├── .gitignore ├── README.md ├── hello_load_inline.py ├── load_inline.py ├── load_inline_cuda ├── .ninja_deps ├── .ninja_log ├── build.ninja ├── cuda.cu ├── cuda.cuda.o ├── main.cpp └── main.o ├── main.py ├── ncu_logs ├── nsys_square.py ├── numba_square.py ├── pt_profiler.py ├── pytorch_square.py ├── square_kernel.ptx ├── test.py ├── tmp ├── .ninja_deps ├── .ninja_log ├── build.ninja ├── main.cpp └── main.o ├── triton_profile └── triton_square.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/README.md -------------------------------------------------------------------------------- /hello_load_inline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/hello_load_inline.py -------------------------------------------------------------------------------- /load_inline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline.py -------------------------------------------------------------------------------- /load_inline_cuda/.ninja_deps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/.ninja_deps -------------------------------------------------------------------------------- /load_inline_cuda/.ninja_log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/.ninja_log -------------------------------------------------------------------------------- /load_inline_cuda/build.ninja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/build.ninja -------------------------------------------------------------------------------- /load_inline_cuda/cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/cuda.cu -------------------------------------------------------------------------------- /load_inline_cuda/cuda.cuda.o: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/cuda.cuda.o -------------------------------------------------------------------------------- /load_inline_cuda/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/main.cpp -------------------------------------------------------------------------------- /load_inline_cuda/main.o: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/load_inline_cuda/main.o -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/main.py -------------------------------------------------------------------------------- /ncu_logs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/ncu_logs -------------------------------------------------------------------------------- /nsys_square.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/nsys_square.py -------------------------------------------------------------------------------- /numba_square.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/numba_square.py -------------------------------------------------------------------------------- /pt_profiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/pt_profiler.py -------------------------------------------------------------------------------- /pytorch_square.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/pytorch_square.py -------------------------------------------------------------------------------- /square_kernel.ptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/square_kernel.ptx -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/test.py -------------------------------------------------------------------------------- /tmp/.ninja_deps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/tmp/.ninja_deps -------------------------------------------------------------------------------- /tmp/.ninja_log: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/tmp/.ninja_log -------------------------------------------------------------------------------- /tmp/build.ninja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/tmp/build.ninja -------------------------------------------------------------------------------- /tmp/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/tmp/main.cpp -------------------------------------------------------------------------------- /tmp/main.o: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/tmp/main.o -------------------------------------------------------------------------------- /triton_profile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/triton_profile -------------------------------------------------------------------------------- /triton_square.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gpu-mode/profiling-cuda-in-torch/HEAD/triton_square.py --------------------------------------------------------------------------------