arXiv subjects

Mauricio Araya-Polo

Publications and source records attributed to Mauricio Araya-Polo.

At least 19 recordsLinked to original sources

arXiv2026

Stencil Computation at the Intersection of AI and HPC

Tensor compilers such as TinyTC and OpenAI Triton were originally developed for AI workloads, but the same tiling and memory abstractions can be applied to implement efficient high-order stencils for scientific and industrial applications. We demonstrate this for an 8th-order, 25-point acoustic stencil with boundary conditions over an a demanding-sized grid, targeting GPGPUs, where we compare the hardware-specialized TinyTC implementation with a portable PyTorch/Triton implementation. The target platforms for evaluation include Intel B70, B580, GPU MAX 1550, NVIDIA A100/RTX6000 Blackwell/H100, and AMD MI325x. For instance, on Battlemage B580 TinyTC reaches 15.6 Gpts/s versus 13.5 Gpts/s for PT/Triton under random initialization, while zero-initialized runs reach up to 35.8 Gpts/s due to hardware memory compression. Using roofline and memory-hierarchy profiling, we show that -as expected- performance is predominantly bandwidth-limited and that compiler-managed L1/LSC caching can effectively replace programmer-managed shared-memory staging for this stencil class. Overall, the results position TinyTC as the performance-oriented path on Intel hardware and PyTorch/Triton as a strong portability/productivity baseline for cross-vendor HPC stencil development.

cs.DC↗

arXiv2026

AGENTS4GEOS: agentic platform for open-source multi-physics simulation

Multi-physics simulations are essential for understanding and monitoring intricate subsurface processes such as CO2 storage. Their computational demands call for surrogate models and, for unstructured meshes, Graph Neural Networks (GNNs) are natural candidates. The main bottleneck in developing them is generating and managing the large, physically consistent simulation datasets required for training. To address this challenge, we present Agents4GEOS, an AI-agent framework built on the Model Context Protocol (MCP) that provides 52 domain-aware tools for natural-language-driven workflows with GEOS, an open-source multi-physics simulator. The agent facilitates input-file creation, mesh inspection, fluid-property computation, and result post-processing. Through human-curated skills and fresh-context subagents coordinated by an orchestrator, the system executes complex workflows, evaluates simulation outputs, diagnoses issues, and suggests improvements, grounding every quantity in actual computation. By automating routine tasks, Agents4GEOS allows domain experts to focus on the most challenging aspects of their work.

physics.geo-ph↗

arXiv2026

Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations

This chapter discusses how a data-driven machine learning approach can reproduce key aspects of the physical behavior of multiphase flows in complex geological formations. We propose an end-to-end graph neural surrogate tailored to CO$_2$ plume migration forecasting in geological storage. The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$_2$ storage scenarios and characterized by sharp gas-water interfaces, strong advective transport, and rapid convective mixing with fingering development. The benchmark is reformulated as a graph in which nodes represent computational cells and edges encode transmissibility-based interactions enriched with geometric attributes. Directional transport arising from grid geometry, permeability contrasts, and geological heterogeneity is captured through an anisotropic message-passing mechanism, where interaction weights are computed via geometry-conditioned edge embeddings, biasing message aggregation toward physically relevant transport directions. Temporal evolution is modeled in latent space using an autoregressive residual formulation trained with multi-step supervision. The proposed model produces competitive forecasts of gas saturation and liquid-phase density, which are key indicators for CO$_2$ storage monitoring, with cumulative errors that remain moderate over extended forecasting horizons.

cs.LG↗

arXiv2026

GICC: A High-Performance Runtime for GPU-Initiated Communication and Coordination in Modern HPC Systems

Distributed GPU applications increasingly rely on kernel-level, cross-node coordination to reduce launch overheads and improve compute-communication overlap, but such support is lacking. On OFI-based interconnects such as HPE Slingshot, which powers six of the top ten systems in the November 2025 Top500, including the top three, GPU kernels cannot autonomously drive distributed coordination: existing runtimes rely on host-driven progress and lack a bounded mechanism for recycling pre-staged NIC work across repeated GPU-triggered operations. On InfiniBand, GPU-initiated communication is possible, but current implementations incur unnecessary synchronization and locking overheads. This paper presents GICC, a framework that enables GPU kernels to directly trigger NIC-level operations without host involvement on the fast path. In stencils, GPU threads initiate halo exchanges as soon as boundary regions are computed, enabling fine-grained overlap between interior computation and boundary transfer. GICC decouples coordination semantics from data movement and introduces asynchronous resource reclamation: the NIC signals completion to both GPU and host memory, letting a lightweight host thread recycle NIC resources concurrently with GPU execution without injecting latency into the coordination path. This sustains GPU-driven coordination under finite NIC state, absent from existing OFI-based runtimes. We implement GICC on NVIDIA and AMD GPUs over InfiniBand and Slingshot. On Slingshot, GICC reduces per-coordination latency by up to 229x and improves weak scaling efficiency by up to 25%. On InfiniBand, it achieves up to 1.95x lower put latency than NVSHMEM by eliminating unnecessary locking and synchronization. On an industrial stencil proxy on 64 AMD MI250X GCDs, GPU-aware MPI incurs over 52% higher communication time than GICC, which achieves 42% parallel efficiency versus MPI's 35.4%.

cs.DC↗

arXiv2026

Identification of Solid-Electrolyte Interphase Species by Joint Characterization of Li-ion Battery Chemistry by Mass Spectrometry and Electro-Chemical Reaction Networks

The formation and stability of the solid electrolyte interphase (SEI) play a central role in determining the long-term performance and safety of modern electrochemical energy storage systems. Despite decades of research, the SEI's heterogeneous, dynamic, and multi-phase nature has defied comprehensive molecular-level characterization, creating a critical knowledge gap that limits rational battery design. In this work, we introduce a computational-experimental framework that integrates high-throughput quantum chemistry calculations, data-driven electro-chemical reaction networks (eCRNs), stochastic algorithms, and Laser Desorption/Ionization Fourier Transform Ion Cyclotron Resonance Mass Spectrometry (LDI-FTICR-MS) to unravel SEI formation in carbonate-based electrolytes without imposing predefined mechanisms. We constructed the most comprehensive eCRN to date, spanning over 10,000 species and 209 million reactions. Through stochastic network analysis, we successfully recovered 27 species that were previously reported in literature and predicted 28 novel SEI species, nearly doubling our scientific knowledge in this area. Each new species was rigorously confirmed through advanced mass spectra analysis of its distinct molecular and isotopic signatures. We kinetically refined the formation pathways for a select set of both previously reported and novel SEI products, revealing kinetically feasible elementary reaction mechanisms with activation barriers below 1 eV. This computational-experimental approach deepens our molecular-level understanding of SEI chemistry and supports the rational design of advanced electrolytes and engineered interphases for next-generation lithium-based batteries.

physics.chem-ph↗

arXiv2026

Accelerated Full Waveform Inversion by Deep Compressed Learning

We propose and test a method to reduce the dimensionality of Full Waveform Inversion (FWI) inputs as computational cost mitigation approach. Given modern seismic acquisition systems, the data (as input for FWI) required for an industrial-strength case is in the teraflop level of storage, therefore solving complex subsurface cases or exploring multiple scenarios with FWI become prohibitive. The proposed method utilizes a deep neural network with a binarized sensing layer that learns by compressed learning a succinct but consequential seismic acquisition layout from a large corpus of subsurface models. Thus, given a large seismic data set to invert, the trained network selects a smaller subset of the data, then by using representation learning, an autoencoder computes latent representations of the data, followed by K-means clustering of the latent representations to further select the most relevant data for FWI. Effectively, this approach can be seen as a hierarchical selection. The proposed approach consistently outperforms random data sampling, even when utilizing only 10% of the data for 2D FWI, these results pave the way to accelerating FWI in large scale 3D inversion.

cs.LG↗

arXiv2025

DiOMP-Offloading: Toward Portable Distributed Heterogeneous OpenMP

As core counts and heterogeneity rise in HPC, traditional hybrid programming models face challenges in managing distributed GPU memory and ensuring portability. This paper presents DiOMP, a distributed OpenMP framework that unifies OpenMP target offloading with the Partitioned Global Address Space (PGAS) model. Built atop LLVM/OpenMP and using GASNet-EX or GPI-2 for communication, DiOMP transparently handles global memory, supporting both symmetric and asymmetric GPU allocations. It leverages OMPCCL, a portable collective communication layer compatible with vendor libraries. DiOMP simplifies programming by abstracting device memory and communication, achieving superior scalability and programmability over traditional approaches. Evaluations on NVIDIA A100, Grace Hopper, and AMD MI250X show improved performance in micro-benchmarks and applications like matrix multiplication and Minimod, highlighting DiOMP's potential for scalable, portable, and efficient heterogeneous computing.

cs.DC↗

arXiv2024

Uncertainty Quantification in Seismic Inversion Through Integrated Importance Sampling and Ensemble Methods

Seismic inversion is essential for geophysical exploration and geological assessment, but it is inherently subject to significant uncertainty. This uncertainty stems primarily from the limited information provided by observed seismic data, which is largely a result of constraints in data collection geometry. As a result, multiple plausible velocity models can often explain the same set of seismic observations. In deep learning-based seismic inversion, uncertainty arises from various sources, including data noise, neural network design and training, and inherent data limitations. This study introduces a novel approach to uncertainty quantification in seismic inversion by integrating ensemble methods with importance sampling. By leveraging ensemble approach in combination with importance sampling, we enhance the accuracy of uncertainty analysis while maintaining computational efficiency. The method involves initializing each model in the ensemble with different weights, introducing diversity in predictions and thereby improving the robustness and reliability of the inversion outcomes. Additionally, the use of importance sampling weights the contribution of each ensemble sample, allowing us to use a limited number of ensemble samples to obtain more accurate estimates of the posterior distribution. Our approach enables more precise quantification of uncertainty in velocity models derived from seismic data. By utilizing a limited number of ensemble samples, this method achieves an accurate and reliable assessment of uncertainty, ultimately providing greater confidence in seismic inversion results.

physics.geo-ph↗

arXiv2024

Towards a Scalable and Efficient PGAS-based Distributed OpenMP

MPI+X has been the de facto standard for distributed memory parallel programming. It is widely used primarily as an explicit two-sided communication model, which often leads to complex and error-prone code. Alternatively, PGAS model utilizes efficient one-sided communication and more intuitive communication primitives. In this paper, we present a novel approach that integrates PGAS concepts into the OpenMP programming model, leveraging the LLVM compiler infrastructure and the GASNet-EX communication library. Our model addresses the complexity associated with traditional MPI+OpenMP programming models while ensuring excellent performance and scalability. We evaluate our approach using a set of micro-benchmarks and application kernels on two distinct platforms: Ookami from Stony Brook University and NERSC Perlmutter. The results demonstrate that DiOMP achieves superior bandwidth and lower latency compared to MPI+OpenMP, up to 25% higher bandwidth and down to 45% on latency. DiOMP offers a promising alternative to the traditional MPI+OpenMP hybrid programming model, towards providing a more productive and efficient way to develop high-performance parallel applications for distributed memory systems.

cs.DC↗

arXiv2024

Evaluation of Programming Models and Performance for Stencil Computation on Current GPU Architectures

Accelerated computing is widely used in high-performance computing. Therefore, it is crucial to experiment and discover how to better utilize GPUGPUs latest generations on relevant applications. In this paper, we present results and share insights about highly tuned stencil-based kernels for NVIDIA Ampere (A100) and Hopper (GH200) architectures. Performance results yield useful insights into the behavior of this type of algorithms for these new accelerators. This knowledge can be leveraged by many scientific applications which involve stencils computations. Further, evaluation of three different programming models: CUDA, OpenACC, and OpenMP target offloading is conducted on aforementioned accelerators. We extensively study the performance and portability of various kernels under each programming model and provide corresponding optimization recommendations. Furthermore, we compare the performance of different programming models on the mentioned architectures. Up to 58% performance improvement was achieved against the previous GPGPU's architecture generation for an highly optimized kernel of the same class, and up to 42% for all classes. In terms of programming models, and keeping portability in mind, optimized OpenACC implementation outperforms OpenMP implementation by 33%. If portability is not a factor, our best tuned CUDA implementation outperforms the optimized OpenACC one by 2.1x.

cs.DC↗

arXiv2024

Matrix-Free Finite Volume Kernels on a Dataflow Architecture

Fast and accurate numerical simulations are crucial for designing large-scale geological carbon storage projects ensuring safe long-term CO2 containment as a climate change mitigation strategy. These simulations involve solving numerous large and complex linear systems arising from the implicit Finite Volume (FV) discretization of PDEs governing subsurface fluid flow. Compounded with highly detailed geomodels, solving linear systems is computationally and memory expensive, and accounts for the majority of the simulation time. Modern memory hierarchies are insufficient to meet the latency and bandwidth needs of large-scale numerical simulations. Therefore, exploring algorithms that can leverage alternative and balanced paradigms, such as dataflow and in-memory computing is crucial. This work introduces a matrix-free algorithm to solve FV-based linear systems using a dataflow architecture to significantly minimize memory latency and bandwidth bottlenecks. Our implementation achieves two orders of magnitude speedup compared to a GPGPU-based reference implementation, and up to 1.2 PFlops on a single dataflow device.

cs.MS↗

arXiv2024

A Portable Framework for Accelerating Stencil Computations on Modern Node Architectures

Finite-difference methods based on high-order stencils are widely used in seismic simulations, weather forecasting, computational fluid dynamics, and other scientific applications. Achieving HPC-level stencil computations on one architecture is challenging, porting to other architectures without sacrificing performance requires significant effort, especially in this golden age of many distinctive architectures. To help developers achieve performance, portability, and productivity with stencil computations, we developed StencilPy. With StencilPy, developers write stencil computations in a high-level domain-specific language, which promotes productivity, while its backends generate efficient code for existing and emerging architectures, including modern many-core CPUs (such as AMD Genoa-X, Fujitsu A64FX, and Intel Sapphire Rapids), latest generations of GPUs (including NVIDIA H100 and A100, AMD MI200, and Intel Ponte Vecchio), and accelerators (including Cerebras and STX). StencilPy demonstrates promising performance results on par with hand-written code, maintains cross-architectural performance portability, and enhances productivity. Its modular design enables easy configuration, customization, and extension. A 25-point star-shaped stencil written in StencilPy is one-quarter of the length of a hand-crafted CUDA code and achieves similar performance on an NVIDIA H100 GPU. In addition, the same kernel written using our tool is 7x shorter than hand-optimized code written in Cerebras Software Language (CSL), and it delivers comparable performance that code on a Cerebras CS-2.

cs.DC↗

arXiv2023

Distributed Reinforcement Learning for Molecular Design: Antioxidant case

Deep reinforcement learning has successfully been applied for molecular discovery as shown by the Molecule Deep Q-network (MolDQN) algorithm. This algorithm has challenges when applied to optimizing new molecules: training such a model is limited in terms of scalability to larger datasets and the trained model cannot be generalized to different molecules in the same dataset. In this paper, a distributed reinforcement learning algorithm for antioxidants, called DA-MolDQN is proposed to address these problems. State-of-the-art bond dissociation energy (BDE) and ionization potential (IP) predictors are integrated into DA-MolDQN, which are critical chemical properties while optimizing antioxidants. Training time is reduced by algorithmic improvements for molecular modifications. The algorithm is distributed, scalable for up to 512 molecules, and generalizes the model to a diverse set of molecules. The proposed models are trained with a proprietary antioxidant dataset. The results have been reproduced with both proprietary and public datasets. The proposed molecules have been validated with DFT simulations and a subset of them confirmed in public "unseen" datasets. In summary, DA-MolDQN is up to 100x faster than previous algorithms and can discover new optimized molecules from proprietary and public antioxidants.

cs.LG↗

arXiv2023

STRIDE: Structure-guided Generation for Inverse Design of Molecules

Machine learning and especially deep learning has had an increasing impact on molecule and materials design. In particular, given the growing access to an abundance of high-quality small molecule data for generative modeling for drug design, results for drug discovery have been promising. However, for many important classes of materials such as catalysts, antioxidants, and metal-organic frameworks, such large datasets are not available. Such families of molecules with limited samples and structural similarities are especially prevalent for industrial applications. As is well-known, retraining and even fine-tuning are challenging on such small datasets. Novel, practically applicable molecules are most often derivatives of well-known molecules, suggesting approaches to addressing data scarcity. To address this problem, we introduce $\textbf{STRIDE}$, a generative molecule workflow that generates novel molecules with an unconditional generative model guided by known molecules without any retraining. We generate molecules outside of the training data from a highly specialized set of antioxidant molecules. Our generated molecules have on average 21.7% lower synthetic accessibility scores and also reduce ionization potential by 5.9% of generated molecules via guiding.

physics.chem-ph↗

arXiv2023

Deep Compressed Learning for 3D Seismic Inversion

We consider the problem of 3D seismic inversion from pre-stack data using a very small number of seismic sources. The proposed solution is based on a combination of compressed-sensing and machine learning frameworks, known as compressed-learning. The solution jointly optimizes a dimensionality reduction operator and a 3D inversion encoder-decoder implemented by a deep convolutional neural network (DCNN). Dimensionality reduction is achieved by learning a sparse binary sensing layer that selects a small subset of the available sources, then the selected data is fed to a DCNN to complete the regression task. The end-to-end learning process provides a reduction by an order-of-magnitude in the number of seismic records used during training, while preserving the 3D reconstruction quality comparable to that obtained by using the entire dataset.

physics.geo-ph↗

arXiv2023

Joint inversion of Time-Lapse Surface Gravity and Seismic Data for Monitoring of 3D CO$_2$ Plumes via Deep Learning

We introduce a fully 3D, deep learning-based approach for the joint inversion of time-lapse surface gravity and seismic data for reconstructing subsurface density and velocity models. The target application of this proposed inversion approach is the prediction of subsurface CO2 plumes as a complementary tool for monitoring CO2 sequestration deployments. Our joint inversion technique outperforms deep learning-based gravity-only and seismic-only inversion models, achieving improved density and velocity reconstruction, accurate segmentation, and higher R-squared coefficients. These results indicate that deep learning-based joint inversion is an effective tool for CO$_2$ storage monitoring. Future work will focus on validating our approach with larger datasets, simulations with other geological storage sites, and ultimately field data.

physics.geo-ph↗

arXiv2023

Learning CO$_2$ plume migration in faulted reservoirs with Graph Neural Networks

Deep-learning-based surrogate models provide an efficient complement to numerical simulations for subsurface flow problems such as CO$_2$ geological storage. Accurately capturing the impact of faults on CO$_2$ plume migration remains a challenge for many existing deep learning surrogate models based on Convolutional Neural Networks (CNNs) or Neural Operators. We address this challenge with a graph-based neural model leveraging recent developments in the field of Graph Neural Networks (GNNs). Our model combines graph-based convolution Long-Short-Term-Memory (GConvLSTM) with a one-step GNN model, MeshGraphNet (MGN), to operate on complex unstructured meshes and limit temporal error accumulation. We demonstrate that our approach can accurately predict the temporal evolution of gas saturation and pore pressure in a synthetic reservoir with impermeable faults. Our results exhibit a better accuracy and a reduced temporal error accumulation compared to the standard MGN model. We also show the excellent generalizability of our algorithm to mesh configurations, boundary conditions, and heterogeneous permeability fields not included in the training set. This work highlights the potential of GNN-based methods to accurately and rapidly model subsurface flow with complex faults and fractures.

cs.LG↗

arXiv2023

Massively Distributed Finite-Volume Flux Computation

Designing large-scale geological carbon capture and storage projects and ensuring safe long-term CO2 containment - as a climate change mitigation strategy - requires fast and accurate numerical simulations. These simulations involve solving complex PDEs governing subsurface fluid flow using implicit finite-volume schemes widely based on Two-Point Flux Approximation (TPFA). This task is computationally and memory expensive, especially when performed on highly detailed geomodels. In most current HPC architectures, memory hierarchy and data management mechanism are insufficient to overcome the challenges of large scale numerical simulations. Therefore, it is crucial to design algorithms that can exploit alternative and more balanced paradigms, such as dataflow and in-memory computing. This work introduces an algorithm for TPFA computations that leverages effectively a dataflow architecture, such as Cerebras CS2, which helps to significantly minimize memory bottlenecks. Our implementation achieves two orders of magnitude speedup compared to multiple reference implementations running on NVIDIA A100 GPUs.

cs.MS↗