30 April 2024 in IEEE Transactions on Parallel and Distributed Systems
Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the neighboring feature vectors for each vertex in each semantic graph and then fuse the aggregated results across all semantic graphs for each vertex. Unfortunately, existing graph neural network accelerators are ill-suited to accelerate HGNNs. This is because they fail to efficiently tackle the specific execution patterns and exploit the high-degree parallelism as well as data reusability inside and across the processing of semantic graphs in HGNNs. In this work, we first quantitatively characterize a set of representative HGNN models on GPU to disclose the execution bound of each stage, inter-semantic-graph parallelism, and inter-semantic-graph data reusability in HGNNs. Guided by our findings, we propose a high-performance HGNN accelerator, HiHGNN, to alleviate the execution bound and exploit the newfound parallelism and data reusability in HGNNs. Specifically, we first propose a bound-aware stage-fusion methodology that tailors to HGNN acceleration, to fuse and pipeline the execution stages being aware of their execution bounds. Second, we design an independency-aware parallel execution design to exploit the inter-semantic-graph parallelism. Finally, we present a similarity-aware execution scheduling to exploit the inter-semantic-graph data reusability. Compared to the state-of-the-art software framework running on NVIDIA GPU T4 and GPU A100, HiHGNN respectively achieves an average 40.0× and 8.3× speedup as well as 99.59% and 99.74% energy reduction with quintile the memory bandwidth of GPU A100.
1 October 2006 in 2006 International Conference on Computer Design
This paper introduces the microarchitecture and logical implementation of SMT (Simultaneous Multithreading) improvement of Godson-2 processor which is a 64-bit, four-issue, out-of-order execution high performance processor. The condition for implementing correct memory consistency model in Godson-2 SMT processor is studied and a new register-level sharing and synchronization scheme is proposed. Godson-2 SMT processor has been implemented at the RTL level and simulated with the VstationPro of Mentor Graphics. The Linux operating system is ported to run in Godson-2 SMT processor and application programs such as SPEC CPU2000 benchmark suite are used to evaluate performance. Experimental results indicate that the performance of Godson-2 SMT processor is improved significantly by fully exploiting thread-level parallelism and optimized utilization of functional units. The average speedup is 31.3% with 18.8% area overhead.
30 July 2022 in Journal of Computer Science and Technology
27 February 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Heterogeneous Graph Neural Networks (HGNNs) have expanded graph representation learning to heterogeneous graph fields. Recent studies have demonstrated their superior performance across various applications, including circuit representation, chip design automation, and placement optimization, often surpassing existing methods. However, GPUs often experience inefficiencies when executing HGNNs due to their unique and complex execution patterns. Compared to traditional Graph Neural Networks, these patterns further exacerbate irregularities in memory access. To tackle these challenges, recent studies have focused on developing domain-specific accelerators for HGNNs. Nonetheless, most of these efforts have concentrated on optimizing the datapath or scheduling data accesses, while largely overlooking the potential benefits that could be gained from leveraging the inherent properties of the semantic graph, such as its topology, layout, and generation. In this work, we focus on leveraging the properties of semantic graphs to enhance HGNN performance. First, we analyze the Semantic Graph Build (SGB) stage and identify significant opportunities for data reuse during semantic graph generation. Next, we uncover the phenomenon of buffer thrashing during the Graph Feature Processing (GFP) stage, revealing potential optimization opportunities in semantic graph layout. Furthermore, we propose a lightweight hardware accelerator frontend for HGNNs, called SiHGNN. This accelerator frontend incorporates a tree-based Semantic Graph Builder for efficient semantic graph generation and features a novel Graph Restructurer for optimizing semantic graph layouts. Experimental results show that SiHGNN enables the state-of-the-art HGNN accelerator to achieve an average performance improvement of 2.95×.
14 July 2025 in ACM Transactions on Embedded Computing Systems
In embedded systems, particularly resource-constrained Internet of Things (IoT) devices, the SM2 Digital Signature Algorithm (SM2-DSA) standard is widely deployed for cryptographic security. While fault injection attacks can compromise digital signatures and extract private keys without physical damage, traditional approaches require precise temporal or spatial control, resulting in limited success rates and revealing insufficient research into the potential vulnerabilities of SM2-DSA. To address this issue, this article introduces a novel and efficient lattice-based fault attack method targeting SM2-DSA. The method involves injecting faults into the nonce before the fourth step of the signature operation. By leveraging both the correct and erroneous intermediate values of Q obtained from the signature and verification processes, we can deduce partial bits of the nonce. Following this, we construct a lattice attack to recover the private key. Additionally, we establish the theoretical security boundary for lattice attack against SM2-DSA. Building upon the boundary, we propose an efficient implementation scheme for the attack. Experimental results demonstrate a 100% success rate over 1,000 trials, using 61 signatures with six known bits of nonces for 256-bit SM2-DSA, with each recovery process completed in under three seconds. Finally, we propose countermeasures against this attack. Our proposed attack reveals potential security vulnerabilities in SM2-DSA implementations, providing constructive guidance for enhancing algorithmic security measures and defensive countermeasures.