Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.17167

PRIM: Energy- and Endurance-Aware Compiler Optimization for Digital Compute in Non-volatile Memory

Patrick Miller·Ulya R. Karpuzcu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Compute-in-Memory (CiM) is an alternative computing paradigm that circumvents the memory bandwidth bottleneck. Variants utilizing non-volatile memory cells (NVCiM) to perform Boolean operations directly within memory arrays offer significant density and energy-efficiency advantages. Fully realizing this potential, however, requires NVCiM-specific compiler optimizations. In conventional digital NVCiM systems, an output cell must be written -- or preset -- to an operation-specific value before any Boolean operation can occur. Preset-induced extra writes can degrade energy efficiency and cell endurance, often to the point of negating CiM's efficiency gains. In this paper, we introduce PRIM (Preset Reduction In Memory), a compiler optimization framework tailored for digital NVCiM that effectively minimizes preset overhead without compromising computational accuracy or architectural complexity. Unlike existing optimization approaches, PRIM is not restricted to specific types of Boolean operations. Experimental results show that PRIM can reduce execution time and energy consumption by up to 50/% and 44/%, respectively, while boosting cell endurance by up to 50/%.

Explore related subjects

cs.ET

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Patrick Miller, Ulya R. Karpuzcu. 2026-10-12. PRIM: Energy- and Endurance-Aware Compiler Optimization for Digital Compute in Non-volatile Memory. https://arxiv.org/abs/2610.17167

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

KEEP EXPLORING

Related papers

arXiv2026

Source Distance and Source Strength Estimation in Turbulent Flow: Exploiting Molecule Degradation Diversity

Locating an odor source and estimating its strength are central problems in nature and engineering. For example, an insect may decide whether a food source is worth traveling to based on its distance and how many molecules it emits. Similarly, a drone or sensor network may need to locate a pipe leak and quantify how much chemical is released. Such tasks are highly challenging due to complex turbulent propagation dynamics. While source distance and strength estimation have been extensively investigated for sources releasing a single molecule type, in both turbulent and non-turbulent flow, many odor sources release multiple molecule types. We investigate whether considering multiple molecule types can aid source distance and strength estimation in challenging turbulent flow. We exploit that different molecule types in a mixture degrade at different rates in the atmosphere. Consequently, the relative abundance of the molecule types observed at a receiver provides information about the source distance that a single molecule type does not. Since this relative abundance is independent of the source strength, it resolves the distance-strength ambiguity inherent in the observed signal intensity and thus also improves strength estimation. Building on this, we propose heuristic low-complexity and learning-based schemes that combine the relative abundance of different molecule types with established features such as mean concentration and whiff duration. All schemes are validated via simulations of turbulent molecule propagation. The low-complexity schemes can achieve estimation quality competitive with learning-based schemes that rely only on a single molecule type, while the proposed learning-based schemes outperform their single-type counterparts. Molecule mixtures can therefore support goal-oriented tasks such as source distance and strength estimation even in challenging turbulent flow.

cs.ET↗
arXiv2026

Two-State Dynamical Synapses as a Physical Substrate for Equilibrium Propagation

Equilibrium Propagation (EqProp) updates each synapse by comparing a local term at the free and nudged equilibria. Because these two values occur at different times, a physical implementation requires temporary local memory. We show that this memory can emerge from a two-timescale synaptic model in which neural and volatile synaptic dynamics are jointly derived from a single energy function. A volatile state $w$ relaxes toward the product of the pre- and postsynaptic activities, while a non-volatile state $M$ stores the learned parameter. At equilibrium, $w$ equals the local term entering the EqProp update. Using its net change between phases implements phase-based EqProp, while transferring its successive changes during nudging yields continual EqProp, in which the temporal comparison is carried by the synaptic dynamics themselves. On MNIST with a single-hidden-layer network, the phase-based model reaches $2.01 \pm 0.09\%$ test error versus $2.00 \pm 0.13\%$ for standard EqProp, and the continual model reaches $2.24 \pm 0.11\%$ versus $2.28 \pm 0.16\%$ for continual EqProp. The framework further specifies the dynamical requirements that a volatile--non-volatile synaptic device must satisfy to implement this learning mechanism.

cs.ET↗
arXiv2026

GPU-Accelerated Quantum Annealing-Inspired UAV Path Planning for Smart Agriculture

With the rapid advancement of smart agriculture, Unmanned Aerial Vehicles (UAVs) have become indispensable for efficient coverage and path planning in grid-mapped agricultural fields. However, optimizing UAV flight paths in large-scale environments remains a complex Nondeterministic Polynomial-time (NP)-hard problem. Traditional path planning methods are often constrained by local optima, limited scalability, and slow convergence, which significantly restrict their effectiveness in solving large-scale problems. To address these limitations, this paper proposes a novel optimization framework utilizing a Graphics Processing Unit (GPU)-parallelized Ising solver. Our method mimics the operational principles of quantum annealing on GPU hardware, enabling rapid search for the minimum-energy state of Ising models. Unlike physical quantum devices, which are often constrained by the number of qubits, our approach leverages the Fixstars Amplify (FA) platform to perform parallel annealing on highly parallelized GPUs. This enables the simultaneous evaluation of thousands of potential path candidates and vast state transitions. By leveraging large-scale parallel processing, this framework's core strength lies in minimizing computation time even as the problem scale increases. Simulation results demonstrate that our proposed method consistently identifies superior flight paths while maintaining stable computational performance compared with the genetic algorithm and simulated annealing method.

cs.ET↗