Diffusion planning is a promising method for learning high-performance policies from offline data. To avoid the impact of discrepancies between planning and reality on performance, previous works generate new plans at each time step. However, this incurs significant computational overhead and leads to lower decision frequencies, and frequent plan switching may also affect performance. In contrast, humans might create detailed short-term plans and more general, sometimes vague, long-term plans, and adjust them over time. Inspired by this, we propose the Temporal Diffusion Planner (TDP) which improves decision efficiency by distributing the denoising steps across the time dimension. TDP begins by generating an initial plan that becomes progressively more vague over time. At each subsequent time step, rather than generating an entirely new plan, TDP updates the previous one with a small number of denoising steps. This reduces the average number of denoising steps, improving decision efficiency. Additionally, we introduce an automated replanning mechanism to prevent significant deviations between the plan and reality. Experiments on D4RL show that, compared to previous works that generate new plans every time step, TDP significantly improves the decision-making frequency by 11-24.8 times while achieving higher or comparable performance.

Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstream Verilog code generation. We treat hardware code generation as a complex transformation from an open-ended natural language space to a domain-specific, highly constrained target space. To bridge this gap, we introduce Core Refined Understanding eXpression (CRUX), a structured intermediate space that captures the essential semantics of user intent while organizing the expression for precise Verilog code generation. We further design a two-stage training framework, comprising Joint Expression Modeling and Dual-Space Optimization, to enhance the quality of both CRUX and Verilog code. Experiments across multiple Verilog generation benchmarks demonstrate that our model, QiMeng-CRUX, achieves state-of-the-art performance among general models, particularly under challenging design tasks. Furthermore, the CRUX space proves transferable and beneficial when used as input prompts for other code models, highlighting its effectiveness in narrowing the gap between free-form natural language descriptions and precise Verilog generation.

Autoformalization aims to translate natural-language mathematical statements into a formal language. While LLMs have accelerated progress in this area, existing methods still suffer from low accuracy. We identify two key abilities for effective autoformalization: comprehensive mastery of formal-language domain knowledge, and reasoning capability of natural language problem understanding and informal-formal alignment. Without the former, a model cannot identify the correct formal objects; without the latter, it struggles to interpret real-world contexts and map them precisely into formal expressions. To address these gaps, we introduce ThinkingF, a data synthesis and training pipeline that improves both abilities. First, we construct two datasets: one by distilling and selecting large-scale examples rich in formal knowledge, and another by generating informal-to-formal reasoning trajectories guided by expert-designed templates. We then apply SFT and RLVR with these datasets to further fuse and refine the two abilities. The resulting 7B and 32B models exhibit both comprehensive formal knowledge and strong informal-to-formal reasoning. Notably, StepFun-Formalizer-32B achieves SOTA BEq@1 scores of 40.5% on FormalMATH-Lite and 26.7% on ProverBench, surpassing all prior general-purpose and specialized models.

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) can effectively reduce harmful responses from LLMs, they often require high-quality datasets and heavy computational overhead during model training. Another way to align language models is to modify the logit of tokens in model outputs without heavy training. Recent studies have shown that contrastive decoding can enhance the performance of language models by reducing the likelihood of confused tokens. However, these methods require the manual selection of contrastive models or instruction templates, limiting the degree of contrast. To this end, we propose Adversarial Contrastive Decoding (ACD), an optimization-based framework to generate two opposite soft system prompts, the Safeguarding Prompt (SP) and the Adversarial Prompt (AP), for prompt-based contrastive decoding. The SP aims to promote safer outputs while the AP aims to exploit the harmful parts of the model, providing a strong contrast to align the model with safety. ACD only needs to apply a lightweight prompt tuning on a rather small anchor dataset without training the target model. Experiments conducted on extensive models and benchmarks demonstrate that the proposed method achieves much better safety performance than previous model training-free decoding methods without sacrificing its original generation ability.

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fully Homomorphic Encryption (FHE) imposes substantial memory demands, presenting significant challenges for efficient hardware acceleration. Near-Memory Processing (NMP) has emerged as a promising architectural solution to alleviate the memory bottleneck. However, the irregular memory access patterns and flexible dataflows inherent to FHE limit the effectiveness of existing NMP accelerators, which fail to fully utilize the available near-memory bandwidth. In this work, we propose FlexMem, a near-memory accelerator featuring high-parallel computational units with varying memory access strides and interconnect topologies to effectively handle irregular memory access patterns. Furthermore, we design polynomialand ciphertext-level dataflows to efficiently utilize near-memory bandwidth under varying degrees of polynomial parallelism and enhance parallel performance. Experimental results demonstrate that FlexMem achieves $1.26 \times$ performance improvement over the state-of-the-art near-memory architectures in end-to-end benchmarks, with on average 95.7% of near-memory bandwidth utilization.

The rapid advancement of Large Language Models (LLMs) has established language as a core general-purpose cognitive substrate, driving the demand for specialized Language Processing Units (LPUs) tailored for LLM inference. To overcome the growing energy consumption of LLM inference systems, this paper proposes a Hardwired-Neurons Language Processing Unit (HNLPU), which physically hardwires LLM weight parameters into the computational fabric, achieving several orders of magnitude computational efficiency improvement by extreme specialization. However, a significant challenge still lies in the scale of modern LLMs. A straightforward hardwiring of GPT-OSS-120B would require fabricating photomask sets valued at over 6 billion dollars, rendering this straightforward solution economically impractical.

Recently, multi-bit slicing has emerged as a promising technique to improve the energy efficiency of charge-domain Compute-In-Memory (CIM) accelerators by reducing the number of Analog-to-Digital (A/D) conversions. However, multi-bit slicing requires shift-and-add operations to reconstruct outputs, which exponentially amplify errors and cause significant accuracy degradation. Existing works mainly rely on hardware-aware retraining or noise-suppression techniques, incurring considerable design or power overhead. Thus, multi-bit CIM designs often face the dilemma of trading off energy efficiency for error resilience. In this paper, we propose Cambricon-CIM, a charge-domain multi-bit CIM accelerator that achieves both high energy efficiency and strong error resilience, without requiring retraining. The core insight is that the error amplification is proportional to digit weights; and by redefining these digit weights with smaller non-binary coding bases, it is possible to reduce the total error amplification. Leveraging this principle, CambriconCIM dynamically selects the minimal coding bases for every analog dot-product. With novel circuit and architectural support, Cambricon-CIM enables fast, low-overhead reconfiguration of coding bases at runtime. Experimental results show that Cambricon-CIM achieves 2.27× energy efficiency and 3.06× performance over RAELLA, a state-of-the-art error-resilient multi-bit slicing CIM architecture.

3D Gaussian Splatting (3DGS) is a breakthrough in 3D reconstruction using 3D Gaussians. However, even on highend GPUs like the NVIDIA A100, reconstructing complex scenes remains time-consuming, taking over 15 minutes. The main bottleneck is α-computation, which accounts for 71.25 % of training workload, yet 93.03 % of it is invalid due to the localized influence of Gaussians. To address this issue, we propose Cambricon-GS, an accelerator for 3DGS training with Gaussian-Pixel hybrid parallelism. At the software level, we introduce a hybrid parallel workflow that breaks the limitation of conventional pixel-only parallelism through two key techniques: Center-Pixel Gaussian Culling (CPGC), which eliminates invalid Gaussians early, and SeedDriven Gaussian Region Exploration (SDGRE), which reduces invalid computation for partially valid Gaussians by selectively exploring valid regions. Overall, the workflow significantly reduces α computations, lowering the workload to 17.99 %. At the hardware level, Cambricon-GS decouples α-computation and α blending into GUnits and PUnits, organized in a 2D mesh-based NoC that supports asynchronous execution and efficient data routing. We further boost performance via Gaussian/Pixel load balancing and tiled SSIM based pipelining. The evaluation results show that Cambricon-GS achieves 19.63×, 14.86×, 15.42×, 2.98× and 2.63× speedup, and 78.62×, 63.00×, 61.72×, 3.89× and 3.22× energy saving, compared to A100, GSCore, GBU, GSArch, and GauSPU, respectively, with negligible image quality loss.

Fully Homomorphic Encryption (FHE) enables encrypted data processing on untrusted cloud servers, crucial for privacy-sensitive applications. Despite its potential, performance overheads (about 10, 000× slower) limit adoption. ASIC accelerators outperform GPUs/FPGAs by optimizing specific operations but rely on costly 7nm processes and large on-chip memory, hindering cost-effective deployment. Balancing efficiency with manufacturing constraints remains critical. This paper presents TensorFHE+, a GPU-optimized FHE acceleration framework leveraging Tensor Cores to accelerate Number Theoretic Transform (NTT) operations. Key innovations include: 1) Decomposing CKKS kernels into vector/matrix operations for hardware utilization; 2) Vectorized modulo arithmetic; 3) Data layout optimization for memory efficiency. Evaluated on NVIDIA A100, TensorFHE+ outperforms TensorFHE [1] by 1.44× in average (up to 1.69× on ResNet-20) and surpasses prior GPU implementations [2], [3]. The design also demonstrates compatibility with commercial linear algebra accelerators, enabling efficient FHE deployment.

Customized processors are essential for domain-specific applications such as the Internet of Things (IoT) and multi-media embedded systems, yet their design often requires extensive expert intervention. Traditional approaches, including hardware design using encapsulated abstractions (e.g., Chisel) and high-level synthesis (HLS) from languages like C or SystemC, reduce some manual efforts but remain either costly or suboptimal. Recent explorations into leveraging Large Language Models (LLMs) to generate RTL from natural language specifications have shown promise, but these methods still struggle with generating complex and high-performance processors mainly due to the complicated low-level details in the RTL code. In this work, we introduce AGON, a novel framework designed to facilitate the development of customized processor RTL from instruction set architecture (ISA) documents using LLMs. The framework comprises two layers: a functional description layer and a hardware implementation layer. At the functional layer, AGON employs a nano-operator (nOP)-based Intermediate Representation (IR) that abstracts basic instruction operations, thereby reducing the semantic gap between natural language and RTL code. This abstraction significantly shortens the descriptive code required for LLM generation, improving the generation accuracy in single-pass. At the hardware layer, AGON offers three abstraction levels (i.e. instruction, ISA, and processor) along with rule-based primitives to systematically lower the nOP-based IR into a fully optimized processor implementation. This decoupled design not only ensures correctness-by-construction but also enables automated, PPA-aware performance optimization. We evaluate AGON by designing high-performance out-of-order processors that correctly execute practical programs. Experimental results demonstrate that processors generated with AGON achieve an average speedup of 4.51× on specific tasks compared to expert-designed general-purpose CPUs while requiring minimal design effort.

Diffusion Transformers (DiTs) have demonstrated remarkable success in text-to-video generation. However, the self-attention mechanism in DiTs imposes significant computational and memory burdens, particularly when handling long patch sequences like high-resolution or long-time videos. While sparse attention shows promise in reducing self-attention costs, existing approaches struggle to deliver performance gains due to the unique challenges in DiTs,i.e., varied sparse patterns across layers and timesteps, and the cumulative nature of inference errors over timesteps. In this paper, we propose DASA, an algorithm-hardware co-design that effectively addresses these challenges of attention sparsification in DiTs. Specifically, leveraging the insight that the generation quality is primarily influenced by overall distribution drift rather than changes in specific values, we introduce a novel Distribution-Aware Filtering (DAF) mechanism for sparsification. To further accelerate the process, we design a specialized Filtering Unit that enables fast candidate selection based on the proposed DAF mechanism. Experimental results show that DASA achieves 2.52× speed up compared to A100 GPU, and up to 1.22× speedup over state-of-the-art accelerators for self-attention computation.

The design flow of processors, particularly in hardware description languages (HDL) like Verilog and Chisel, is complex and costly. While recent advances in large language models (LLMs) have significantly improved coding tasks in software languages such as Python, their application in HDL generation remains limited due to the scarcity of high-quality HDL data. Traditional methods of adapting LLMs for hardware design rely on synthetic HDL datasets, which often suffer from low quality because even advanced LLMs like GPT perform poorly in the HDL domain. Moreover, these methods focus solely on chat tasks and the Verilog language, limiting their application scenarios. In this paper, we observe that: (1) HDL code collected from the real world is of higher quality than code generated by LLMs. (2) LLMs like GPT-3.5 excel in summarizing HDL code rather than generating it. (3) An explicit language tag can help LLMs better adapt to the target language when there is insufficient data. Based on these observations, we propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method. The pipeline enhances the generation of HDL code from natural language descriptions and enables the handling of various tasks such as chat and infilling incomplete code. Utilizing this pipeline, we introduce CodeV, a series of HDL generation LLMs. Among them, CodeV-All not only possesses a more diverse range of language abilities (Verilog and Chisel) and a broader scope of tasks (Chat and FIM), but also achieves performance on VerilogEval that is comparable to that of CodeV-Verilog fine-tuned on Verilog only, making them the first series of open-source LLMs designed for multi-scenario HDL generation. Code, models, and dataset: https://github.com/IPRC-DIP/CodeV.

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a data augmentation technique that uses a fine-tuned LLM to generate additional instructions of code responses from its own training dataset. The additional instruction-response pairs are added to the original dataset, and a stronger code LLM can be obtained by fine-tuning on the augmented dataset. We empirically validate Inverse-Instruct on a range of open-source code models (e.g. CodeLlama-Python and DeepSeek-Coder) and benchmarks (e.g., HumanEval(+), MBPP(+), DS-1000 and MultiPL-E), showing it consistently improves the base models.

Deep learning has achieved great success in numerous application areas at the cost of high computational complexity. To meet the ever-increasing computational demand, commodity hardware platforms (e.g., CPUs and GPUs) offer abundant computing resources including scalar, vector, and tensor units for deep learning that could execute in parallel. However, existing top-down tiling-based deep learning compilers often generate a homogeneous mapping from the given tensor computation task to hardware arithmetic instructions, failing to utilize different computing units simultaneously to achieve higher performance.

Graph Convolutional Neural Networks (GCNs) have gained widespread popularity in various fields like personal healthcare and financial systems, due to their remarkable performance. Despite the growing demand for cloud-based GCN services, privacy concerns over sensitive graph data remain significant. Homomorphic Encryption (HE) facilitates Privacy-Preserving Machine Learning (PPML) by allowing computations to be performed on encrypted data. However, HE introduces substantial computational overhead, particularly for GCN operations that require rotations and multiplications in matrix products. The sparsity of GCNs offers significant performance potential, but their irregularity introduces additional operations that reduce practical gains. In this paper, we propose FicGCN, a HE-based framework specifically designed to harness the sparse characteristics of GCNs and strike a globally optimal balance between aggregation and combination operations. FicGCN employs a latency-aware packing scheme, a Sparse Intra-Ciphertext Aggregation (SpIntra-CA) method to minimize rotation overhead, and a region-based data reordering driven by local adjacency structure. We evaluated FicGCN on several popular datasets, and the results show that FicGCN achieved the best performance across all tested datasets, with up to a $4.10\times$ improvement over the latest design.

Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an innovative memory system that integrates longterm and short-term memory modules, enhancing large language models (LLMs) for planning in embodied agents through memory-augmented prompting. Karma distinguishes between long-term and short-term memory, with long-term memory capturing comprehensive 3D scene graphs as representations of the environment, while short-term memory dynamically records changes in objects' positions and states. This dualmemory structure allows agents to retrieve relevant past scene experiences, thereby improving the accuracy and efficiency of task planning. Short-term memory employs strategies for effective and adaptive memory replacement, ensuring the retention of critical information while discarding less pertinent data. Compared to state-of-the-art embodied agents enhanced with memory, our memory-augmented embodied AI agent improves success rates by$1.3 \times$and$2.3 \times$in Composite Tasks and Complex Tasks within the AI2-THOR simulator, respectively, and enhances task execution efficiency by$3.4 \times$and$62.7 \times$. Furthermore, we demonstrate that KARMA's plug-and-play capability allows for seamless deployment on real-world robotic systems, such as mobile manipulation platforms. Through this plug-and-play memory system, KARMA significantly enhances the ability of embodied agents to generate coherent and contextually appropriate plans, making the execution of complex household tasks more efficient. Our code is available at https://github.com/WZX0Swarm0Robotics/KARMA/tree/master.

Automated processor design, which can significantly reduce human efforts and accelerate design cycles, has received considerable attention. While recent advancements have automatically designed single-cycle processors that execute one instruction per cycle, their performance cannot compete with modern superscalar processors that execute multiple instructions per cycle. Previous methods fail on superscalar processor design because they cannot address inter-instruction data dependencies, leading to inefficient sequential instruction execution. This paper proposes a novel approach to automatically designing superscalar processors using a hardware-friendly model called the Stateful Binary Speculation Diagram (State-BSD). We observe that processor parallelism can be enhanced through on-the-fly inter-instruction dependent data predictors, reusing the processor's internal states to learn the data dependency. To meet the challenge of both hardware-resource limitation and design functional correctness, State-BSD consists of two components: 1) a lightweight state-selector trained by simulated annealing method to detect the most reusable processor states and store them in a small buffer; and 2) a highly precise state-speculator trained by BSD expansion method to predict the inter-instruction dependent data using the selected states. It is the first work to achieve the automated superscalar processor design, i.e. QiMeng-CPU-v2, which improves the performance by about 380x than the state-of-the-art automated design and is comparable to human-designed superscalar processors such as ARM Cortex A53.

Neural Scene Representation (NSR) is a promising technique for representing real scenes.By learning from dozens of 2D photos captured from different viewpoints, NSR computes the 3D representation of real scenes.However, the performance of NSR processing running on GPU is insufficient for applications.Cambricon-R achieves high performance of more than 60 scenes per second, but at the cost of modeling quality.

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 72.59\% ($\uparrow 50.74\%$) for migration tasks.

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rewards hinders the preference optimization based on Reinforcement Learning (RL) for producing functionally correct Verilog code. In this paper, we propose Signal-Aware Learning for Verilog code generation (QiMeng-SALV) by leveraging code segments of functionally correct output signal to optimize RL training. Considering Verilog code specifies the structural interconnection of hardware gates and wires so that different output signals are independent, the key insight of QiMeng-SALV is to extract verified signal-aware implementations in partially incorrect modules, so as to enhance the extraction of meaningful functional rewards. Roughly, we verify the functional correctness of signals in generated module by comparing with that of reference module in the training data. Then abstract syntax tree (AST) is employed to identify signal-aware code segments which can provide meaningful functional rewards from erroneous modules. Finally, we introduce signal-aware DPO which is optimized on the correct signal-level code segments, thereby preventing noise and interference from incorrect signals. The proposed QiMeng-SALV underscores the paradigm shift from conventional module-level to fine-grained signal-level optimization in Verilog code generation, addressing the issue of insufficient functional rewards. Experiments demonstrate that our method achieves state-of-the-art performance on VerilogEval and RTLLM, with a 7B parameter model matching the performance of the DeepSeek v3 671B model and significantly outperforming the leading open-source model CodeV trained on the same dataset.

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code–NL–code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68.6 \% and 72.9 \% pass@1 on VerilogEval v2 and RTLLM v1.1, respectively, surpassing prior state-of-the-art by 12$\sim$20 \%, while even exceeding the performance of 671B DeepSeek-R1 on RTLLM. We have released our model, training code, and dataset to facilitate research in EDA and LLM communities.

The widespread adoption of deep learning accelerators (DLAs) underscores their pivotal role in improving the performance and energy efficiency of neural networks. To fully leverage the capabilities of these accelerators, exploration-based library generation approaches have been widely used to substantially reduce software development overhead. However, these approaches have been challenged by issues related to sub-optimal optimization results and excessive optimization overheads. In this paper, we proposeHeronto generate high-performance libraries of DLAs in an efficient and fast way. The key is automatically enforcing massive constraints through the entire program generation process and guiding the exploration with an accurate pre-trained cost model.Heronrepresents the search space as a constrained satisfaction problem (CSP) and explores the space via evolving the CSPs. Thus, the sophisticated constraints of the search space are strictly preserved during the entire exploration process. The exploration algorithm has the flexibility to engage in space exploration using either online-trained models or pre-trained models. Experimental results demonstrate thatHeronaveragely achieves 2.71$\times$speedup over three state-of-the-art automatic generation approaches. Also, compared to vendor-provided hand-tuned libraries,Heronachieves a 2.00$\times$speedup on average. When employing a pre-trained model,Heronachieves 11.6$\times$compilation time speedup, incurring a minor impact on execution time.

Due to the end of Moore’s Law and Dennard Scaling, Domain-Specific Accelerators (DSAs) have come to a Cambrian explosion. Especially when advancing into the intelligent era, more and more DSAs are integrated into System-on-Chips (SoCs) as intellectual property (IP) blocks to provide high performance and efficiency. Currently, IPs usually expose IP-dependent hardware interfaces, requiring SoCs to manage them as isolated devices with software running on the host CPU. However, such software-managed heterogeneity in CPU-centric SoCs leads to low IP utilization. This inefficiency arises from the dependence on software optimization, coupled with the control and data exchange overheads. To improve IP utilization of heterogeneous SoCs, in this article, we rearchitect the SoC as a processor (i.e., SaaP) to orchestrate hardware heterogeneity. SaaP features an orchestration pipeline where DSAs are integrated as execution units and managed directly by the hardware pipeline to conceal the hardware heterogeneity from software. Moreover, SaaP redesigns the register file and data paths to implement an IP-level data-forwarding mechanism, avoiding the costly control and data exchange in the CPU-centric execution model. Block data dependence among different DSAs is carefully resolved to exploit mixed-level parallelism and inter-IP data exchange. SaaP abstracts tasks as mixed-scale instructions, where each instruction can be mapped to different IPs. Experimental results show that compared against Xavier on six fully software-optimized benchmarks from different domains, SaaP-rearchitected Xavier achieves a$2.08{\times }$speedup, with an 8.21% area reduction and only 2.98% increase in power consumption.

Chiplet-based DNN accelerators have been extensively explored to save design and manufacturing costs. Previous works regard all chiplets as identical and employ uniform workload partitioning strategies. These workload partitioning strategies overlook various real-world factors that contribute to remarkable performance variations among chiplets, including manufacturing process variation, thermal condition, physical placement, and power supply condition. When considering these performance variations, a variation-aware workload partitioning can achieve superior performance. This paper introduces VariPar, a systematic framework to employ variation-aware partitioning strategy in chiplet-based DNN accelerators. VariPar models performance variations for each chiplet and partition workloads accordingly. VariPar includes a simulator with multi-factor variation modeling and a heuristic search engine to generate near-optimal partitioning within a reasonable time. Experiment results show that VariPar achieves 1.45× performance and 1.82× energy efficiency improvement on average when compared to uniform partitioning strategy.

Symbolic regression (SR), the process of formulating a mathematical expression based on observed data points, is a fundamental task in artificial intelligence but is often hindered by its intense computational demands. Deep-learning-based SR methods (DSR) aim to alleviate these demands by breaking down the SR process into two stages: 1) neural network (NN) inference and 2) Broyden-Fletcher–Goldfarb-Shanno (BFGS) optimization. Although NN accelerators can expedite the NN stage, the performance of the BFGS optimization is compromised due to its poor performance for the variety of transcendental functions. Moreover, the distinct computational characteristics of NN inference and BFGS cause not only low hardware utilization but also significant area waste. To address these issues, we propose Harmonia, a unified architecture with the neural transcendental function unit (NTFU) and the Unified Array for efficient DSR. The NTFU utilizes the radial basis function network (RBFN) as a universal approximator for various transcendental functions, which significantly reduces the heavy transcendental function computation cost. We further propose an efficient training algorithm called random nonlinear optimization (RNO) to obtain a lightweight RBFN without accuracy loss. Moreover, Harmonia supports configurable dataflow which integrates the two computing stages into the Unified Array. Experimental results show that Harmonia achieves hardware utilization of 83.83%, on average. Compared to the GPU baseline, Harmonia achieves$4.8\times $speedup and$47.6\times $energy saving, alongside considerable low area cost.

Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding problem still hinders the applications of LLMs in the real-world environment. Existing studies try to fine-tune the LLM or utilize pre-defined behavior APIs to bridge the LLMs and the environment, which not only costs huge human efforts to customize for every single task but also weakens the generality strengths of LLMs. To autonomously ground the LLM onto the environment, we proposed the Hypothesis, Verification, and Induction (HYVIN) framework to automatically and progressively ground the LLM with self-driven skill learning. HYVIN first employs the LLM to propose the hypothesis of sub-goals to achieve tasks and then verify the feasibility of the hypothesis via interacting with the underlying environment. Once verified, HYVIN can then learn generalized skills with the guidance of these successfully grounded subgoals. These skills can be further utilized to accomplish more complex tasks that fail to pass the verification phase. Verified in the famous instruction following task set, BabyAI, HYVIN achieves comparable performance in the most challenging tasks compared with imitation learning methods that cost millions of demonstrations, proving the effectiveness of learned skills and showing the feasibility and efficiency of our framework.

Heterogeneous collaborative computing with NPU and CPU has received widespread attention due to its substantial performance benefits. To ensure data confidentiality and integrity during computing, Trusted Execution Environments (TEE) is considered a promising solution because of its comparatively lower overhead. However, existing heterogeneous TEE designs are inefficient for collaborative computing due to fine and different memory granularities between CPU and NPU. 1) The cacheline granularity of CPU TEE intensifies memory pressure due to its extra memory access, and 2) the cacheline granularity MAC of NPU escalates the pressure on the limited memory storage. 3) Data transfer across heterogeneous enclaves relies on the transit of non-secure regions, resulting in cumbersome re-encryption and scheduling.

Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant personalized concepts onto the basic Stable Diffusion model with minimal computational costs on small datasets. However, these innovations have also given rise to issues like facial privacy forgery and artistic copyright infringement. In recent studies, researchers have explored the addition of imperceptible adversarial perturbations to images to prevent potential unauthorized exploitation and infringements when personal data is used for fine-tuning Stable Dif-fusion. Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios. In this paper, we systematically evaluate the use of perturbations to protect images within a practical threat model. The results suggest that these approaches may not be sufficient to safeguard image privacy and copyright effectively. Furthermore, we introduce a purification method capable of removing protected perturbations while preserving the original image structure to the greatest extent possible. Experiments reveal that Stable Diffusion can effectively learn from purified images over all protective methods1.

Pipelining is a widely applied micro-architectural performance optimization and requires non-trivial designs for better execution throughput. The key to pipeline throughput optimization is to resolve data hazards caused by read-after-write (RAW) dependencies, which are traditionally tackled by forwarding and speculation to avoid pipeline stalls. However, existing approaches are conducted based on high-level dataflow analysis, with potential loss of optimization opportunities for lack of analysis of the netlist structures.

The use of cross-scheme fully homomorphic encryption (FHE) in privacy-preserving applications present to be a new challenge to hardware accelerator design. Existing accelerator architectures with customized polynomial-level operator abstraction fail to efficiently handle hybrid FHE schemes due to the mismatch between computational demands and available hardware resources under various parameter settings. In this work, we propose a new accelerator architecture that consists of a novel finer-grained low-level operator, i.e., Meta-OP, that not only mathematically supports a diverse range of polynomial operations, but is also hardware-friendly for accelerator design without complex topological logic. We then design a new slot-based data management scheme to efficiently handle the distinct memory access patterns over the Meta-OP. With a slot-based data management approach, Alchemist can accelerate both arithmetic and logic FHE workloads with high hardware utilization rates. In the experiment, we show that Alchemist is up to 24,829X faster than CPU. For arithmetic FHE, compared with the SOTA ASIC accelerators, Alchemist achieves a 29.4X performance per area improvement on average. For logic FHE, compared with the SOTA ASIC accelerators, Alchemist achieves a 7.0X overall speed up on average.

Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain representation and resulting in performance degradation on unseen domains. Besides, abundant data from multiple domains are needed. To address these issues, in this work, we propose prompt-based visual alignment (PVA), a robust framework to mitigate the detrimental domain bias in the image for zero-shot policy transfer. Inspired that Visual-Language Model (VLM) can serve as a bridge to connect both text space and image space, we leverage the semantic information contained in a text sequence as an explicit constraint to train a visual aligner. Thus, the visual aligner can map images from multiple domains to a unified domain and achieve good generalization performance. To better depict semantic information, prompt tuning is applied to learn a sequence of learnable tokens. With explicit constraints of semantic information, PVA can learn unified cross-domain representation under limited access to cross-domain data and achieves great zero-shot generalization ability in unseen domains. We verify PVA on a vision-based autonomous driving task with CARLA simulator. Experiments show that the agent generalizes well on unseen domains under limited access to multi-domain data.

Diffusion models have made significant progress in current image generation tasks, thus becoming a prominent area of research. Diffusion models necessitate repetitive iterations on minimally altered input data across timesteps, each timestep requiring the recalculation of the entire model, resulting in a remarkable computational redundancy and substantial hardware expenditures.Performing differential computing on input data seems to be a feasible approach for addressing such computational redundancy and improving hardware efficacy. However, non-linear operations (particularly activation functions) necessitate the merging of deltas (i.e., differential values) with raw inputs repeatedly to ensure computational correctness, leading to significant memory access for loading raw inputs, which fragmentedly blocks the forwarding of deltas throughout the network and undermines performance.To solve this problem, we propose Cambricon-D, a fullnetwork differential computing architecture with concise memory access. While maintaining the computational efficiency brought by differential computing, Cambricon-D employs a sign-mask dataflow, which requires only the loading of 1-bit signs (instead of large bitwidth raw inputs), thereby facilitating the seamless forwarding of deltas and effectively mitigating memory access overheads. Experimental results show that, compared to Diffy, Cambricon-D’s dataflow reduces 66% ~ 82% off-chip memory access. In total, Cambricon-D achieves 1.46× ~ 2.38× speedup over A100 on various diffusion models with different resolutions.

Deep learning trends to use low precision numeral formats to cope with the ever-growing model sizes. For example, the large language model LLaMA2 has been widely deployed in 4-bit precision. With larger models and fewer unique values caused by low precision, an increasing proportion of arithmetic in matrix multiplication is repeating. Although discussed in prior works, such value redundancy has not been fully exploited, and the cost to leverage the value redundancy often offsets any advantages. In this paper, we propose to primitivize the matrix multiplication, that is decomposing it down to the 1-ary successor function (a.k.a. counting) to merge repeating arithmetic. We revisited various techniques to propose Cambricon-C SA, a 4-bit primitive matrix multiplication unit that doubles the energy efficiency over conventional systolic arrays. Experimental results show that Cambricon-C SA can achieve$\mathbf{1}.\mathbf{95}\times$energy efficiency improvement compared with MAC-based systolic array.

Charge-domain SRAM-based Computing-in-memory (CIM) proves to be a promising method for DNN inference, and benefits from avoiding data movement between computing units and memory. However, the high resolution Analog-to-Digital Converters (ADCs) dominates the energy consumption (up to 64%), limiting the energy efficiency of SRAM-CIM architectures. The main reason is the wide range of input analog values, requiring high resolution ADCs to convert the high precision averaged analog voltages into high bitwidth digital data. In this paper, to reduce the ADC overhead, we propose Cambricon-M, a novel Fibonacci-coded SRAM-based charge-domain CIM accelerator for DNN inference. Cambricon-M features the Fibonacci coding, which guarantees low density of ‘1’ in operands (i.e., the adjacent two bits of each ‘1’ are both ‘0’), narrowing the output voltage range and enabling low resolution ADCs. Further, Cambricon-M exploits the high bit-level sparsity to address the extra energy and area overhead caused by the larger bitwidth in Fibonacci coding. Specifically, Cambricon-M proposes zero-skipping methods to reduce ineffectual input/output, and the bit-slice based compression method to reduce memory capacity/bandwidth pressure. Experimental results show that Cambricon-M reduces ADC energy by 68.7%, and improves the energy efficiency 3.48× and 1.62× compared to TPUv4 and an ISAAC-based charge-domain SRAM-CIM accelerator.

Deploying advanced large language models on edge devices, such as smartphones and robotics, is a growing trend that enhances user data privacy and network connectivity resilience while preserving intelligent capabilities. However, such a task exhibits single-batch computing with incredibly low arithmetic intensity, which poses the significant challenges of huge memory footprint and bandwidth demands on limited edge resources. To address these issues, we introduce Cambricon-LLM, a chiplet-based hybrid architecture with NPU and a dedicated NAND flash chip to enable efficient on-device inference of 70B LLMs. Such a hybrid architecture utilizes both the high computing capability of NPU and the data capacity of the NAND flash chip, with the proposed hardware-tiling strategy that minimizes the data movement overhead between NPU and NAND flash chip. Specifically, the NAND flash chip, enhanced by our innovative in-flash computing and on-die ECC techniques, excels at performing precise lightweight on-die processing. Simultaneously, the NPU collaborates with the flash chip for matrix operations and handles special function computations beyond the flash's on-die processing capabilities. Overall, Cambricon-LLM enables the on-device inference of 70B LLMs at a speed of 3.44 token/s, and 7B LLMs at a speed of 36.34 token/s, which is over 22× to 45× faster than existing flash-offloading technologies, showing the potentiality of deploying powerful LLMs in edge devices.

DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision tasks because of its practicality, feasibility, and powerful attack effectiveness. This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust VOD. We observe that adversarial patches exhibit extremely localized superficial feature importance in a small region with nonrobust predictions, and thus propose the adversarial region detection algorithm for adversarial effect elimination. Themis also proposes a systematic design to efficiently support the algorithm by eliminating redundant computations and memory traffics. Experimental results show that the proposed methodology can effectively recover the system from the adversarial attack with negligible hardware overhead.

Symbolic regression, the task of extracting mathematical expressions from the observed data, plays a crucial role in scientific discovery. Despite the promising performance of existing methods, most of them conduct symbolic regression in an offline setting. That is, they treat the observed data points as given ones that are simply sampled from uniform distributions without exploring the expressive potential of data. However, for real-world scientific problems, the data used for symbolic regression are usually actively obtained by doing experiments, which is an online setting. Thus, how to obtain informative data that can facilitate the symbolic regression process is an important problem that remains challenging. In this paper, we propose QUOSR, a query-based framework for online symbolic regression that can automatically obtain informative data in an iterative manner. Specifically, at each step, QUOSR receives historical data points, generates new x, and then queries the symbolic expression to get the corresponding y, where the (x, y) serves as new data points. This process repeats until the maximum number of query steps is reached. To make the generated data points informative, we implement the framework with a neural network and train it by maximizing the mutual information between generated data points and the target expression. Through comprehensive experiments, we show that QUOSR can facilitate modern symbolic regression methods by generating informative data.

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across various environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes noisy or irrelevant information and cause spurious correlations that are dependent on instances, thus hurting generalization performance and training efficiency. To address the above issue, we propose a conceptual reinforcement learning (CRL) framework to learn the concept-like joint representation for language-conditioned policy. The key insight is that concepts are compact and invariant representations in human cognition through extracting similarities from numerous instances in real-world. In CRL, we propose a multi-level attention encoder and two mutual information constraints for learning compact and invariant concepts. Verified in two challenging environments, RTFM and Messenger, CRL significantly improves the training efficiency (up to 70%) and generalization ability (up to 30%) to the new environment dynamics.

Deep Learning Accelerators (DLAs) are effective to improve both performance and energy efficiency of compute-intensive deep learning algorithms. A flexible and portable mean to exploit DLAs is using high-performance software libraries with well-established APIs, which are typically either manually implemented or automatically generated by exploration-based compilation approaches. Though exploration-based approaches significantly reduce programming efforts, they fail to find optimal or near-optimal programs from a large but low-quality search space because the massive inherent constraints of DLAs cannot be accurately characterized.

Domain adaptation in RL mainly deals with the changes of observation when transferring the policy to a new environment. Many traditional approaches of domain adaptation in RL manage to learn a mapping function between the source and target domain in explicit or implicit ways. However, they typically require access to abundant data from the target domain. Besides, they often rely on visual clues to learn the mapping function and may fail when the source domain looks quite different from the target domain. To address these problems, in this paper, we propose a novel framework Online Prototype Alignment (OPA) to learn the mapping function based on the functional similarity of elements and is able to achieve few-shot policy transfer within only several episodes. The key insight of OPA is to introduce an exploration mechanism that can interact with the unseen elements of the target domain in an efficient and purposeful manner, and then connect them with the seen elements in the source domain according to their functionalities (instead of visual clues). Experimental results show that when the target domain looks visually different from the source domain, OPA can achieve better transfer performance even with much fewer samples from the target domain, outperforming prior methods.

Neural scene representation (NSR) initiates a new methodology of encoding a 3D scene with neural networks by learning from dozens of photos taken from different camera positions. NSR not only achieves significant improvement in the quality of novel view synthesis and 3D reconstruction but also reduces the camera cost from the expensive laser cameras to the cheap color cameras on the shelf. However, performing 3D scene encoding using NSR is far from real-time due to the extremely low hardware utilization (only utilization of hardware peak performance), which greatly limits its applications in real-time AR/VR interactions

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.

Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an efficient gradient-based learning method named Efficient Symbolic Policy Learning (ESPL) that learns the symbolic policy from scratch in an end-to-end way. We introduce a symbolic network as the search space and employ a path selector to find the compact symbolic policy. By doing so we represent the policy with a differentiable symbolic expression and train it in an off-policy manner which further improves the efficiency. In addition, in contrast with previous symbolic policies which only work in single-task RL because of complexity, we expand ESPL on meta-RL to generate symbolic policies for unseen tasks. Experimentally, we show that our approach generates symbolic policies with higher performance and greatly improves data efficiency for single-task RL. In meta-RL, we demonstrate that compared with neural network policies the proposed symbolic policy achieves higher performance and efficiency and shows the potential to be interpretable.

Though LLMs are capable of generating plausible programs, it’s challenging to interact with the LLMs further to revise the program, especially if the user’s specific requirements are different from the initial proposal. In this paper, we introduce ANPL, an interactive programming system that ensures users can always refine the generated code towards their specific programmatic intents via structured decompositions. Borrowing the paradigm of sketching from program synthesis, an ANPL program consists of a set of input-outputs that it must satisfy, a “sketch” — control/data flow expressed in precise code (e.g. Python), and “holes” — sub-modules to be implemented by the LLM specified with natural language. The user revises an ANPL program by either modifying the sketch, changing the language used to describe the holes, or providing additional input-outputs to a particular hole, turning it into a sub-ANPL program that can be solved recursively. This workflow allows the users to offload programming burdens to the LLM as much as possible while retaining the ability to pinpoint and resolve bugs locally, without exposing the rest of the program to the LLM. We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together. Additional evaluations on APPS, HumanEval, and real-world programming tasks have validated that the ANPL framework is applicable to multiple programming domains. We release the ANPL solutions to the ARC tasks as a dataset, providing insights into how humans decompose novel tasks programmatically.

In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has been widely adopted as a promising approach to prevent the negative transfer problem that performance degradation due to conflicts between tasks. However, most of the existing multi-task RL methods only combine shared modules at the task level, ignoring that there may be conflicts within the task. In addition, these methods do not take into account that without constraints, some modules may learn similar functions, resulting in restricting the model's expressiveness and generalization capability of modular methods. In this paper, we propose the Contrastive Modules with Temporal Attention(CMTA) method to address these limitations. CMTA constrains the modules to be different from each other by contrastive learning and combining shared modules at a finer granularity than the task level with temporal attention, alleviating the negative transfer within the task and improving the generalization ability and the performance for multi-task RL. We conducted the experiment on Meta-World, a multi-task RL benchmark containing various robotics manipulation tasks. Experimental results show that CMTA outperforms learning each task individually for the first time and achieves substantial performance improvements over the baselines.

In recent years, Multi-Agent Reinforcement Learning (MARL) techniques have made significant strides in achieving high asymptotic performance in single task. However, there has been limited exploration of model transferability across tasks. Training a model from scratch for each task can be time-consuming and expensive, especially for large-scale Multi-Agent Systems. Therefore, it is crucial to develop methods for generalizing the model across tasks. Considering that there exist task-independent subtasks across MARL tasks, a model that can decompose such subtasks from the source task could generalize to target tasks. However, ensuring true task-independence of subtasks poses a challenge. In this paper, we propose to \textbf{d}ecompose a \textbf{t}ask in\textbf{to} a series of \textbf{g}eneralizable \textbf{s}ubtasks (DT2GS), a novel framework that addresses this challenge by utilizing a scalable subtask encoder and an adaptive subtask semantic module. We show that these components endow subtasks with two properties critical for task-independence: avoiding overfitting to the source task and maintaining consistent yet scalable semantics across tasks. Empirical results demonstrate that DT2GS possesses sound zero-shot generalization capability across tasks, exhibits sufficient transferability, and outperforms existing methods in both multi-task and single-task problems.

As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency. Model compression has been proposed as a promising technique to improve the running efficiency via parameter and operation reduction, whereas this technique is mainly practiced in ANNs rather than SNNs. It is interesting to answer how much an SNN model can be compressed without compromising its functionality, where two challenges should be addressed: 1) the accuracy of SNNs is usually sensitive to model compression, which requires an accurate compression methodology and 2) the computation of SNNs is event-driven rather than static, which produces an extra compression dimension on dynamic spikes. To this end, we realize a comprehensive SNN compression through three steps. First, we formulate the connection pruning and weight quantization as a constrained optimization problem. Second, we combine spatiotemporal backpropagation (STBP) and alternating direction method of multipliers (ADMMs) to solve the problem with minimum accuracy loss. Third, we further propose activity regularization to reduce the spike events for fewer active operations. These methods can be applied in either a single way for moderate compression or a joint way for aggressive compression. We define several quantitative metrics to evaluate the compression performance for SNNs. Our methodology is validated in pattern recognition tasks over MNIST, N-MNIST, CIFAR10, and CIFAR100 datasets, where extensive comparisons, analyses, and insights are provided. To the best of our knowledge, this is the first work that studies SNN compression in a comprehensive manner by exploiting all compressible components and achieves better results.

Spiking neural network (SNN) is broadly deployed in neuromorphic devices to emulate brain function. In this context, SNN security becomes important while lacking in-depth investigation. To this end, we target the adversarial attack against SNNs and identify several challenges distinct from the artificial neural network (ANN) attack: 1) current adversarial attack is mainly based on gradient information that presents in a spatiotemporal pattern in SNNs, hard to obtain with conventional backpropagation algorithms; 2) the continuous gradient of the input is incompatible with the binary spiking input during gradient accumulation, hindering the generation of spike-based adversarial examples; and 3) the input gradient can be all-zeros (i.e., vanishing) sometimes due to the zero-dominant derivative of the firing function. Recently, backpropagation through time (BPTT)-inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given spatiotemporal gradient maps. We propose two approaches to address the above challenges of gradient-input incompatibility and gradient vanishing. Specifically, we design a gradient-to-spike (G2S) converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a restricted spike flipper (RSF) to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all-zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer on the attack effectiveness. Extensive experiments are conducted to validate our solution. Besides the quantitative analysis of the influence factors, we also compare SNNs and ANNs against adversarial attacks under different attack methods. This work can help reveal what happens in SNN attacks and might stimulate more research on the security of SNN models and neuromorphic devices.

GPUs have become the dominant computing platforms for many applications, while programming GPUs with the widely-used CUDA parallel programming model is difficult. As sequential C code is relatively easy to obtain either from legacy repositories or by manual implementation, automatically translating C to its parallel CUDA counterpart is promising to relieve the burden of GPU programming. However, because of huge differences between the sequential C and the parallel CUDA programming model, existing approaches fail to conduct the challenging auto-parallelized program translation. In this paper, we propose a learning-based framework, i.e., BabelTower, to address this problem. We first create a large-scale dataset consisting of compute-intensive function-level monolingual corpora. We further propose using back-translation with a discriminative reranker to cope with unpaired corpora and parallel semantic conversion. Experimental results show that BabelTower outperforms state-of-the-art by 1.79, 6.09, and 9.39 in terms of BLEU, CodeBLEU, and specifically designed ParaBLEU, respectively. The CUDA code generated by BabelTower attains a speedup of up to 347x over the sequential C code, and the developer productivity is improved by at most 3.8x.

Arbitrary precision computing (APC), where the digits vary from tens to millions of bits, is fundamental for scientific applications, such as mathematics, physics, chemistry, and biology. APC on existing platforms (e.g., CPUs and GPUs) is achieved by decomposing the original data into small pieces to accommodate to the low-bitwidth (e.g., 32-/64-bit) functional units. However, such fine-grained decomposition inevitably introduces large amounts of intermediates, bringing in intensive on-chip data traffic and long, complex dependency chains, so that causing low hardware utilization.To address this issue, we propose Cambricon-P, a bitflow architecture supporting monolithic large and flexible bitwidth operations for efficient APC processing, which avoids generating large amounts of intermediates from decomposition. Cambricon- P features a tightly-integrated computational architecture for processing different bitflows in parallel, where full bit-serial data paths are deployed. The bit-serial scheme still needs to eliminate the dependency chain of APC for exploiting parallelism within one monolithic large-bitwidth operation. For this purpose, Cambricon-P adopts a carry parallel computing mechanism, which enables recursively transforming the multiplication into smaller inner-products that can be performed in parallel between bit-indexed IPUs (Inner-Product Units). Furthermore, to improve the computing efficiency of APC, Cambricon- P employs a bit-indexed inner-product processing scheme, namely BIPS, to eliminate intra-IPU bit-level redundancy. Compared to Intel Xeon 6134 CPU, Cambricon-P achieves 100.98$\times$ performance on monolithic long multiplication, and 23.41$\times$/30.16$\times$ speedup and energy benefit over four real-world APC applications on average. Compared to NVidia V100 GPU, Cambricon-P also delivers the same throughput, as well as 430$\times$/60.5$\times$ lesser area and power, respectively, on batch-processing multiplications.

As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention.Currently, researchers have already demonstrated an SNN can be attacked with adversarial examples. How to build a robust SNN becomes an urgent issue.Recently, many studies apply certified training in artificial neural networks (ANNs), which can improve the robustness of an NN model promisely. However, existing certifications cannot transfer to SNNs directly because of the distinct neuron behavior and input formats for SNNs. In this work, we first design S-IBP and S-CROWN that tackle the non-linear functions in SNNs' neuron modeling. Then, we formalize the boundaries for both digital and spike inputs. Finally, we demonstrate the efficiency of our proposed robust training method in different datasets and model architectures. Based on our experiment, we can achieve a maximum $37.7\%$ attack error reduction with $3.7\%$ original accuracy loss. To the best of our knowledge, this is the first analysis on robust training of SNNs.

Hierarchical reinforcement learning (HRL) has been proven to be effective for tasks with sparse rewards, for it can improve the agent's exploration efficiency by discovering high-quality hierarchical structures (e.g., subgoals or options). However, automatically discovering high-quality hierarchical structures is still a great challenge. Previous HRL methods can only find the hierarchical structures in simple environments, as they are mainly achieved through the randomness of agent's policies during exploration. In complicated environments, such a randomness-driven exploration paradigm can hardly discover high-quality hierarchical structures because of the low exploration efficiency. In this paper, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, to build high-quality hierarchical structures efficiently in complicated environments. The key insight is that the causalities among environment variables are naturally fit for modeling reachable subgoals and their dependencies; thus, the causality is suitable to be the guidance in building high-quality hierarchical structures. Roughly, we build the hierarchy of subgoals based on causality autonomously, and utilize the subgoal-based policies to unfold further causality efficiently. Therefore, CDHRL leverages a causality-driven discovery instead of a randomness-driven exploration for high-quality hierarchical structure construction. The results in two complex environments, 2D-Minecraft and Eden, show that CDHRL can discover high-quality hierarchical structures and significantly enhance exploration efficiency.

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on learning the object representations and then solving tasks via reasoning based on these object representations. However, none of these works tries to explicitly model the inherent similarity between different object instances of the same category. Objects of the same category should share similar functionalities; therefore, the category is the most critical property of an object. Following this insight, we propose a novel framework named Object-Category Aware Reinforcement Learning (OCARL), which utilizes the category information of objects to facilitate both perception and reasoning. OCARL consists of three parts: (1) Category-Aware Unsupervised Object Discovery (UOD), which discovers the objects as well as their corresponding categories; (2) Object-Category Aware Perception, which encodes the category information and is also robust to the incompleteness of (1) at the same time; (3) Object-Centric Modular Reasoning, which adopts multiple independent and object-category-specific networks when reasoning based on objects. Our experiments show that OCARL can improve both the sample efficiency and generalization in the OORL domain.

As deep neural networks (DNNs) continue to find applications in ever more domains, the exact nature of the neural network architecture becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. While prior work has explored aspects of the risk associated with model leakage, exactly which parts of the model are most sensitive and how one infers the full architecture of the DNN when nothing is known about the structure a priori are problems that have been left unexplored. In this paper we address this gap, first by presenting a schema for reasoning about model leakage holistically, and then by proposing and quantitatively evaluating DeepSniffer, a novel learning-based model extraction framework that uses no prior knowledge of the victim model. DeepSniffer is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models and that the extracted models significantly improve attempts at crafting adversarial inputs. The DeepSniffer project has been released inhttps://github.com/xinghu7788/DeepSniffer.

Machine Learning Computers (MLCs) with tensor functional units (e.g., NVIDIA's Tensor Core, Google's TPU and Habana's Tensor Processor Core) have emerged significantly over recent years. The broad diversity of MLCs makes it hard to deploy machine learning workloads with optimized performance. Though deep learning compilers (e.g., TVM) are effective to produce optimized code for different hardware back-ends, when deploying to a new MLC, it is tedious to implement platform-specific compilation optimizations by thoroughly understanding system/architectural details. To address this problem, we propose a holistic approach to achieve one-size-fits-all compilation optimization across different MLCs or inference. The key observation is that diverse MLCs share multiple key architectural characteristics for tensor processing, which can be generalized for conducting cross-platform compilation optimizations. Concretely, we propose the Tensor Abstract Machine (TAM), which features such common architectural characteristics, as the abstraction of a broad range of MLCs. To leverage architectural characteristics of the TAM, we propose the Tensor Scheduling Language (TSL) consisting of tensor computation description and tensor scheduling primitives for implementing operations with portable optimization. Experimental results demonstrate that the code generated from the same optimization schedule achieves 1.05x to 2.05x better performance than hand-tuned libraries and deep learning compilers across different platforms.

The graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs. However, learning from graphs is nontrivial because of its mixed computation model involving both graph analytics and neural network computing. To this end, we decompose the GCN learning into two hierarchical paradigms: 1) graph-level and 2) node-level computing. Such a hierarchical paradigm facilitates the software and hardware accelerations for GCN learning. We propose a lightweight graph reordering methodology, incorporated with a GCN accelerator architecture that equips a customized cache design to fully utilize the graph-level data reuse. We also propose a mapping methodology aware of data reuse and task-level parallelism to handle various graphs inputs effectively. The results show that Rubik accelerator design improves energy efficiency by$26.3\times $–$1375.2\times $than GPU platforms across different datasets and GCN models.

Graph neural networks (GNNs), which extend traditional neural networks for processing graph-structured data, have been widely used in many fields. The GNN computation mainly consists of theedge processingto generate messages by combining the edge/vertex features and thevertex processingto update the vertex features with aggregated messages. In addition to nontrivial vector operations in the edge processing, huge random accesses and neural network operations in the vertex processing, the graph topology of GNNs may also vary during the computation (i.e., dynamic GNNs). The above characteristics pose significant challenges on existing architectures. In this article, we propose a novel accelerator named CAMBRICON-G for efficient processing of both dynamic and static GNNs. The key of CAMBRICON-G is to abstract the irregular computation of a broad range of GNN variants to the process of regularly tiledadjacent cuboid(which extends the traditional adjacent matrix of graph by adding the dimension of vertex features). The intuition is that the adjacent cuboid facilitates exploitation of both data locality and parallelism by offeringmultidimensional multilevel tiling(including spatial and temporal tiling) opportunities. To perform themultidimensional spatial tiling, the CAMBRICON-G architecture mainly consists of the cuboid engine (CE) and hybrid on-chip memory. The CE has multiple vertex processing units (VPUs) working in a coordinated manner to efficiently process the sparse data and dynamically update the graph topology with dedicated instructions. The hybrid on-chip memory contains the topology-aware cache and multiple scratchpad memory to reduce off-chip memory access. To perform themultidimensional temporal tiling, an easy-to-use programming model is provided to flexibly explore different tiling options for large graphs. Experimental results show that compared against Nvidia P100 GPU, the performance and energy efficiency can be improved by$7.14\times $and$20.18\times $, respectively, on various GNNs, which validates both the versatility and energy efficiency of CAMBRICON-G.

Deep learning (DL) accelerators suffer from a new security problem, i.e., being vulnerable to physical access based attacks. An adversary can easily obtain the entire neural network (NN) model by physically snooping the memory bus that connects the accelerator chip with DRAM memory. Therefore, memory encryption becomes important for DL accelerators to improve their security. Nevertheless, we observe that traditional memory encryption techniques that have been efficiently used in CPU systems cause significant performance degradation when directly used in DL accelerators, due to the big bandwidth gap between the memory bus and the encryption engine. To address this problem, our paper proposes SEAL, a Secure and Efficient Accelerator scheme for deep Learning to enhance the performance of encrypted DL accelerators by improving the data access bandwidth. Specifically, SEAL leverages a criticality-aware smart encryption scheme that identifies partial data having no impact on the security of NN models and allows them to bypass the encryption engine, thus reducing the amount of data to be encrypted without affecting security. Extensive experimental results demonstrate that, compared with existing memory encryption techniques, SEAL achieves 1.34 – 1.4× overall performance improvement.

Sparse matrix-vector multiplication (SpMV) is an important primitive across a wide range of application domains such as scientific computing and graph analytics. Due to its intrinsic memory-bound characteristics, the performance of SpMV on throughput-oriented architectures such as GPU is bounded by the limited bandwidth between processors and memory. Processing-in-memory (PIM) architectures, made feasible by advances in 3D stacking, provide new opportunities to utilize ultra-high bandwidth by integrating compute-logic into memory.In this paper, we develop an SpMV accelerator, named as SpaceA, based on PIM architectures. SpaceA integrates compute logic near memory banks to exploit bank-level bandwidth. SpaceA contains both hardware and data-mapping design features to alleviate irregular memory access patterns which hinder full utilization of high memory bandwidth. In terms of hardware design features, SpaceA consists of two unique features: (1) it utilizes the capability of outstanding memory requests to hide the memory access latency to data located in non-local memory banks; (2) it integrates Content Addressable Memory (CAM) at the bank level to exploit data reuse of the input vectors. In addition, we develop a mapping scheme that partitions the sparse matrix into different memory banks, to maximize the data locality of the input vector and to achieve workload balance among processing elements (PEs) near each bank. Overall, SpaceA together with the proposed mapping method achieves 13.54x speedup and 87.49% energy saving on average over the GPU baseline on SpMV computation. In addition to SpMV primitives, we conduct a case study on graph analytics to demonstrate the benefits of SpaceA for applications built on SpMV. Compared to Tesseract and GraphP, state-of-the-art graph accelerators, SpaceA obtains better performance due to its higher effective bandwidth provided by near-bank integration.

Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function becomes limited in stochastic dynamic environments, where the unexpected state dynamics and rewards will increase the variance. In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments. Particularly, to obtain an ideally unbiased gradient estimate, we propose an information-theoretic approach, which optimizes the embeddings of the future to be independent of previous actions. In our experiments, we apply the proposed hindsight value function in stochastic dynamic environments, including discrete-action environments and continuous-action environments. Compared with the standard state value function, the proposed hindsight value function consistently reduces the variance, stabilizes the training, and improves the eventual policy.

Deep neural network (DNN) training is notoriously time-consuming, and quantization is promising to improve the training efficiency with reduced bandwidth/storage requirements and computation costs. However, state-of-the-art quantized algorithms with negligible training accuracy loss, which require on-the-fly statistic-based quantization over a great amount of data (e.g., neurons and weights) and high-precision weight update, cannot be effectively deployed on existing DNN accelerators. To address this problem, we propose the first customized architecture for efficient quantized training with negligible accuracy loss, which is named as Cambricon-Q. Cambricon-Q features a hybrid architecture consisting of an ASIC acceleration core and a near-data-processing (NDP) engine. The acceleration core mainly targets at improving the efficiency of statistic-based quantization with specialized computing units for both statistical analysis (e.g., determining maximum) and data reformating, while the NDP engine avoids transferring the high-precision weights from the off-chip memory to the acceleration core. Experimental results show that on the evaluated benchmarks, Cambricon-Q improves the energy efficiency of DNN training by 6.41× and 1.62×, performance by 4.20× and 1.70× compared to GPU and TPU, respectively, with only ⩽ 0.4% accuracy degradation compared with full precision training.

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10 datasets, but achieve very poor certified accuracy on higher-resolution images like ImageNet. It is urgent to design both robust and effective defenses against such a practical and harmful attack in industry-level larger images. In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. The basic insight of our work is that the adversarial patch intends to leverage localized superficial important neurons (SIN) to manipulate the prediction results. Hence, we leverage the SIN-based DNN compression techniques to significantly improve the certified accuracy, by reducing the adversarial region searching overhead and filtering the prediction noises. Our experimental results show that the certified accuracy is increased from 36.3% (the state-of-the-art certified detection) to 60.4%on the ImageNet dataset, largely pushing the certified defenses for practical use.

Deep neural network (DNN) accelerators are widely deployed in computer vision, speech recognition, and machine translation applications, in which attacks on DNNs have become a growing concern. This article focuses on exploring the implications of hardware Trojan attacks on DNNs. Trojans are one of the most challenging threat models in hardware security where adversaries insert malicious modifications to the original integrated circuits (ICs), leading to malfunction once being triggered. Such attacks can be conducted by adversaries because modern ICs commonly include third-party intellectual property (IP) blocks. Previous studies design hardware Trojans to attack DNNs with the assumption that adversaries have full knowledge or manipulation of the DNN systems' victim model and toolchain in addition to the hardware platforms, yet such a threat model is strict, limiting their practical adoption. In this article, we propose a memory Trojan methodology that implants the malicious logics merely into the memory controllers of DNN systems without the necessity of toolchain manipulation or accessing to the victim model and thus is feasible for practical uses. Specifically, we locate the input image data among the massive volume of memory traffics based on memory access patterns and propose a Trojan trigger mechanism based on detecting the geometric feature in input images. Extensive experiments show that the proposed trigger mechanism is effective even in the presence of environmental noises and preprocessing operations. Furthermore, we design and implement the payload and verify that the proposed Trojan technique can effectively conduct both untargeted and targeted attacks on DNNs.

Emerging resistive random access memory (RRAM) has shown the great potential of in-memory processing capability, and thus attracts considerable research interests in accelerating memory-intensive applications, such as neural networks (NNs). However, the accuracy of RRAM-based NN computing can degrade significantly, due to the intrinsic statistical variations of the resistance of RRAM cells. In this article, we propose SIGHT, a synergistic algorithm-architecture fault-tolerant framework, to holistically address this issue. Specifically, we consider three major types of faults for RRAM computing: 1) nonlinear resistance distribution; 2) static variation; and 3) dynamic variation. From the algorithm level, we propose a resistance-aware quantization to compel the NN parameters to follow the exact nonlinear resistance distribution as RRAM, and introduce an input regulation technique to compensate for RRAM variations. We also propose a selective weight refreshing scheme to address the dynamic variation issue that occurs at runtime. From the architecture level, we propose ageneralandlow-costarchitecture accordingly for supporting our fault-tolerant scheme. Our evaluation demonstrates almost no accuracy loss for our three fault-tolerant algorithms, and the proposed SIGHT architecture incurs performance overhead as little as 7.14%.

Deep neural networks (DNNs) thrive in recent years, wherein batch normalization (BN) plays an indispensable role. However, it has been observed that BN is costly due to the huge reduction and elementwise operations that are hard to be executed in parallel, which heavily reduces the training speed. To address this issue, in this article, we propose a methodology to alleviate the BN's cost by using only a few sampled or generated data for mean and variance estimation at each iteration. The key challenge to reach this goal is how to achieve a satisfactory balance between normalization effectiveness and execution efficiency. We identify that the effectiveness expects less data correlation in sampling while the efficiency expects more regular execution patterns. To this end, we design two categories of approach: sampling or creating a few uncorrelated data for statistics' estimation with certain strategy constraints. The former includes "batch sampling (BS)" that randomly selects a few samples from each batch and "feature sampling (FS)" that randomly selects a small patch from each feature map of all samples, and the latter is "virtual data set normalization (VDN)" that generates a few synthetic random samples to directly create uncorrelated data for statistics' estimation. Accordingly, multiway strategies are designed to reduce the data correlation for accurate estimation and optimize the execution pattern for running acceleration in the meantime. The proposed methods are comprehensively evaluated on various DNN models, where the loss of model accuracy and the convergence rate are negligible. Without the support of any specialized libraries, 1.98× BN layer acceleration and 23.2% overall training speedup can be practically achieved on modern GPUs. Furthermore, our methods demonstrate powerful performance when solving the well-known "micro-BN" problem in the case of a tiny batch size. This article provides a promising solution for the efficient training of high-performance DNNs.

As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. Previous studies explore to leverage architecture-level events disposed in hardware platforms to extract the model architecture information. They pose the following limitations: requiring a priori knowledge of victim models, lacking in robustness and generality, or obtaining incomplete information of the victim model architecture.

Inspired by the great success of neural networks, graph convolutional neural networks (GCNs) are proposed to analyze graph data. GCNs mainly include two phases with distinct execution patterns. The Aggregation phase, behaves as graph processing, showing a dynamic and irregular execution pattern. The Combination phase, acts more like the neural networks, presenting a static and regular execution pattern. The hybrid execution patterns of GCNs require a design that alleviates irregularity and exploits regularity. Moreover, to achieve higher performance and energy efficiency, the design needs to leverage the high intra-vertex parallelism in Aggregation phase, the highly reusable inter-vertex data in Combination phase, and the opportunity to fuse phase-by-phase execution introduced by the new features of GCNs. However, existing architectures fail to address these demands. In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU. Guided by the characterization, we design a GCN accelerator, HyGCN, using a hybrid architecture to efficiently perform GCNs. Specifically, first, we build a new programming model to exploit the fine-grained parallelism for our hardware design. Second, we propose a hardware design with two efficient processing engines to alleviate the irregularity of Aggregation phase and leverage the regularity of Combination phase. Besides, these engines can exploit various parallelism and reuse highly reusable data efficiently. Third, we optimize the overall system via inter-engine pipeline for inter-phase fusion and priority-based off-chip memory access coordination to improve off-chip bandwidth utilization. Compared to the state-of-the-art software framework running on Intel Xeon CPU and NVIDIA V100 GPU, our work achieves on average 1509× speedup with 2500× energy reduction and average 6.5× speedup with 10× energy reduction, respectively.

Deep Neural Networks (DNNs) have been driving the mainstream of Machine Learning applications. However, deploying DNNs on modern hardware with stringent latency requirements and energy constraints is challenging because of the compute-intensive and memory-intensive execution patterns of various DNN models. We propose an algorithm-architecture co-design to boost DNN execution efficiency. Leveraging the noise resilience of nonlinear activation functions in DNNs, we propose dual-module processing that uses approximate modules learned from original DNN layers to compute insensitive activations. Therefore, we can save expensive computations and data accesses of unnecessary sensitive activations. We then design an Executor-Speculator dual-module architecture with support for balance execution and memory access reduction. With acceptable model inference quality degradation, our accelerator design can achieve 2.24x speedup and 1.97x energy efficiency improvement for compute-bound Convolutional Neural Networks (CNNs) and memory-bound Recurrent Neural Networks (RNNs).

With the rapid development of deep learning techniques, the security issue for Neural Network (NN) systems has emerged as an urgent and severe problem. Hardware Trojan attack is one of the threatens, which provides attackers backdoors to control the prediction results of NN systems. This paper proposes a sequence triggered hardware Trojan. Normal images but with specific sequence are used to trigger the hardware Trojan and let attackers fully control the prediction results. This kind of trigger is not only robust to image pre-processing, but also unrecognizable by human beings. In comparison with existing hardware Trojan design, it is more practical and less hardware overhead. The experiments on MNIST, CIFAR100, and ISLVRC show that the proposed hardware Trojan is rarely triggered in normal working status while the hardware cost is reduced by 19X.

The tremendous impact of deep learning algorithms over a wide range of application domains has encouraged a surge of neural network (NN) accelerator research. Facilitating the NN accelerator design calls for guidance from an evolving benchmark suite that incorporates emerging NN models. Nevertheless, existing NN benchmarks are not suitable for guiding NN accelerator designs. These benchmarks are either selected for general-purpose processors without considering unique characteristics of NN accelerators or lack quantitative analysis to guarantee their completeness during the benchmark construction, update, and customization. In light of the shortcomings of prior benchmarks, we propose a novel benchmarking methodology for NN accelerators with a quantitative analysis of application performance features and a comprehensive awareness of software-hardware co-design. Specifically, we decouple the benchmarking process into three stages: First, we characterize the NN workloads with quantitative metrics and select the representative applications for the benchmark suite to ensure diversity and completeness. Second, we refine the selected applications according to the customized model compression techniques provided by specific software-hardware co-design. Finally, we evaluate a variety of accelerator designs on the generated benchmark suite. To demonstrate the effectiveness of our benchmarking methodology, we conduct a case study of composing an NN benchmark from the TensorFlow Model Zoo and compress these selected models with various model compression techniques. Finally, we evaluate compressed models on various architectures, including GPU, Neurocube, DianNao, and Cambricon-X.

Crossbar architecture has been widely used in neural network (NN) accelerators, involving conventional and emerging devices. It performs well on the fully connected layer through efficient vector-matrix multiplication. Whereas, the advantages degrade on the convolutional layer with huge data reuse, since the execution speed and resource overhead are imbalanced when using existing fully unfolded or fully folded mapping strategy. To address this issue, we propose a novel semi-folded mapping (SemiMap) framework for implementing the convolution on crossbars. It simultaneously folds the physical resources along the row dimension of feature maps (FMs) and unfolds them along the column dimension. The former reduces the resource overhead, and the latter maintains the parallelism. An FM slicing scheme is further proposed to enable the processing of large-size image. Via our mapping framework, a row-by-row streaming pipeline for intraimage dataflow and periodical pipeline for interimage dataflow are easy to be obtained. To validate the idea, we build a many-crossbar architecture with several designs to guarantee the overall functionality and performance. Based on the measurement data of a fabricated chip, a mapping compiler and a cycle-accurate simulator are developed for the hardware simulation of large-scale networks. We evaluate the proposed SemiMap on various convolutional NNs across different network scale. ${>} 35 {\times }$ resource saving and several hundred times cycle reduction are demonstrated compared to the existing fully unfolded and fully folded strategies, respectively. This paper jumps out of the current extreme mapping schemes, and provides a balanced solution on how to efficiently deploy the computational graphs with data reuse on many-crossbar architecture.

Neural Network (NN) accelerators with emerging ReRAM (resistive random access memory) technologies have been investigated as one of the promising solutions to address the memory wall challenge, due to the unique capability of processing-in-memory within ReRAM-crossbar-based processing elements (PEs). However, the high efficiency and high density advantages of ReRAM have not been fully utilized due to the huge communication demands among PEs and the overhead of peripheral circuits. In this paper, we propose a full system stack solution, composed of a reconfigurable architecture design, Field Programmable Synapse Array (FPSA) and its software system including neural synthesizer, temporal-to-spatial mapper, and placement & routing. We highly leverage the software system to make the hardware design compact and efficient. To satisfy the high-performance communication demand, we optimize it with a reconfigurable routing architecture and the placement & routing tool. To improve the computational density, we greatly simplify the PE circuit with the spiking schema and then adopt neural synthesizer to enable the high density computation-resources to support different kinds of NN operations. In addition, we provide spiking memory blocks (SMBs) and configurable logic blocks (CLBs) in hardware and leverage the temporal-to-spatial mapper to utilize them to balance the storage and computation requirements of NN. Owing to the end-to-end software system, we can efficiently deploy existing deep neural networks to FPSA. Evaluations show that, compared to one of state-of-the-art ReRAM-based NN accelerators, PRIME, the computational density of FPSA improves by 31x; for representative NNs, its inference performance can achieve up to 1000x speedup.

Blockchain applications have shown huge potential in various domains. Proof of Work (PoW) is the key procedure in blockchain applications, which exhibits the memory-bound characteristic and hinders the performance improvement of blockchain accelerators. In order to mitigate the "memory wall" and improve the performance of memory-hard PoW accelerators, using Ethash as an example, we optimize the memory architecture from two perspectives: 1) Hiding memory latency. We propose specialized context switch design to overcome the uncertain cycles of repetitive memory requests. 2) Increasing memory bandwidth utilization. We introduce on-chip memory that stores a portion of the Ethash directed acyclic graph (DAG) for larger effective memory bandwidth, and further propose adopting embedded NOR flash to fulfill the role. Then, we conduct extensive experiments to explore the design space of our optimized memory architecture for Ethash, including number of hash cores, on-chip/off-chip memory technologies and specifications. Based on the design space exploration, we finally provide the guidance for designing the memory-bound PoW accelerator. The experiment results show that our optimized designs achieve 8.7% -- 55% higher hash rate and 17% -- 120% higher hash rate per Joule compared with the baseline design in different configurations.

Homomorphic encryption is a promising technology for enabling various privacy-preserving applications such as secure biomarker search. However, current implementations are not practical due to large performance overheads. A homomorphic encryption scheme has recently been proposed that allows bitwise comparison without the computationally-intensive multiplication and bootstrapping operations. Even so, this scheme still suffers from memory-bound performance bottleneck due to large ciphertext expansion. In this work, we propose HEGA, a near-data processing architecture that leverages this scheme with 3D-stacked memory to accelerate privacy-preserving biomarker search. We observe that homomorphic encryption-based search, like other emerging applications, can greatly benefit from the large throughput, capacity, and energy savings of 3D-stacked memory-based near-data processing architectures. Our near-data acceleration solution can speed up biomarker search by 6.3 × with 5.7× energy savings compared to an 8-core Intel Xeon processor.

Neural network accelerators are widely deployed in application systems for computer vision, speech recognition, and machine translation. Due to ubiquitous deployment of these systems, a strong incentive rises for adversaries to attack such artificial intelligence (AI) systems. Trojan is one of the most important attack models in hardware security domain. Hardware Trojans are malicious modifications to original ICs inserted by adversaries, which lead the system to malfunction after being triggered. The globalization of the semiconductor gives a chance for the adversary to conduct the hardware Trojan attacks.Previous works design Neural Network (NN) Trojans with access to the model, toolchain, and hardware platform. However, the threat model is impractical which hinders their real adoption. In this work, we propose a memory Trojan methodology without the help of toolchain manipulation and model parameter information. We first leverage the memory access patterns to identify the input image data. Then we propose a Trojan triggering method based on the dedicated input image other than the circuit events, which has better controllability. The triggering mechanism works well even with environment noise and preprocessing towards the original images. In the end, we implement and verify the effectiveness of accuracy degradation attack.

Resistive random access memory (ReRAM) demonstrates the great potential of in-memory processing for neural network (NN) acceleration. However, since the convolutional neural network (CNN) is widely known as compute-bound, current ReRAM-based accelerators are not able to support CNN efficiently. In this paper, we for the first time propose the CNN accelerator with Winograd's convolution on ReRAM (CNNWire), which minimizes the multiplications to enable fast and efficient CNN inference. We realize the convolution with Winograd Processing Element (WPE) based on convolutional tiles. Interconnections between WPEs are designed aiming to improve the data reuse. Finally, we introduce the full mapping flow to implement the Winograd convolution The results show that CNMWire gains 3.85x energy efficiency boosting and 3.24x speedup on average among different CNN benchmarks, compared with traditional GEMM based mapping.

Graph processing is an important analysis technique for a wide range of big data applications. The ability to explicitly represent relationships between entities gives graph analytics a significant performance advantage over traditional relational databases. However, at the microarchitecture level, performance is bounded by the inefficiencies in the memory subsystem for single-machine in-memory graph analytics. This paper consists of two contributions in which we analyze and optimize the memory hierarchy for graph processing workloads. First, we perform an in-depth data-type-aware characterization of graph processing workloads on a simulated multi-core architecture. We analyze 1) the memory-level parallelism in an out-of-order core and 2) the request reuse distance in the cache hierarchy. We find that the load-load dependency chains involving different application data types form the primary bottleneck in achieving a high memory-level parallelism. We also observe that different graph data types exhibit heterogeneous reuse distances. As a result, the private L2 cache has negligible contribution to performance, whereas the shared L3 cache shows higher performance sensitivity.

Deep neural network (DNN) has demonstrated promising performance in various machine learning tasks. Due to the privacy issue and the unpredictable transmission latency, inferring DNN models directly on edge devices trends the development of intelligent systems, like self-driving cars, smart Internet-of-Things (IoTs) and autonomous robotics. The on-device DNN model is obtained by expensive training via vast volumes of high-quality training data in the cloud datacenter, and then deployed into these devices, expecting it to work effectively at the edge. However, edge device always deals with low-quality images caused by compression or environmental noise pollutions. The well-trained model, though could work perfectly on the cloud, cannot adapt to these edge-specific conditions without remarkable accuracy drop. In this paper, we propose an automated strategy, called "AutoMask", to embrace effective machine learning and accelerate DNN inference on edge devices. AutoMask comprises end-to-end trainable software strategies and cost-effective hardware accelerator architecture to improve the adaptability of the device without compromising the constrained computation and storage resources. Extensive experiments, over ImageNet dataset and various state-of-the-art DNNs, show that AutoMask achieves significant inference acceleration and storage reduction while maintains comparable accuracy level on embedded Xilinx Z7020 FPGA, as well as NVIDIA Jetson TX2.

Domain-specific accelerators for graph analytics leverage a large on-chip memory in order to tackle the intensive random memory accesses, offering higher performance and energy efficiency than conventional architectures. However, limited by the inefficient usage of on-chip memory, current accelerators suffer from energy and performance bottlenecks due to the large amount of off-chip memory accesses. In this work, we introduce an online preprocessing step for the vertex-centric programming model based on our observation of imbalanced memory bandwidth utilization between two execution phases. Our scheme improves energy efficiency and performance by significantly reducing off-chip accesses in two ways. First, we sequence random off-chip memory accesses to balance memory bandwidth demands and improve the utilization of on-chip memory. Second, we prune active leaf vertices to avoid redundant memory accesses. We evaluate our method on a state-of-the-art graph analytics accelerator and achieve 1.6× speedup while reducing energy consumption by 42% on average.

Computational genomics has proven its great potential to support precise and customized health care. However, with the wide adoption of the Next Generation Sequencing (NGS) technology, 'DNA Alignment', as the crucial step in computational genomics, is becoming more and more challenging due to the booming bio-data. Consequently, various hardware approaches have been explored to accelerate DNA seeding - the core and most time consuming step in DNA alignment.

Graph analytics is an emerging application which extracts insights by processing large volumes of highly connected data, namely graphs. The parallel processing of graphs has been exploited at the algorithm level, which in turn incurs three irregularities onto computing and memory patterns that significantly hinder an efficient architecture design. Certain irregularities can be partially tackled by the prior domain-specific accelerator designs with well-designed scheduling of data access, while others remain unsolved.

Next Generation Sequencing (NGS) technology has become an indispensable tool for studying genomics, resulting in an exponentially growth of biological data. Booming data volume demands significant computational resources and creates challenges for 'Sequence Alignment', which is the most fundamental application in bioinformatics. Consequently, many researchers exploit both software and hardware methods to accelerate the most widely used sequence alignment algorithm - Basic Local Alignment Search Tool (BLAST). However, prior work suffers from moving huge DNA databases from the storage to computational units. Such data movement is both time and energy consuming.

Software testing is a widely used technique to ensure the quality of software systems. Code coverage measures are commonly used to evaluate and improve the existing test suites. Based on our industrial and open source studies, existing state-of-the-art code coverage tools are only used during unit and integration testing due to issues like engineering challenges, performance overhead, and incomplete results. To resolve these issues, in this paper we have proposed an automated approach, called LogCoCo, to estimating code coverage measures using the readily available execution logs. Using program analysis techniques, LogCoCo matches the execution logs with their corresponding code paths and estimates three different code coverage criteria: method coverage, statement coverage, and branch coverage. Case studies on one open source system (HBase) and five commercial systems from Baidu and systems show that: (1) the results of LogCoCo are highly accurate (>96% in seven out of nine experiments) under a variety of testing activities (unit testing, integration testing, and benchmarking); and (2) the results of LogCoCo can be used to evaluate and improve the existing test suites. Our collaborators at Baidu are currently considering adopting LogCoCo and use it on a daily basis.

Emerging non-volatile memories (NVM), such as phase change memory (PCM) and Resistive RAM (ReRAM), incorporate the features of fast byte-addressability and data persistence, which are beneficial for data services such as file systems and databases. To support data persistence, a persistent memory system requires ordering for write requests. The datapath of a persistent request consists of three segments: through the cache hierarchy to the memory controller, through the bus from the memory controller to memory devices, and through the network from a remote node to a local node. Previous work contributes significantly to improve the persistence parallelism in the first segment of the data path. However, we observe that the memory bus and the Remote Direct Memory Access (RDMA) network remain severely under-utilized because the persistence parallelism in these two segments is not fully leveraged during ordering. In this paper, we propose a novel architecture to further improve the persistence parallelism in the memory bus and the RDMA network. First, we utilize inter-thread persistence parallelism for barrier epoch management with better bank-level parallelism (BLP). Second, we enable intra-thread persistence parallelism for remote requests through RDMA network with buffered strict persistence. With these features, the architecture efficiently supports persistence through all three segments of the write datapath. Experimental results show that for local applications, the proposed mechanism can achieve 1.3× performance improvement, compared to the original buffered persistence work. In addition, it can achieve 1.93× performance improvement for remote applications serviced through the RDMA network.

Memory-centric architecture, which bridges the gap between compute and memory, is considered as a promising solution to tackle the memory wall and the power wall. Such architecture integrates the computing logic and the memory resources close to each other, in order to embrace large internal memory bandwidth and reduce the data movement overhead. The closer the compute and memory resources are located, the greater these benefits become. DRAM-based in-situ accelerators [1] tightly couple processing units to every memory bitline, achieving the maximum benefits among various memory-centric architectures. However, the processing units in such architectures are typically limited to simple functions like AND/OR due to strict area and power overhead constraints in DRAMs, making it difficult to accomplish complex tasks while providing high performance. In this paper, we address the challenge by applying stochastic computing arithmetic to the DRAM-based in-situ accelerator, targeting at the acceleration of error-tolerant applications such as deep learning. In stochastic computing, binary numbers are converted into stochastic bitstreams, which turns integer multiplications into simple bitwise AND operations, but at the expense of larger memory capacity/bandwidth demands. Stochastic computing is a perfect match for the DRAM-based in-situ accelerators because it addresses the in-situ accelerator's low performance problem by simplifying the operations, while leveraging the in-situ accelerator's advantage of large memory capacity/bandwidth. To further boost the performance and compensate for the numerical precision loss, we propose a novel Hierarchical and Hybrid Deterministic (H2D) stochastic computing arithmetic. Finally, we consider quantized deep neural network inference and training applications as a case study. The proposed architecture provides 2.3× improvement in performance per unit area compared with the binary arithmetic baseline, and 3.8× improvement over GPU. The proposed H2D arithmetic contributes 11× performance boost and 60% numerical precision improvement.

As technology scales, thermal management for multicore architectures becomes a critical challenge due to increasing power density. Existing power budgeting techniques focus on maximizing performance under a given power budget by optimizing the core configurations. In multicore era, a chip-wide power budget, however, is not sufficient to ensure thermal constraints because the thermal sustainable power capacity varies with different threading strategies and core configurations. In this article, we propose two models to dynamically estimate the thermal sustainable power capacity in homogeneous multicore systems: uniform power model and nonuniform power model . These two models convert the thermal effect of threading strategies and core configurations into power capacity, which provide a context-based core power capacity for power budgeting. Based on these models, we introduce a power budgeting framework aiming to improve the performance within thermal constraints, named as TSocket. Compared to the chip-wide power budgeting solution, TSocket shows 19% average performance improvement for the PARSEC benchmarks in single program scenario and up to 11% performance improvement in multiprogram scenario. The performance improvement is achieved by reducing thermal violations and exploring thermal headrooms.

One of the design challenges for the emerging 3D ICs is the power integrity. With multiple dies stacked vertically, the voltage droop may result in severe power integrity issues. In this paper, we first analyze the impact of application behaviors on voltage droop in a 3D power supply network (PDN) and observe that voltage droop is extremely imbalanced either across different layers or among the cores in the same layer. Based on the observation, we propose Swimming Lane, a hardware/software co-design method with two key schemes: (1) Mitigating the interference among different dies via a layer-independent scheme, and (2) balancing the intra-layer voltage droop and reducing the worst-case margin via OS scheduling. Compared to conventional designs, our method can reduce power consumption by 18%, worst-case voltage droops by 13%, and the number of voltage violations by 40%.

As technology scales, thermal management for multi-core architectures becomes a critical challenge due to increased power density and higher integration density. Existing power budgeting techniques focus on maximizing performance under a given power budget by optimizing the core dynamics. However, in multi-core era, a chip-wide power budget is not sufficient to ensure thermal constraints because the thermal sustainable power capacity varies with different threading strategies and core configurations. In this paper, we propose a model which estimates the thermal sustainable power capacity considering these two run-time factors. The model converts the thermal effect of threading strategies and core configurations into power capacity, which provides a context-based power budget for the power budgeting. Based on this model, we introduce a power budgeting framework aiming to optimize the performance within thermal constraints, named as TSocket. Compared to the chip-wide power budgeting solution, TSocket shows 19% of performance improvement for the PARSEC benchmarks by reducing thermal violations and providing extra power budget for performance improvement.

Voltage emergency (VE) has become a critical challenge with decreasing feature size and increasing power capacity. Destructive core interference is one main source of VE in multicore processors. We observed that the applications following single program and multiple data programming model tend to spark domain-wide destructive core interference because multiple threads exhibit similar power activity. We analyze and quantify this effect and propose one low-cost solution, Orchestrator, to avoid voltage droop synergy among cores. Orchestrator leverages the thread diversity to smooth voltage droops in multicore architectures based on thread scheduling. The thread migration impact on performance is also considered. Experimental results show that Orchestrator can significantly reduce VEs, thereby improving performance.

Voltage emergencies have become a major challenge to multi-core processors because core-to-core resonance may put all cores into danger which jeopardizes system reliability. We observed that the applications following SPMD (Single Program and Multiple Data) programming model tend to spark domain-wide voltage resonance because multiple threads sharing the same function body exhibit similar power activity. When threads are judiciously relocated among the cores, the voltage droops can be greatly reduced. We propose “Orchestrator”, a sensor-free non-intrusive scheme for multi-core architectures to smooth the voltage droops. Orchestrator focuses on the inter-core voltage interactions, and maximally leverages the thread diversity to avoid voltage droops synergy among cores. Experimental results show that Orchestrator can reduce up to 64% voltage emergencies on average, meanwhile improving performance.

Supply voltage fluctuation caused by inductive noises has become a critical problem in microprocessor design. A voltage emergency occurs when supply voltage variation exceeds the acceptable voltage margin, jeopardizing the microprocessor reliability. Existing techniques assume all voltage emergencies would definitely lead to incorrect program execution and prudently activate rollbacks or flushes to recover, and consequently incur high performance overhead. We observe that not all voltage emergencies result in external visible errors, which can be exploited to avoid unnecessary protection. In this paper, we propose a substantial-impact-filter based method to tolerate voltage emergencies, including three key techniques: 1) Analyze the architecture-level masking of voltage emergencies during program execution; 2) Propose a metric intermittent vulnerability factor for intermittent timing faults (IV Fitf) to quantitatively estimate the vulnerability of microprocessor structures (load/store queue and register file) to voltage emergencies; 3) Propose a substantial-impact-filter based method to handle voltage emergencies. Experimental results demonstrate our approach gains back nearly 57% of the performance loss compared with the once-occur-then-rollback approach.