arXiv subjects

Junshi Chen

Publications and source records attributed to Junshi Chen.

18 recordsLinked to original sources

arXiv2026

TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling

Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global attention, but existing distributed systems such as AERIS primarily target pixel-level models and do not jointly support convolutional sampling modules and shifted-window execution. Long-lead rollout finetuning further increases activation memory. To address these challenges, we present TERRA, a hierarchical parallel training framework for high-resolution Earth forecasting. TERRA introduces Sampling-Aware Window, Sequence, and Tensor Parallelism (SAWSTP), which preserves spatially contiguous layouts for sampling modules and routes tokens into topology-aware ragged window layouts for Transformer execution. For long-lead finetuning, Memory Orchestration (MO) provides rollout-aware checkpoint planning and combines input buffering with budget-constrained activation offloading. Experiments on the $1/12^\circ$ GLORYS-based Wenhai workload show that TERRA supports models with up to 11.4B parameters on 96 H200 GPUs and sustains up to $39.76$ PFLOPS, achieving $65.0\%$ strong-scaling and $94.1\%$ weak-scaling efficiency. Compared with checkpoint-only policies, MO further reduces peak allocated GPU memory by $32.2\%$--$51.8\%$ with at most $20.0\%$ step-time overhead, which makes finetuning with smaller patch sizes and longer rollouts feasible for improved forecasting accuracy.

cs.CV↗

arXiv2026

Cellular Signal Constructed Convolutional Vision Transformer for High Accuracy Positioning

Modern cellular systems employ wide bandwidths and large antenna arrays to meet high data rate requirements. The high spatial and temporal resolution for communication also enables high-accuracy positioning as an ancillary benefit. Standard convolutional neural networks (CNNs) and vision Transformers have demonstrated excellent performance in positioning by leveraging delay-angle domain channel representations. However, they still face practical challenges in complicated cellular environments with low signal-to-noise ratios and severe inter-cell interference. This paper proposes a hybrid convolutional vision Transformer (ConViT) architecture that integrates the local receptive fields of CNNs to suppress local noise and employs Transformers to capture global attention among different multipath components. Various fusion strategies for combining signals from multiple distributed base stations are also evaluated. An extended Kalman filter with sensor fusion is applied to further mitigate long tail fluctuations of model estimates. Comprehensive validation is conducted with commercial long-term-evolution signals received by a large antenna array in urban environments with non line-of-sight signals and strong inter-cell interference. ConViT achieves a distance root mean square error (RMSE) of 3.46 meters and a yaw RMSE of 2.54 degrees, significantly outperforming benchmark models, while maintaining a lower parameter count and reduced computational complexity. Finally, a correspondence analysis between delay-angle power distributions and Transformer attention weights demonstrates the interpretability of the model.

eess.SP↗

arXiv2026

FusionRCG: Orchestrating Recursive Computation Graphs across GPU Memory Hierarchies

Evaluating high-dimensional integrals via deep hierarchical recurrences is a dominant cost in quantum chemistry. While CPUs manage these efficiently, GPUs suffer a critical mismatch: limited per-thread memory is quickly overwhelmed by an explosion of simultaneously live intermediate variables. As recurrence scales, this forces massive data spilling to global memory, collapsing performance into a severe memory-bound regime. We present FusionRCG, a framework that jointly optimizes computation graph structure and GPU memory mapping. Exploiting the inherent topological flexibility of recurrence graphs, using electron repulsion integrals as an example, we contribute: (1) liveness-aware graph orchestration to minimize peak live intermediates; (2) algebraic dimensionality reduction via stepwise Cartesian-to-spherical fusion, shrinking intermediate footprints by up to $7.7\times$; and (3) an adaptive multi-tier kernel architecture routing graphs across the memory hierarchy. Evaluated on NVIDIA A100 GPUs, FusionRCG achieves up to $3.09\times$ end-to-end SCF speedup over GPU4PySCF and maintains $75\%$ parallel efficiency at 64~GPUs, successfully rescuing these workloads from memory-bound limits.

physics.comp-ph↗

arXiv2025

Robust Localization in Modern Cellular Networks using Global Map Features

Radio frequency (RF) signal-based localization using modern cellular networks has emerged as a promising solution to accurately locate objects in challenging environments. One of the most promising solutions for situations involving obstructed-line-of-sight (OLoS) and multipath propagation is multipathbased simultaneous localization and mapping (MP-SLAM) that employs map features (MFs), such as virtual anchors. This paper presents an extended MP-SLAM method that is augmented with a global map feature (GMF) repository. This repository stores consistent MFs of high quality that are collected during prior traversals. We integrate these GMFs back into the MP-SLAM framework via a probability hypothesis density (PHD) filter, which propagates GMF intensity functions over time. Extensive simulations, together with a challenging real-world experiment using LTE RF signals in a dense urban scenario with severe multipath propagation and inter-cell interference, demonstrate that our framework achieves robust and accurate localization, thereby showcasing its effectiveness in realistic modern cellular networks such as 5G or future 6G networks. It outperforms conventional proprioceptive sensor-based localization and conventional MP-SLAM methods, and achieves reliable localization even under adverse signal conditions.

eess.SP↗

arXiv2025

Robust quantum computational advantage with programmable 3050-photon Gaussian boson sampling

The creation of large-scale, high-fidelity quantum computers is not only a fundamental scientific endeavour in itself, but also provides increasingly robust proofs of quantum computational advantage (QCA) in the presence of unavoidable noise and the dynamic competition with classical algorithm improvements. To overcome the biggest challenge of photon-based QCA experiments, photon loss, we report new Gaussian boson sampling (GBS) experiments with 1024 high-efficiency squeezed states injected into a hybrid spatial-temporal encoded, 8176-mode, programmable photonic quantum processor, Jiuzhang 4.0, which produces up to 3050 photon detection events. Our experimental results outperform all classical spoofing algorithms, particularly the matrix product state (MPS) method, which was recently proposed to utilise photon loss to reduce the classical simulation complexity of GBS. Using the state-of-the-art MPS algorithm on the most powerful supercomputer EI Capitan, it would take > $10^{42}$ years to construct the required tensor network for simulation, while our Jiuzhang 4.0 quantum computer takes 25.6 $\mu$s to produce a sample. This work establishes a new frontier of QCA and paves the way to fault-tolerant photonic quantum computing hardware.

quant-ph↗

arXiv2025

SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation

Sparse Tensor Cores offer exceptional performance gains for AI workloads by exploiting structured 2:4 sparsity. However, their potential remains untapped for core scientific workloads such as stencil computations, which exhibit irregular sparsity patterns.This paper presents SparStencil, the first system to retarget sparse TCUs for scientific stencil computations through structured sparsity transformation. SparStencil introduces three key techniques: (1) Adaptive Layout Morphing, which restructures stencil patterns into staircase-aligned sparse matrices via a flatten-and-crush pipeline; (2) Structured Sparsity Conversion, which formulates transformation as a graph matching problem to ensure compatibility with 2:4 sparsity constraints; (3) Automatic Kernel Generation, which compiles transformed stencils into optimized sparse MMA kernels via layout search and table-driven memory mapping. Evaluated on 79 stencil kernels spanning diverse scientific domains, SparStencil achieves up to 7.1x speedup (3.1x on average) over state-of-the-art framework while reducing code complexity and matching or exceeding expert-tuned performance in both compute throughput and memory efficiency.

cs.CE↗

arXiv2025

NDFT: Accelerating Density Functional Theory Calculations via Hardware/Software Co-Design on Near-Data Computing System

Linear-response time-dependent Density Functional Theory (LR-TDDFT) is a widely used method for accurately predicting the excited-state properties of physical systems. Previous works have attempted to accelerate LR-TDDFT using heterogeneous systems such as GPUs, FPGAs, and the Sunway architecture. However, a major drawback of these approaches is the constant data movement between host memory and the memory of the heterogeneous systems, which results in substantial \textit{data movement overhead}. Moreover, these works focus primarily on optimizing the compute-intensive portions of LR-TDDFT, despite the fact that the calculation steps are fundamentally \textit{memory-bound}. To address these challenges, we propose NDFT, a \underline{N}ear-\underline{D}ata Density \underline{F}unctional \underline{T}heory framework. Specifically, we design a novel task partitioning and scheduling mechanism to offload each part of LR-TDDFT to the most suitable computing units within a CPU-NDP system. Additionally, we implement a hardware/software co-optimization of a critical kernel in LR-TDDFT to further enhance performance on the CPU-NDP system. Our results show that NDFT achieves performance improvements of 5.2x and 2.5x over CPU and GPU baselines, respectively, on a large physical system.

cs.AR↗

arXiv2024

PWDFT-SW: Extending the Limit of Plane-Wave DFT Calculations to 16K Atoms on the New Sunway Supercomputer

First-principles density functional theory (DFT) with plane wave (PW) basis set is the most widely used method in quantum mechanical material simulations due to its advantages in accuracy and universality. However, a perceived drawback of PW-based DFT calculations is their substantial computational cost and memory usage, which currently limits their ability to simulate large-scale complex systems containing thousands of atoms. This situation is exacerbated in the new Sunway supercomputer, where each process is limited to a mere 16 GB of memory. Herein, we present a novel parallel implementation of plane wave density functional theory on the new Sunway supercomputer (PWDFT-SW). PWDFT-SW fully extracts the benefits of Sunway supercomputer by extensively refactoring and calibrating our algorithms to align with the system characteristics of the Sunway system. Through extensive numerical experiments, we demonstrate that our methods can substantially decrease both computational costs and memory usage. Our optimizations translate to a speedup of 64.8x for a physical system containing 4,096 silicon atoms, enabling us to push the limit of PW-based DFT calculations to large-scale systems containing 16,384 carbon atoms.

cs.DC↗

arXiv2024

A$^3$PIM: An Automated, Analytic and Accurate Processing-in-Memory Offloader

The performance gap between memory and processor has grown rapidly. Consequently, the energy and wall-clock time costs associated with moving data between the CPU and main memory predominate the overall computational cost. The Processing-in-Memory (PIM) paradigm emerges as a promising architecture that mitigates the need for extensive data movements by strategically positioning computing units proximate to the memory. Despite the abundant efforts devoted to building a robust and highly-available PIM system, identifying PIM-friendly segments of applications poses significant challenges due to the lack of a comprehensive tool to evaluate the intrinsic memory access pattern of the segment. To tackle this challenge, we propose A$^3$PIM: an Automated, Analytic and Accurate Processing-in-Memory offloader. We systematically consider the cross-segment data movement and the intrinsic memory access pattern of each code segment via static code analyzer. We evaluate A$^3$PIM across a wide range of real-world workloads including GAP and PrIM benchmarks and achieve an average speedup of 2.63x and 4.45x (up to 7.14x and 10.64x) when compared to CPU-only and PIM-only executions, respectively.

cs.AR↗

arXiv2024

Pruner: A Draft-then-Verify Exploration Mechanism to Accelerate Tensor Program Tuning

Tensor program tuning is essential for the efficient deployment of deep neural networks. Search-based approaches have demonstrated scalability and effectiveness in automatically finding high-performance programs for specific hardware. However, the search process is often inefficient, taking hours or even days to discover optimal programs due to the exploration mechanisms guided by an accurate but slow-learned cost model. Meanwhile, the learned cost model trained on one platform cannot seamlessly adapt online to another, which we call cross-platform online unawareness. In this work, we propose Pruner and MoA-Pruner. Pruner is a "Draft-then-Verify" exploration mechanism that accelerates the schedule search process. Instead of applying the complex learned cost model to all explored candidates, Pruner drafts small-scale potential candidates by introducing a naive Symbol-based Analyzer (draft model), then identifies the best candidates by the learned cost model. MoA-Pruner introduces a Momentum online Adaptation strategy to address the cross-platform online unawareness. We incorporate Pruner into the TVM and conduct extensive experiments on three GPU-based platforms. Results show considerable speedup in schedule search time. In online tuning scenarios, Pruner and MoA-Pruner achieve an average speedup of $2.6 \times$ and $4.82 \times$ compared to Ansor. In offline tuning scenarios, Pruner achieves an average speedup of $4.75 \times$ and $4.05\times$ compared to TenSet and TLP, respectively. Furthermore, Pruner achieves an average speedup of $4.08 \times$ compared to MetaSchedule on TensorCore.

cs.LG↗

arXiv2023

Wiometrics: Comparative Performance of Artificial Neural Networks for Wireless Navigation

Radio signals are used broadly as navigation aids, and current and future terrestrial wireless communication systems have properties that make their dual-use for this purpose attractive. Sub-6 GHz carrier frequencies enable widespread coverage for data communication and navigation, but typically offer smaller bandwidths and limited resolution for precise estimation of geometries, particularly in environments where propagation channels are diffuse in time and/or space. Non-parametric methods have been employed with some success for such scenarios both commercially and in literature, but often with an emphasis on low-cost hardware and simple models of propagation, or with simulations that do not fully capture hardware impairments and complex propagation mechanisms. In this article, we make opportunistic observations of downlink signals transmitted by commercial cellular networks by using a software-defined radio and massive antenna array mounted on a passenger vehicle in an urban non line-of-sight scenario, together with a ground truth reference for vehicle pose. With these observations as inputs, we employ artificial neural networks to generate estimates of vehicle location and heading for various artificial neural network architectures and different representations of the input observation data, which we call wiometrics, and compare the performance for navigation. Position accuracy on the order of a few meters, and heading accuracy of a few degrees, are achieved for the best-performing combinations of networks and wiometrics. Based on the results of the experiments we draw conclusions regarding possible future directions for wireless navigation using statistical methods.

eess.SP↗

arXiv2023

Extended FastSLAM Using Cellular Multipath Component Delays and Angular Information

Opportunistic navigation using cellular signals is appealing for scenarios where other navigation technologies face challenges. In this paper, long-term evolution (LTE) downlink signals from two neighboring commercial base stations (BS) are received by a massive antenna array mounted on a passenger vehicle. Multipath component (MPC) delays and angle-of-arrival (AOA) extracted from the received signals are used to jointly estimate the positions of the vehicle, transmitters, and virtual transmitters (VT) with an extended fast simultaneous localization and mapping (FastSLAM) algorithm. The results show that the algorithm can accurately estimate the positions of the vehicle and the transmitters (and virtual transmitters). The vehicle's horizontal position error of SLAM fused with proprioception is less than 6 meters after a traversed distance of 530 meters, whereas un-aided proprioception results in a horizontal error of 15 meters.

eess.SP↗

arXiv2023

High-Resolution Channel Sounding and Parameter Estimation in Multi-Site Cellular Networks

Accurate understanding of electromagnetic propagation properties in real environments is necessary for efficient design and deployment of cellular systems. In this paper, we show a method to estimate high-resolution channel parameters with a massive antenna array in real network deployments. An antenna array mounted on a vehicle is used to receive downlink long-term evolution (LTE) reference signals from neighboring base stations (BS) with mutual interference. Delay and angular information of multipath components is estimated with a novel inter-cell interference cancellation algorithm and an extension of the RIMAX algorithm. The estimated high-resolution channel parameters are consistent with the movement pattern of the vehicle and the geometry of the environment and allow for refined channel modeling and precise cellular positioning.

eess.SP↗

arXiv2022

$2^{1296}$ Exponentially Complex Quantum Many-Body Simulation via Scalable Deep Learning Method

For decades, people are developing efficient numerical methods for solving the challenging quantum many-body problem, whose Hilbert space grows exponentially with the size of the problem. However, this journey is far from over, as previous methods all have serious limitations. The recently developed deep learning methods provide a very promising new route to solve the long-standing quantum many-body problems. We report that a deep learning based simulation protocol can achieve the solution with state-of-the-art precision in the Hilbert space as large as $2^{1296}$ for spin system and $3^{144}$ for fermion system , using a HPC-AI hybrid framework on the new Sunway supercomputer. With highly scalability up to 40 million heterogeneous cores, our applications have measured 94% weak scaling efficiency and 72% strong scaling efficiency. The accomplishment of this work opens the door to simulate spin models and Fermion models on unprecedented lattice size with extreme high precision.

quant-ph↗

arXiv2022

Bridging the Gap between Deep Learning and Frustrated Quantum Spin System for Extreme-scale Simulations on New Generation of Sunway Supercomputer

Efficient numerical methods are promising tools for delivering unique insights into the fascinating properties of physics, such as the highly frustrated quantum many-body systems. However, the computational complexity of obtaining the wave functions for accurately describing the quantum states increases exponentially with respect to particle number. Here we present a novel convolutional neural network (CNN) for simulating the two-dimensional highly frustrated spin-$1/2$ $J_1-J_2$ Heisenberg model, meanwhile the simulation is performed at an extreme scale system with low cost and high scalability. By ingenious employment of transfer learning and CNN's translational invariance, we successfully investigate the quantum system with the lattice size up to $24\times24$, within 30 million cores of the new generation of sunway supercomputer. The final achievement demonstrates the effectiveness of CNN-based representation of quantum-state and brings the state-of-the-art record up to a brand-new level from both aspects of remarkable accuracy and unprecedented scales.

cond-mat.str-el↗

arXiv2021

Establishing a non-hydrostatic global atmospheric modeling system (iAMAS) at 3-km horizontal resolution with online integrated aerosol feedbacks on the Sunway supercomputer of China

During the era of global warming and highly urbanized development, extreme and high impact weather as well as air pollution incidents influence everyday life and might even cause the incalculable loss of life and property. Although with the vast development of numerical simulation of atmosphere, there still exists substantial forecast biases objectively. To predict extreme weather, severe air pollution, and abrupt climate change accurately, the numerical atmospheric model requires not only to simulate meteorology and atmospheric compositions and their impacts simultaneously involving many sophisticated physical and chemical processes but also at high spatiotemporal resolution. Global atmospheric simulation of meteorology and atmospheric compositions simultaneously at spatial resolutions of a few kilometers remains challenging due to its intensive computational and input/output (I/O) requirement. Through multi-dimension-parallelism structuring, aggressive and finer-grained optimizing, manual vectorizing, and parallelized I/O fragmenting, an integrated Atmospheric Model Across Scales (iAMAS) was established on the new Sunway supercomputer platform to significantly increase the computational efficiency and reduce the I/O cost. The global 3-km atmospheric simulation for meteorology with online integrated aerosol feedbacks with iAMAS was scaled to 39,000,000 processor cores and achieved the speed of 0.82 simulation day per hour (SDPH) with routine I/O, which enables us to perform 5-day global weather forecast at 3-km horizontal resolution with online natural aerosol impacts. The results demonstrate the promising future that the increasing of spatial resolution to a few kilometers with online integrated aerosol impacts may significantly improve the global weather forecast.

physics.ao-ph↗

arXiv2020

Extreme-Scale Density Functional Theory High Performance Computing of DGDFT for Tens of Thousands of Atoms using Millions of Cores on Sunway TaihuLight

High performance computing (HPC) is a powerful tool to accelerate the Kohn-Sham density functional theory (KS-DFT) calculations on modern heterogeneous supercomputers. Here, we describe a massively extreme-scale parallel and portable implementation of discontinuous Galerkin density functional theory (DGDFT) method on the Sunway TaihuLight supercomputer. The DGDFT method uses the adaptive local basis (ALB) functions generated on-the-fly during the self-consistent field (SCF) iteration to solve the KS equations with the high precision comparable to that of plane-wave basis set. In particular, the DGDFT method adopts a two-level parallelization strategy that makes use of different types of data distribution, task scheduling, and data communication schemes, and combines with the feature of master-slave multi-thread heterogeneous parallelism of SW26010 processor, resulting in extreme-scale HPC KS-DFT calculations on the Sunway TaihuLight supercomputer. We show that the DGDFT method can scale up to 8,519,680 processing cores (131,072 core groups) on the Sunway TaihuLight supercomputer for investigating the electronic structures of two-dimensional (2D) metallic graphene systems containing tens of thousands of carbon atoms.

physics.comp-ph↗

arXiv2018

PEPS++: Towards Extreme-scale Simulations of Strongly Correlated Quantum Many-particle Models on Sunway TainhuLight

The study of strongly frustrated magnetic systems has drawn great attentions from both theoretical and experimental physics. Efficient simulations of these models are essential for understanding their exotic properties. Here we present PEPS++, a novel computational paradigm for simulating frustrated magnetic systems and other strongly correlated quantum many-body systems. PEPS++ can accurately solve these models at the extreme scale with low cost and high scalability on modern heterogeneous supercomputers. We implement PEPS++ on Sunway TaihuLight based on a carefully designed tensor computation library for manipulating high-rank tensors and optimize it by invoking various high-performance matrix and tensor operations. By solving a 2D strongly frustrated $J_1$-$J_2$ model with over ten million cores, PEPS++ demonstrates the capability of simulating strongly correlated quantum many-body problems at unprecedented scales with accuracy and time-to-solution far beyond the previous state of the art.

cond-mat.str-el↗