How tongkaio/cuda_kernel_samples works
CUDA_Kernel_Samples is an educational collection of CUDA operator implementations and optimization examples, not a single application pipeline. The principal workflow is a learner consulting the guide, choosing an operator, and studying its implementations and GPU concepts. The README identifies elementwise, GEMV, reduction, SGEMM, transpose, and introductory examples; source excerpts do not show runtime call relationships among them, so the graph represents documented navigation rather than inferred execution flow.
Main entry points: README.md Operator Guide · example CUDA Examples · add.cu Elementwise Add · sum.cu Sum Reduction
Components 11
Learning Guide
- Operator Guide
README.md
CUDA Basics
- CUDA Examples
example - Elementwise Add
elementwise/add.cu
Reduction Operators
- Sum Reduction
reduce/sum/sum.cu - Max Reduction
reduce/max/max.cu - Softmax
reduce/softmax/softmax.cu - Matrix Softmax
reduce/softmax_matrix/softmax_matrix.cu
Other components
- Learner
Connections 10
- Learner → Operator Guide: consults
README.md - Operator Guide → CUDA Examples: introduces
README.md - Operator Guide → Elementwise Add: describes
README.md - Operator Guide → SGEMV: catalogs
README.md - Operator Guide → Sum Reduction: describes
README.md - Operator Guide → Max Reduction: catalogs
README.md - Operator Guide → Softmax: describes
README.md - Operator Guide → Matrix Softmax: catalogs
README.md - Operator Guide → SGEMM: describes
README.md - Operator Guide → Transpose: describes
README.md