1.16X to 4.12X, and is 3.67X to 10.96X more energy efficiency compared to PIM-based architecture. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email