Skip to main content

Crate sc_neurocore_engine

Crate sc_neurocore_engine 

Source

ModulesΒ§

adc_to_spike
Bit-true integer reference for the ADC-to-spike window rate-code encoder.
adc_to_spike_binding πŸ”’
Python binding for decimating ADC samples into exact integer rate codes.
analysis
attention
Stochastic Attention
bitstream
Bitstream Operations
bitstream_binding πŸ”’
Python bindings for packing, unpacking, counting, and encoding bitstreams.
brunel
Fused Brunel balanced network simulation in fixed-point Q8.8 arithmetic.
brunel_binding πŸ”’
Python binding for the fixed-point Brunel network simulator.
coba_lif_binding πŸ”’
Python binding for the Brette et al. 2007 conductance-based LIF cell.
connectome
Biologically plausible connectivity generators.
conv
SC 2D convolutional layer using probability-domain multiplication.
cordiv
CORDIV: stochastic computing divider.
cordiv_binding πŸ”’
Python bindings for CORDIV stochastic division and stream-length planning.
cortical_column
5-population cortical column (Douglas & Martin 2004). L4 (thalamic) β†’ L2/3 exc ↔ L2/3 inh β†’ L5 (output) β†’ L6 (feedback β†’ L4).
cortical_column_binding πŸ”’
Python binding for the layered cortical-column simulator.
cortical_inject
Per-row-parallel CSR sparse matrix-vector add for the Potjans CorticalColumn block-CSR injection path.
cortical_inject_binding πŸ”’
Python bindings for per-row-parallel cortical-column CSR injection.
dcls_binding πŸ”’
Python binding for the bit-true batched DCLS-max tent contraction.
dense_layer_binding πŸ”’
Python binding for the stochastic-computing dense layer.
dna
High-performance DNA strand displacement pipeline.
ei_network
Fused E-I balanced LIF network simulation in f64 arithmetic.
ei_network_binding πŸ”’
Python binding for the seeded excitatory/inhibitory network simulator.
encoder
Stochastic Encoders
escape_rate_binding πŸ”’
Python binding for the Gerstner 2000 stochastic-threshold cell.
evo
Accelerates evolutionary substrate hot paths:
evolution_binding πŸ”’
Python bindings for population-level evolutionary operators.
exp_if_binding πŸ”’
Python binding for the exponential integrate-and-fire neuron.
fault
Hardware fault injection for robustness testing.
fault_binding πŸ”’
Python bindings for deterministic byte-level hardware fault injection.
fixed_point_lif_binding πŸ”’
Python bindings for sequential and parallel fixed-point LIF batch kernels.
fusion
Multi-modal fusion layer using stochastic multiplexing.
grad
graph
Stochastic Graph Layer
hdc_binding πŸ”’
Python binding for the packed binary vector used by HDC/VSA operations.
iqif_binding πŸ”’
Python binding for the Wu et al. (2021) integer QIF neuron.
ir
SC Compute Graph IR
izhikevich2007_binding πŸ”’
Python binding for the NeuroML Izhikevich 2007 model.
izhikevich_binding πŸ”’
Python binding for the floating-point Izhikevich neuron.
kuramoto_binding πŸ”’
Python binding and validation contracts for the Kuramoto solver.
layer
Dense Stochastic Layer
learning_bindings πŸ”’
Registers the responsibility-specific differentiable-learning bindings.
lgssm
Rust implementation of the Kalman filter forward pass for a linear Gaussian state-space model.
lgssm_binding πŸ”’
Python binding for the Linear Gaussian state-space model Kalman filter.
matrix_inputs_binding πŸ”’
Shared matrix parsing and row reshaping for Python learning and solver bindings.
mixed_dense_binding πŸ”’
Python binding for the bit-true Q8.8 by Q16.16 dense contraction.
network_runner
High-performance network simulation backend.
network_runner_binding πŸ”’
Python bindings for heterogeneous network execution and named-model batches.
neuron
Stable composition surface for the v3 engine’s foundational neuron models.
neurons
ollivier_ricci_binding πŸ”’
Python binding for discrete Ollivier-Ricci graph curvature.
optimizer
Accelerates SC-Optimizer hot paths:
optimizer_binding πŸ”’
Python bindings for stochastic-computing hardware design-space optimisation.
partition
Kernighan-Lin local refinement for the chiplet hierarchical partitioner. Mirrors HierarchicalPartitioner._refine step-for-step so the Rust output is bit-identical to the Python reference (the algorithm is fully deterministic given a CSR adjacency, a list of per-edge |scc| weights, vertex weights, an initial part_map and (kl_iterations, correlation_penalty, n_parts)).
partition_binding πŸ”’
Python binding for correlation-aware Kernighan-Lin partition refinement.
phi
Barrett & Seth 2011 geometric Phi under Gaussian assumption. Phi* = MI(past; future) - max_partition sum MI(past_k; future_k)
phi_binding πŸ”’
Python binding for Gaussian integrated-information estimation.
photonic
High-performance photonic network-on-chip primitives.
ping
Step-by-step parity with PINGCircuit.step in src/sc_neurocore/network/gamma_oscillation.py.
ping_binding πŸ”’
Python binding for the BΓΆrgers-Kopell PING circuit step kernel.
poisson_binding πŸ”’
Python binding for the homogeneous Poisson binary-bin generator.
predictive_coding
Predictive coding via XOR + popcount in packed bitstream domain.
predictive_coding_binding πŸ”’
Python bindings for packed prediction error and lossless spike prediction codecs.
pyo3_neurons
PyO3 wrappers and compatibility exports for all neuron models.
quantum
High-performance quantum annealing primitives.
rall_dendrite
Compartmental dendritic tree with Rall’s 3/2 power rule. Distal β†’ proximal propagation with inter-compartment coupling.
rall_dendrite_binding πŸ”’
Python binding for the branched Rall cable-model simulator.
recorder
Spike recording and statistics.
recurrent
SC recurrent/reservoir layer (echo state network).
rk4_neurons
Explicit RK4 ports for the priority neuron integrator paths.
runtime_control_binding πŸ”’
Python bindings for runtime SIMD discovery and Rayon thread-pool control.
sc_inference
Stochastic forward pass over caller-owned packed weight bitstreams.
sc_inference_binding πŸ”’
Python binding for inference over caller-owned packed stochastic weights.
scpn
scpn_metrics_binding πŸ”’
Python binding for aggregate SCPN coherence metrics.
simd
SIMD Popcount Dispatch
sobol
Sobol quasi-random bitstream generator.
stdp_synapse_binding πŸ”’
Python binding for the fixed-point spike-timing-dependent plasticity synapse.
supervisor
Pure-Rust supervisory execution and verification pipeline.
synapses
Stochastic STDP Synapse
topology
Rust implementation of discrete Ollivier-Ricci curvature on a coupling graph.
wilson_cowan
Batch parity with WilsonCowanUnit.step in src/sc_neurocore/neurons/models/wilson_cowan.py (Wilson & Cowan 1972, Biophys. J. 12:1–24).
wilson_cowan_binding πŸ”’
Python binding for the Wilson-Cowan 1972 excitatory/inhibitory rate model.
wong_wang
Explicit-Euler NMDA dynamics with the published AMPA Ornstein-Uhlenbeck current noise. The deterministic sample-taking boundary is shared by the scalar engine class and the batch accelerator.

StructsΒ§

PyBitStreamTensor
Python wrapper for a packed binary hypervector.

FunctionsΒ§

sc_neurocore_engine πŸ”’
SC-NeuroCore ─ High-Performance Rust Engine