sandialabs/cross-sim

How sandialabs/cross-sim works

CrossSim is a Python accuracy simulator and co-design tool for analog in-memory computing, with a NumPy-like core API, signal-processing algorithms, and a neural-network inference interface. In the principal workflow, an engineer configures hardware parameters, converts a Keras or PyTorch model to analog layers, and runs inference through CrossSim cores to assess algorithm accuracy under device and circuit effects. Application examples also cover ADC/DAC calibration and profiling. The graph reflects documented capabilities and indexed references; unsampled implementation details are represented only where the tree or README supports them.

Main entry points: dnn Inference Examples · analog_core.py Analog Core · interface Inference Interface · dnn_inference_params.py DNN Parameters

Components 20

Applications

Inference Examples applications/dnn
Inference Interface applications/dnn/inference/interface
ADC/DAC Calibration applications/dnn/inference/adc
Data Preparation applications/dnn/inference/helpers/imagenet_preprocess
DNN Parameters applications/dnn/dnn_inference_params.py
Inference Evaluation applications/dnn/inference/run_inference.py

DNN Interfaces

PyTorch Conversion simulator/algorithms/dnn/torch/convert.py
PyTorch Analog Layers simulator/algorithms/dnn/torch/conv.py
Keras Conversion simulator/algorithms/dnn/keras/convert.py

Simulation Engine

Analog Core simulator/cores/analog_core.py
Core Variants simulator/cores/bitsliced_core.py
Core Parameters simulator/parameters/core_parameters.py
Compute Backend simulator/backend/backend.py

Hardware Models

Crossbar Arrays simulator/circuits/array/iarray.py
ADC and DAC simulator/circuits/adc/iadc.py
Device Models simulator/devices/idevice.py

Algorithms

DNN Operations simulator/algorithms/dnn/dnn.py
Analog Convolution simulator/algorithms/dnn/analog_convolution.py
DFT Algorithm simulator/algorithms/dsp/dft.py

Other components

Engineer

Connections 25

Engineer → Inference Examples: selects model
Inference Examples → DNN Parameters: configures hardware applications/dnn/torch/cifar10_resnet/inference_cifar10_resnet.py
Inference Examples → PyTorch Conversion: converts model applications/dnn/torch/cifar10_resnet/inference_cifar10_resnet.py
Inference Examples → Keras Conversion: converts model applications/dnn/keras/cifar10_resnet/inference_cifar10_resnet.py
Inference Examples → Inference Interface: uses interface applications/dnn/inference/interface/inference_net.py
Inference Examples → Data Preparation: prepares inputs
Inference Interface → Inference Evaluation: runs inference
Inference Interface → DNN Parameters: configures parameters applications/dnn/inference/interface/inference_net.py
ADC/DAC Calibration → Inference Examples: sets ADC/DAC ranges
DNN Parameters → Core Parameters: sets core settings applications/dnn/dnn_inference_params.py
PyTorch Conversion → PyTorch Analog Layers: replaces layers simulator/algorithms/dnn/torch/convert.py
PyTorch Analog Layers → Analog Convolution: delegates convolution simulator/algorithms/dnn/torch/conv.py
Keras Conversion → Analog Core: creates analog layers
DNN Operations → Analog Core: uses analog cores simulator/algorithms/dnn/dnn.py
DNN Operations → Analog Convolution: uses convolution simulator/algorithms/dnn/dnn.py
DFT Algorithm → Analog Core: uses analog core applications/dsp/2d_dft_example.py
Analog Core → Core Variants: supports core styles simulator/cores/analog_core.py
Analog Core → Crossbar Arrays: simulates array operations simulator/cores/analog_core.py
Analog Core → Core Parameters: reads configuration simulator/cores/analog_core.py
Core Variants → ADC and DAC: uses ADC/DAC models simulator/cores/bitsliced_core.py
Crossbar Arrays → Compute Backend: uses compute backend simulator/circuits/array/iarray.py
ADC and DAC → Compute Backend: uses compute backend simulator/circuits/adc/iadc.py
Device Models → Compute Backend: uses compute backend simulator/devices/idevice.py
Core Parameters → Device Models: configures device effects
Inference Evaluation → Engineer: reports accuracy

More Jupyter Notebook diagrams: mikexcohen/linalgbook · pszemraj/vid2cleantxt · answerdotai/fastlite · devmaxxing/videocr-paddleocr · krishnaik06/generative-ai-with-cloud

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·