Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1809.04028

p-Bits for Probabilistic Spin Logic

Kerem Y. Camsari·Brian M. Sutton·Supriyo Datta
View original source ↗Read source document ↗Export metadata ↓

Abstract

We introduce the concept of a probabilistic or p-bit, intermediate between the standard bits of digital electronics and the emerging q-bits of quantum computing. We show that low barrier magnets or LBM's provide a natural physical representation for p-bits and can be built either from perpendicular magnets (PMA) designed to be close to the in-plane transition or from circular in-plane magnets (IMA). Magnetic tunnel junctions (MTJ) built using LBM's as free layers can be combined with standard NMOS transistors to provide three-terminal building blocks for large scale probabilistic circuits that can be designed to perform useful functions. Interestingly, this three-terminal unit looks just like the 1T/MTJ device used in embedded MRAM technology, with only one difference: the use of an LBM for the MTJ free layer. We hope that the concept of p-bits and p-circuits will help open up new application spaces for this emerging technology. However, a p-bit need not involve an MTJ, any fluctuating resistor could be combined with a transistor to implement it, while completely digital implementations using conventional CMOS technology are also possible. The p-bit also provides a conceptual bridge between two active but disjoint fields of research, namely stochastic machine learning and quantum computing. First, there are the applications that are based on the similarity of a p-bit to the binary stochastic neuron (BSN), a well-known concept in machine learning. Three-terminal p-bits could provide an efficient hardware accelerator for the BSN. Second, there are the applications that are based on the p-bit being like a poor man's q-bit. Initial demonstrations based on full SPICE simulations show that several optimization problems including quantum annealing are amenable to p-bit implementations which can be scaled up at room temperature using existing technology.

Explore related subjects

cs.ETcond-mat.dis-nn

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Kerem Y. Camsari, Brian M. Sutton, Supriyo Datta. 2019-03-11. p-Bits for Probabilistic Spin Logic. https://doi.org/10.1063/1.5055860

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

KEEP EXPLORING

Related papers

arXiv2026

Beyond HBM-on-GPU: Thermal Design Envelope for 3D Volumetric DRAM-on-GPU Integration

The scaling of GPUs for AI and HPC workloads is increasingly constrained by the capacity, bandwidth, and thermal limits of both 2.5D HBM-GPU and direct-stacked 3D HBM-on-GPU integration. This work establishes the thermal design envelope for 3D volumetric DRAM-on-GPU integration, in which vertically oriented DRAM dies and interleaved cooling cavities reshape heat flow and memory interfacing above the GPU. Using a package-level thermal model anchored to a consistent HBM-on-GPU baseline and driven by a realistic reticle-scale non-uniform GPU power map, we quantify the key parameters governing thermal feasibility. Stack height is the dominant limiter of peak temperature, while cooling-cavity conductivity shifts the feasible region, and mold insertion and stack orientation further modulate thermal behavior. A distributed memory-controller and network-on-chip tier introduces only a moderate thermal penalty. Although die-level parallelism increases bandwidth, the reduction in simulated training time saturates once execution becomes compute-bound. These results define a bounded co-design space across bandwidth, capacity, and thermal constraints for 3D volumetric DRAM-on-GPU integration.

cs.ET↗
arXiv2026

Droop-Aware Foundation Model Power Flow

This paper develops a droop-aware extension of the GridFM power systems foundation model, embedding droop gains and frequency/voltage deadband parameters as per-bus node features to enable control-aware AC power-flow analysis. Existing power-flow datasets encode only static electrical features, conflating operating points from qualitatively different control regimes; this work resolves that gap by exposing droop and deadband parameters as structured node features, with deadband discontinuities handled through a smooth tanh approximation that preserves solver differentiability. A transformer-based graph neural network is pre-trained on masked reconstruction and fine-tuned on the resulting control-aware datasets. The framework is validated against PSCAD electromagnetic-transient simulations on a two-bus system (0.11% maximum steady-state error) and cross-validated against an independent PyPower droop solver on the IEEE 24-bus RTS. On the 24-bus system the surrogate attains R2 = 0.9996 for active generation and 0.0015 p.u. voltage-magnitude RMSE; scalability is confirmed on the IEEE 300-bus system (0.0036 p.u. RMSE, R2 = 0.9841 for voltage magnitude across 299,700 predictions). A three-mode control study further shows that the deadband widens the control-error distribution while leaving total droop compensation unchanged, establishing deadband width as an actionable node-level design feature.

cs.ET↗
arXiv2026

GNN-based Path-aware multi-view Circuit Learning for Technology Mapping

Traditional technology mapping suffers from systemic inaccuracies in delay estimation due to its reliance on abstract, technology-agnostic delay models that fail to capture the nuanced timing behavior behavior of real post-mapping circuits. To address this fundamental limitation, we introduce GPA(graph neural network (GNN)-based Path-Aware multi-view circuit learning), a novel GNN framework that learns precise, data-driven delay predictions by synergistically fusing three complementary views of circuit structure: And-Inverter Graphs (AIGs)-based functional encoding, post-mapping technology emphasizes critical timing paths. Trained exclusively on real cell delays extracted from critical paths of industrial-grade post-mapping netlists, GPA learns to classify cut delays with unprecedented accuracy, directly informing smarter mapping decisions. Evaluated on the 19 EPFL combinational benchmarks, GPA achieves 19.9%, 2.1% and 4.1% average delay reduction over the conventional heuristics methods (techmap, MCH) and the prior state-of-the-art ML-based approach SLAP, respectively-without compromising area efficiency.

cs.ET↗