Search

In this work, we proposed a new 3D integration technology: the Flip 3D integration (F3D), consisting of the 3D transistor stacking, the 3D dual-sided interconnects, the 3D die-to-die stacking and the dual-sided Monolithic 3D (M3D). Based on a 32-bit FFET RISCV core, besides the scaling benefits of the Flip FET (FFET), the dual-sided signal routing shows even more routing flexibility with 6.8% area reduction and 5.9% EDP improvement. Novel concepts of Multi-Flipping processes (Double Flips and Triple Flips) were proposed to relax the thermal budget constraints in the F3D and thus support the dual-sided M3D in the F3D. The core's EDP and frequency are improved by up to 3.2% and 2.3% respectively, after BEOL optimizations based on the Triple Flips compared with unoptimized ones., Comment: Accepted by EDTM 2025

Analog layout design heavily involves interactive processes between humans and design tools. The tools are usually designed to use scripting commands or visualized buttons for manipulation, especially for those interactive automation functionalities, which have a steep learning curve and cumbersome user experience, making a notable barrier to their adoption by designers. Aiming to address such a usability issue, this paper introduces LayoutCopilot, a pioneering multi-agent collaborative framework powered by Large Language Models (LLMs) for interactive analog layout design. LayoutCopilot simplifies human-tool interaction by converting natural language instructions into executable script commands, and it interprets high-level design intents into actionable suggestions, significantly streamlining the design process. Experimental results demonstrate the flexibility, efficiency, and accessibility of LayoutCopilot in handling real-world analog designs., Comment: 8pages, 8figures

Analog Computing-in-Memory (ACIM) is an emerging architecture to perform efficient AI edge computing. However, current ACIM designs usually have unscalable topology and still heavily rely on manual efforts. These drawbacks limit the ACIM application scenarios and lead to an undesired time-to-market. This work proposes an end-to-end automated ACIM based on a synthesizable architecture (EasyACIM). With a given array size and customized cell library, EasyACIM can generate layouts for ACIMs with various design specifications end-to-end automatically. Leveraging the multi-objective genetic algorithm (MOGA)-based design space explorer, EasyACIM can obtain high-quality ACIM solutions based on the proposed synthesizable architecture, targeting versatile application scenarios. The ACIM solutions given by EasyACIM have a wide design space and competitive performance compared to the state-of-the-art (SOTA) ACIMs.

IR drop on the power delivery network (PDN) is closely related to PDN's configuration and cell current consumption. As the integrated circuit (IC) design is growing larger, dynamic IR drop simulation becomes computationally unaffordable and machine learning based IR drop prediction has been explored as a promising solution. Although CNN-based methods have been adapted to IR drop prediction task in several works, the shortcomings of overlooking PDN configuration is non-negligible. In this paper, we consider not only how to properly represent cell-PDN relation, but also how to model IR drop following its physical nature in the feature aggregation procedure. Thus, we propose a novel graph structure, PDNGraph, to unify the representations of the PDN structure and the fine-grained cell-PDN relation. We further propose a dual-branch heterogeneous network, PDNNet, incorporating two parallel GNN-CNN branches to favorably capture the above features during the learning process. Several key designs are presented to make the dynamic IR drop prediction highly effective and interpretable. We are the first work to apply graph structure to deep-learning based dynamic IR drop prediction method. Experiments show that PDNNet outperforms the state-of-the-art CNN-based methods by up to 39.3% reduction in prediction error and achieves 545x speedup compared to the commercial tool, which demonstrates the superiority of our method.

This paper presents an innovative approach to 3D mixed-size placement in heterogeneous face-to-face (F2F) bonded 3D ICs. We propose an analytical framework that utilizes a dedicated density model and a bistratal wirelength model, effectively handling macros and standard cells in a 3D solution space. A novel 3D preconditioner is developed to resolve the topological and physical gap between macros and standard cells. Additionally, we propose a mixed-integer linear programming (MILP) formulation for macro rotation to optimize wirelength. Our framework is implemented with full-scale GPU acceleration, leveraging an adaptive 3D density accumulation algorithm and an incremental wirelength gradient algorithm. Experimental results on ICCAD 2023 contest benchmarks demonstrate that our framework can achieve 5.9% quality score improvement compared to the first-place winner with 4.0x runtime speedup. Additional experiments on modern RISC-V designs further validate the generalizability and superiority of our framework.

Within the Electronic Design Automation (EDA) domain, AI-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an AI4EDA approach falls short of achieving a holistic design synthesis and understanding, overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This paper argues for a paradigm shift from AI4EDA towards AI-native EDA, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, RTL designs, circuit netlists, and physical layouts. We champion the creation of large circuit models (LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-native philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound shift-left in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area (PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities., Comment: The authors are ordered alphabetically. Contact: qxu@cse[dot]cuhk[dot]edu[dot]hk, gluo@pku[dot]edu[dot]cn, yuan.mingxuan@huawei[dot]com

Post-layout simulation provides accurate guidance for analog circuit design, but post-layout performance is hard to be directly optimized at early design stages. Prior work on analog circuit sizing often utilizes pre-layout simulation results as the optimization objective. In this work, we propose a post-layout-simulation-driven (post-simulation-driven for short) analog circuit sizing framework that directly optimizes the post-layout simulation performance. The framework integrates automated layout generation into the optimization loop of transistor sizing and leverages a coupled Bayesian optimization algorithm to search for the best post-simulation performance. Experimental results demonstrate that our framework can achieve over 20% better post-layout performance in competitive time than manual design and the method that only considers pre-layout optimization.

In this paper, we present a new analytical 3D placement framework with a bistratal wirelength model for F2F-bonded 3D ICs with heterogeneous technology nodes based on the electrostatic-based density model. The proposed framework, enabled GPU-acceleration, is capable of efficiently determining node partitioning and locations simultaneously, leveraging the dedicated 3D wirelength model and density model. The experimental results on ICCAD 2022 contest benchmarks demonstrate that our proposed 3D placement framework can achieve up to 6.1% wirelength improvement and 4.1% on average compared to the first-place winner with much fewer vertical interconnections and up to 9.8x runtime speedup. Notably, the proposed framework also outperforms the state-of-the-art 3D analytical placer by up to 3.3% wirelength improvement and 2.1% on average with up to 8.8x acceleration on large cases using GPUs.

With the rapid advancements of deep learning in recent years, hardware accelerators are continuously deployed in more and more safety-critical applications such as autonomous driving and robotics. While the accelerators are usually fabricated with advanced technology nodes for high performance and energy efficiency, they are also more prone to timing errors under process, voltage, temperature, and aging (PVTA) variations. By revisiting the physical sources of timing errors, we show that most of the timing errors in the accelerator are caused by a specific subset of input patterns, defined as critical input patterns. To improve the timing error resilience of the accelerator, in this paper, we propose READ, a reliability-enhanced accelerator dataflow optimization technique that can effectively reduce timing errors. READ reduces the occurrence of critical input patterns by exploring the optimal computing sequence when mapping a trained deep neural network to accelerators. READ only changes the order of multiply-accumulate operations in a convolution, which introduces negligible hardware overhead and no impact on accuracy. The experimental results on VGG and ResNet demonstrate on average 7.8X timing error rate (TER) reduction and up to 37.9X TER reduction for certain layers. The results also show that READ enables the accelerator to maintain accuracy over a wide range of PVTA variations, making it a promising approach for robust deep-learning design

Multi-die FPGAs are crucial components in modern computing systems, particularly for high-performance applications such as artificial intelligence and data centers. Super long lines (SLLs) provide interconnections between super logic regions (SLRs) for a multi-die FPGA on a silicon interposer. They have significantly higher delay compared to regular interconnects, which need to be minimized. With the increase in design complexity, the growth of SLLs gives rise to challenges in timing and power closure. Existing placement algorithms focus on optimizing the number of SLLs but often face limitations due to specific topologies of SLRs. Furthermore, they fall short of achieving continuous optimization of SLLs throughout the entire placement process. This highlights the necessity for more advanced and adaptable solutions. In this paper, we propose LEAPS, a comprehensive, systematic, and adaptable multi-die FPGA placement algorithm for SLL minimization. Our contributions are threefold: 1) proposing a high-performance global placement algorithm for multi-die FPGAs that optimizes the number of SLLs while addressing other essential design constraints such as wirelength, routability, and clock routing; 2) introducing a versatile method for more complex SLR topologies of multi-die FPGAs, surpassing the limitations of existing approaches; and 3) executing continuous optimization of SLLs across the whole placement stages, including global placement (GP), legalization (LG), and detailed placement (DP). Experimental results demonstrate the effectiveness of LEAPS in reducing SLLs and enhancing circuit performance. Compared with the most recent state-of-the-art (SOTA) method, LEAPS achieves an average reduction of 43.08% in SLLs and 9.99% in HPWL, while exhibiting a notable 34.34$\times$ improvement in runtime.

Packing is a required step in a typical FPGA CAD flow. It has high impacts to the performance of FPGA placement and routing. Early prediction of packing results can guide design optimization and expedite design closure. In this work, we propose an imbalanced large graph learning framework, ImLG, for prediction of whether logic elements will be packed after placement. Specifically, we propose dedicated feature extraction and feature aggregation methods to enhance the node representation learning of circuit graphs. With imbalanced distribution of packed and unpacked logic elements, we further propose techniques such as graph oversampling and mini-batch training for this imbalanced learning task in large circuit graphs. Experimental results demonstrate that our framework can improve the F1 score by 42.82% compared to the most recent Gaussian-based prediction method. Physical design results show that the proposed method can assist the placer in improving routed wirelength by 0.93% and SLICE occupation by 0.89%.

This paper proposes OpenPARF, an open-source placement and routing framework for large-scale FPGA designs. OpenPARF is implemented with the deep learning toolkit PyTorch and supports massive parallelization on GPU. The framework proposes a novel asymmetric multi-electrostatic field system to solve FPGA placement. It considers fine-grained routing resources inside configurable logic blocks (CLBs) for FPGA routing and supports large-scale irregular routing resource graphs. Experimental results on ISPD 2016 and ISPD 2017 FPGA contest benchmarks and industrial benchmarks demonstrate that OpenPARF can achieve 0.4-12.7% improvement in routed wirelength and more than $2\times$ speedup in placement. We believe that OpenPARF can pave the road for developing FPGA physical design engines and stimulate further research on related topics.

Accurate early congestion prediction can prevent unpleasant surprises at the routing stage, playing a crucial character in assisting designers to iterate faster in VLSI design cycles. In this paper, we introduce a novel strategy to fully incorporate topological and geometrical features of circuits by making several key designs in our network architecture. To be more specific, we construct two individual graphs (geometry-graph, topology-graph) with distinct edge construction schemes according to their unique properties. We then propose a dual-branch network with different encoder layers in each pathway and aggregate representations with a sophisticated fusion strategy. Our network, named HybridNet, not only provides a simple yet effective way to capture the geometric interactions of cells, but also preserves the original topological relationships in the netlist. Experimental results on the ISPD2015 benchmarks show that we achieve an improvement of 10.9% compared to previous methods.

When modern FPGA architecture becomes increasingly complicated, modern FPGA placement is a mixed optimization problem with multiple objectives, including wirelength, routability, timing closure, and clock feasibility. Typical FPGA devices nowadays consist of heterogeneous SLICEs like SLICEL and SLICEM. The resources of a SLICE can be configured to {LUT, FF, distributed RAM, SHIFT, CARRY}. Besides such heterogeneity, advanced FPGA architectures also bring complicated constraints like timing, clock routing, carry chain alignment, etc. The above heterogeneity and constraints impose increasing challenges to FPGA placement algorithms. In this work, we propose a multi-electrostatic FPGA placer considering the aforementioned SLICEL-SLICEM heterogeneity under timing, clock routing and carry chain alignment constraints. We first propose an effective SLICEL-SLICEM heterogeneity model with a novel electrostatic-based density formulation. We also design a dynamically adjusted preconditioning and carry chain alignment technique to stabilize the optimization convergence. We then propose a timing-driven net weighting scheme to incorporate timing optimization. Finally, we put forward a nested Lagrangian relaxation-based placement framework to incorporate the optimization objectives of wirelength, routability, timing, and clock feasibility. Experimental results on both academic and industrial benchmarks demonstrate that our placer outperforms the state-of-the-art placers in quality and efficiency.

The electronic design automation (EDA) community has been actively exploring machine learning (ML) for very large-scale integrated computer-aided design (VLSI CAD). Many studies explored learning-based techniques for cross-stage prediction tasks in the design flow to achieve faster design convergence. Although building ML models usually requires a large amount of data, most studies can only generate small internal datasets for validation because of the lack of large public datasets. In this essay, we present the first open-source dataset called CircuitNet for ML tasks in VLSI CAD.

Precise congestion prediction from a placement solution plays a crucial role in circuit placement. This work proposes the lattice hypergraph (LH-graph), a novel graph formulation for circuits, which preserves netlist data during the whole learning process, and enables the congestion information propagated geometrically and topologically. Based on the formulation, we further developed a heterogeneous graph neural network architecture LHNN, jointing the routing demand regression to support the congestion spot classification. LHNN constantly achieves more than 35% improvements compared with U-nets and Pix2Pix on the F1 score. We expect our work shall highlight essential procedures using machine learning for congestion prediction., Comment: Accepted as a conference paper in DAC 2022; 6 pages, 4 figures

In this paper, we introduce Heteroflow, a new C++ library to help developers quickly write parallel CPU-GPU programs using task dependency graphs. Heteroflow leverages the power of modern C++ and task-based approaches to enable efficient implementations of heterogeneous decomposition strategies. Our new CPU-GPU programming model allows users to express a problem in a way that adapts to effective separation of concerns and expertise encapsulation. Compared with existing libraries, Heteroflow is more cost-efficient in performance scaling, programming productivity, and solution generality. We have evaluated Heteroflow on two real applications in VLSI design automation and demonstrated the performance scalability across different CPU-GPU numbers and problem sizes. At a particular example of VLSI timing analysis with million-scale tasking, Heteroflow achieved 7.7x runtime speed-up (99 vs 13 minutes) over a baseline on a machine of 40 CPU cores and 4 GPUs.

Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows. Compared with traditional solvers using heuristics or expert-well-designed algorithms, machine learning has shown promising prospects by its data-driven nature, which can be of less reliance on knowledge and priors, and potentially more scalable by its advanced computational paradigms (e.g. deep networks with GPU acceleration). This survey starts with the introduction of basics of placement and routing, with a brief description on classic learning-free solvers. Then we present detailed review on recent advance in machine learning for placement and routing. Finally we discuss the challenges and opportunities for future research.

Pipeline is a fundamental parallel programming pattern. Mainstream pipeline programming frameworks count on data abstractions to perform pipeline scheduling. This design is convenient for data-centric pipeline applications but inefficient for algorithms that only exploit task parallelism in pipeline. As a result, we introduce a new task-parallel pipeline programming framework called Pipeflow. Pipeflow does not design yet another data abstraction but focuses on the pipeline scheduling itself, enabling more efficient implementation of task-parallel pipeline algorithms than existing frameworks. We have evaluated Pipeflow on both micro-benchmarks and real-world applications. As an example, Pipeflow outperforms oneTBB 24% and 10% faster in a VLSI placement and a timing analysis workloads that adopt pipeline parallelism to speed up runtimes, respectively.

Taskflow aims to streamline the building of parallel and heterogeneous applications using a lightweight task graph-based approach. Taskflow introduces an expressive task graph programming model to assist developers in the implementation of parallel and heterogeneous decomposition strategies on a heterogeneous computing platform. Our programming model distinguishes itself as a very general class of task graph parallelism with in-graph control flow to enable end-to-end parallel optimization. To support our model with high performance, we design an efficient system runtime that solves many of the new scheduling challenges arising out of our models and optimizes the performance across latency, energy efficiency, and throughput. We have demonstrated the promising performance of Taskflow in real-world applications. As an example, Taskflow solves a large-scale machine learning workload up to 29% faster, 1.5x less memory, and 1.9x higher throughput than the industrial system, oneTBB, on a machine of 40 CPUs and 4 GPUs. We have opened the source of Taskflow and deployed it to large numbers of users in the open-source community., Comment: 18 pages, 24 figures

Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no rigorous theoretical guarantees on why existing neural net compression methods should work. In this paper, we provide provable guarantees on some hashing-based parameter reduction methods in neural nets. First, we introduce a neural net compression scheme based on random linear sketching (which is usually implemented efficiently via hashing), and show that the sketched (smaller) network is able to approximate the original network on all input data coming from any smooth and well-conditioned low-dimensional manifold. The sketched network can also be trained directly via back-propagation. Next, we study the previously proposed HashedNets architecture and show that the optimization landscape of one-hidden-layer HashedNets has a local strong convexity property similar to a normal fully connected neural network. We complement our theoretical results with empirical verifications., Comment: AISTATS 2019

Multiple patterning lithography has been widely adopted in advanced technology nodes of VLSI manufacturing. As a key step in the design flow, multiple patterning layout decomposition (MPLD) is critical to design closure. Due to the NP-hardness of the general decomposition problem, various efficient algorithms have been proposed with high quality solutions. However, with increasingly complicated design flow and peripheral processing steps, developing a high-quality layout decomposer becomes more and more difficult, slowing down the further advancement in this field. This paper presents OpenMPL [1], an open-source layout decomposition framework, with well-separated peripheral processing and the core solving steps. We demonstrate the flexibility of the framework with efficient implementations of various state-of-the-art algorithms, which enable us to reproduce most of the recent results on widely-recognized benchmarks. We believe OpenMPL can pave the road for developing layout decomposition engines and stimulate further researches on this problem.

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this work, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., 3-10X reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.

It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, the Fourier Recurrent Unit (FRU), that stabilizes the gradients that arise in its training while giving us stronger expressive power. Specifically, FRU summarizes the hidden states $h^{(t)}$ along the temporal dimension with Fourier basis functions. This allows gradients to easily reach any layer due to FRU's residual learning structure and the global support of trigonometric functions. We show that FRU has gradient lower and upper bounds independent of temporal dimension. We also show the strong expressivity of sparse Fourier basis, from which FRU obtains its strong expressive power. Our experimental study also demonstrates that with fewer parameters the proposed architecture outperforms other recurrent architectures on many tasks.