Contents Menu Expand Light mode Dark mode Auto light/dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
onnx-extended 0.3.0 documentation
Logo
onnx-extended 0.3.0 documentation

Contents

  • Tutorial
    • CReferenceEvaluator
    • Cython Binding of onnxruntime
    • Custom Kernels for onnxruntime
    • Focus on operators optimization
      • Using C implementation of operator Conv
      • How float format has an impact on speed computation
      • Measuring Gemm performance with different input and output tests
      • Measuring performance about Gemm with onnxruntime
      • Profiles a simple onnx graph including a singleGemm
      • Compares implementations of Einsum
      • Fusing multiplication operators on CUDA
      • TreeEnsemble optimization
      • TreeEnsemble, dense, and sparse
    • Many Tools to help investigating issues
      • External Data and Big Models
      • Onnx Manipulations
      • Quantization
      • Statistics
      • Profiling onnxruntime
      • Debug Intermediate Results
      • Compare multiple versions of onnxruntime
      • Trees
    • Build from source
      • Build with cython
      • Build with pybind11
      • Build with CUDA
      • Build with onnxruntime
      • Readings
    • Experiments about parallelization
      • Measuring CPU performance
  • command lines
  • API
    • onnx_extended.__init__.py
    • onnx_extended.ext_test_case
    • onnx_extended.memory_peak
    • onnx_extended.helper
    • onnx_extended.ortcy
    • onnx_extended.ortops
      • onnx_extended.ortops.tutorial.cpu
      • onnx_extended.ortops.tutorial.cuda
      • onnx_extended.ortops.optim.cpu
      • onnx_extended.ortops.optim.cuda
    • onnx_extended.plotting
    • onnx_extended.reference
    • validation
      • validation.cpu
      • validation.cuda
      • validation.bench_trees
      • validation.bench_trees
    • tools
      • onnx_extended.tools.onnx_io
      • onnx_extended.tools.einsum
      • onnx_extended.tools.graph
      • onnx_extended.tools.graph.onnx_graph_transformer
      • onnx_extended.tools.onnx_inline
      • onnx_extended.tools.onnx_nodes
      • onnx_extended.tools.stats_nodes
      • onnx_extended.tools
  • Technical Details
    • Install CUDA on WSL (2)
    • Useful commands on Linux
    • Gemm and storage order
    • 2023-09-05 - version GLIBCXX_3.4.30 not found
  • ONNX Benchmarks
  • Examples Gallery
    • Measuring CPU performance
    • Using C implementation of operator Conv
    • Measuring onnxruntime performance against a cython binding
    • Evaluating random access for sparse
    • Measuring performance of TfIdfVectorizer
    • Measuring Gemm performance with different input and output tests
    • Fuse Tranpose and Cast on CUDA
    • Compares implementations of Einsum
    • Fusing multiplication operators on CUDA
    • How float format has an impact on speed computation
    • TreeEnsemble optimization
    • Optimizing ScatterND operator on CUDA
    • Optimizing Masked ScatterND operator on CUDA
    • TreeEnsemble, dense, and sparse
    • Profiles a simple onnx graph including a singleGemm
    • Measuring performance about Gemm with onnxruntime
    • Evaluate different implementation of TreeEnsemble

More

  • Change Logs
  • LICENSE
Back to top
View this page

Focus on operators optimization¶

Conv

  • Using C implementation of operator Conv
  • How float format has an impact on speed computation

Gemm

  • Measuring Gemm performance with different input and output tests
  • Measuring performance about Gemm with onnxruntime
  • Profiles a simple onnx graph including a singleGemm

Einsum

  • Compares implementations of Einsum

Mul

  • Fusing multiplication operators on CUDA

TreeEnsemble

  • TreeEnsemble optimization
  • TreeEnsemble, dense, and sparse
Next
Using C implementation of operator Conv
Previous
Custom Kernels for onnxruntime
Copyright © 2023-2024, Xavier Dupré
Made with Sphinx and @pradyunsg's Furo