Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.23964

A Unified Intermediate Representation and Execution Architecture for Heterogeneous and Distributed Neural Simulation

Xinjun Li
View original source ↗Read source document ↗Export metadata ↓

Abstract

Equation-based neural modeling offers flexibility, but executing models across processors and nodes requires explicit control of order, ownership, and numerical behavior. We present brian2-atlas, a rebuilt execution architecture retaining Brian2's modeling interface and bringing heterogeneous and distributed targets under a common model-to-execution contract. Its unified intermediate representation, AtlasIR, describes typed state, clocks, schedules, effects, events, and random-stream identities, and is checked by an independent Rust validator. Target-specific implementations support Rust CPU execution, CUDA and Apple Metal GPUs, browser WebAssembly, and MPI within declared contracts. In a repeated full-connectome CPU cohort, the best measured Rust configuration reduced simulation-and-recording time by 5.43-fold relative to the best measured Brian2 C++ configuration on the same Linux host. A 298.9-million-synapse model completed on a 16 GB laptop while the compared C++ preparation path exceeded its controlled memory budget. Distributed execution completed 100.5 seconds of model time for 4,129,924 neurons and 24.1 billion recurrent synapses on four nodes and 32 ranks. A five-point synthetic weak-scaling study reached 860 million neurons and 860 billion recurrent connections for 100 ms on 30 hosts and 240 physical worker cores. These establish tested capacity configurations rather than statistical equivalence or a matched speed advantage over NEST. Published-model workflows extend validation to explicit NMDA dynamics and contextual dendritic plasticity, with up to 2.10-fold acceleration in a matched eight-core NMDA cohort. The results characterize semantic, numerical, and resource boundaries rather than universal compatibility or performance superiority.

Explore related subjects

cs.CE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xinjun Li. 2026-10-10. A Unified Intermediate Representation and Execution Architecture for Heterogeneous and Distributed Neural Simulation. https://doi.org/10.5281/zenodo.23273257

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Mode-Weighted Transport Certificates for State-Dependent Reflected Switching Diffusions

State-dependent switching diffusions can contract in law even when individual modes are expansive. We establish a computable, constant-one contraction certificate on $\mathbb{R}^n$ and compact convex domains with normal reflection. The mode-weighted transport cost combines spatial separation with a discrete graph penalty and retains spatial dependence when the modes differ. A synchronous Brownian coupling and a maximal coupling of jump clocks in equal modes lead to separate equal- and unequal-mode generator inequalities. We give a complete regularization argument for the nonsmooth cost, including the drift and jump errors, the sign of reflection, and the limiting Itô-Dynkin calculation. A resolvent proof transfers contraction to probability-valued weak solutions of the no-flux Fokker-Planck-Kolmogorov system, while an explicit Foster-Lyapunov condition ensures existence and uniqueness of an invariant law on the whole space. For fixed weight ordering and decay rate, certificate synthesis is a semi-infinite linear feasibility problem; on compact domains, a Lipschitz-buffered finite mesh provides a rigorous test. One-dimensional and planar examples illustrate the certificate and its numerical verification.

cs.CE↗
arXiv2026

VeriFin: A Neurosymbolic Framework for Verifying LLM-Generated Financial Claims

Large language models often produce plausible numerical claims from financial filings while using the wrong reporting period, unit, line item, or formula. Verifying such claims requires more than rechecking arithmetic: a verifier must ground the relevant facts, establish the authorized calculation, and determine whether the candidate value follows from both. We propose VeriFin, a neurosymbolic verification framework for numerical financial question answering that grounds operands in filed XBRL facts, derives calculations from the question, filing linkbases, or documented metric definitions, and checks claims using Z3. When a claim is inconsistent, solver-derived unsatisfiable cores identify the conflicting facts, formula, and candidate value, enabling targeted repair. We evaluate VeriFin on XBRLFiling, a new 600-question benchmark constructed from 10-K filings of 28 U.S. companies, and on FinanceBench. On fixed candidate pools shared by all verification methods, VeriFin accepts none of the incorrect claims, whereas the baselines accept 6 to 92 incorrect claims on XBRLFiling's 600 claims and 4 to 21 incorrect claims on FinanceBench's 67 claims. The zero false-accept result persists across multiple answer-generator models. Solver-derived feedback further improves repair, achieving up to 69.9% recovery among true catches. These results show that source-grounded symbolic verification can provide a reliable and auditable acceptance control for LLM-generated financial claims.

cs.CE↗
arXiv2026

A decomposition-integration framework coupling singular spectrum analysis with a volatility-adaptive LSTM for stock price forecasting

Financial time series exhibit multi-scale, high-noise, and non-stationary volatility dynamics. Decomposition--integration frameworks built on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) have advanced this field, yet existing CEEMDAN hybrids remain unstable: high-frequency mode mixing contaminates downstream predictors, and the heterogeneous volatility of decomposed components is not matched by any volatility-adaptive mechanism. To address these gaps, this paper proposes CEEMDAN-SE-SSA-VMGL. CEEMDAN adaptively decomposes the original series, and sample-entropy-driven K-means clustering groups the intrinsic mode functions into high-, mid-, and low-frequency and residual components. Singular spectrum analysis (SSA) is then applied to the high-frequency group, whose singular-value decomposition of the trajectory matrix and principal-component reconstruction decouple intertwined pseudo-oscillatory modes and alleviate mode mixing. We further design a plug-and-play robust LSTM variant, the volatility-modulated GARCH-LSTM (VMGL), which embeds a differentiable GARCH(1,1) layer inside the LSTM cell as a risk gate; the estimated conditional volatility multiplicatively scales the forget-gate activation, letting memory decay adapt to the instantaneous volatility while remaining fully end-to-end trainable. Component predictions are linearly combined. On five US and Chinese financial series (CSI 300, CSI 500, AAPL, GOOGL, S&P 500), the proposed model is compared with eleven benchmark architectures, lowering the forecasting error by 9% to 24% relative to the best benchmark and by 60% to 70% relative to a standard LSTM. Diebold--Mariano and model-confidence-set (MCS) tests confirm the statistical significance and stability of the gains, spectral analyses verify the SSA denoising efficacy, and backtesting demonstrates the framework's economic utility.

cs.CE↗