├── .gitignore ├── 2023-IUS-US-GPU.md ├── 2023-TIB-DSP-GPU.md ├── 2024-IUS-US-GPU.md ├── README.md ├── cfg ├── conda-requirements-linux.yml ├── conda-requirements-windows.yml ├── docker │ ├── Dockerfile │ └── utils │ │ ├── fix-permissions │ │ ├── jupyter_notebook_config.py │ │ ├── start-notebook.sh │ │ └── start.sh └── pip-requirements.txt ├── demos └── TensorFlow2TensorRTDemo │ ├── Cpp │ ├── TensorRT_ONNXMNIST │ │ ├── TensorRT_ONNX_MNIST.sln │ │ ├── TensorRT_ONNX_MNIST.vcxproj │ │ ├── TensorRT_ONNX_MNIST.vcxproj.user │ │ ├── logger.cpp │ │ ├── main - Copy.cpp │ │ ├── main.cpp │ │ └── output_example.txt │ └── sample_mnist_data │ │ ├── 0.pgm │ │ ├── 1.pgm │ │ ├── 2.pgm │ │ ├── 3.pgm │ │ ├── 4.pgm │ │ ├── 5.pgm │ │ ├── 6.pgm │ │ ├── 7.pgm │ │ ├── 8.pgm │ │ ├── 9.pgm │ │ └── simple_nn.onnx │ ├── Python │ ├── simple_nn │ │ ├── keras_metadata.pb │ │ ├── saved_model.pb │ │ └── variables │ │ │ ├── variables.data-00000-of-00001 │ │ │ └── variables.index │ └── train_onnx.py │ └── README.txt ├── exercises ├── cupy │ ├── 1_CUDA_programming_model │ │ ├── 1_1_first_kernel.cc │ │ ├── 1_2_add_matrices.cc │ │ ├── 1_2_add_vectors.cc │ │ ├── 1_2_increment.cc │ │ ├── 1_3_add_vectors_invalid.cc │ │ ├── 1_3_decrement.cc │ │ ├── 1_CUDA_programming_model.ipynb │ │ └── solutions │ │ │ ├── 1_1_first_kernel.cc │ │ │ ├── 1_2_add_matrices.cc │ │ │ ├── 1_2_add_vectors.cc │ │ │ ├── 1_2_increment.cc │ │ │ ├── 1_3_add_vectors_invalid.cc │ │ │ ├── 1_3_decrement.cc │ │ │ └── 1_CUDA_programming_model.ipynb │ ├── 2_CUDA_memory_model │ │ ├── 2_1_convolve1d.cc │ │ ├── 2_2_convolve1d_shared_memory.cc │ │ ├── 2_3_convolve1d_shared_const_memory.cc │ │ ├── 2_4_beamform.cc │ │ ├── 2_4_beamform_const.cc │ │ ├── 2_CUDA_memory_model.ipynb │ │ └── solutions │ │ │ ├── 2_1_convolve1d.cc │ │ │ ├── 2_2_convolve1d_shared_memory.cc │ │ │ ├── 2_3_convolve1d_shared_const_memory.cc │ │ │ ├── 2_4_beamform.cc │ │ │ ├── 2_4_beamform_const.cc │ │ │ └── 2_CUDA_memory_model.ipynb │ ├── 3_CUDA_performance_guidelines │ │ ├── 3_CUDA_performance_guidelines.ipynb │ │ ├── 3_add_vectors.cc │ │ ├── 3_add_vectors_mod8_overcomplicated.cc │ │ ├── 3_add_vectors_mod8_simple.cc │ │ ├── 3_convolve1d_axis0.cc │ │ └── 3_convolve1d_axis1.cc │ ├── 4_CUDA_streams_and_processing │ │ ├── 4_1_add_vectors.cc │ │ └── 4_CUDA_streams_and_processing.ipynb │ ├── Case_study_Color_Doppler │ │ ├── Case_study_Color_Doppler.ipynb │ │ └── doppler.cc │ ├── Case_study_RCA │ │ ├── 1_delayAndSumLUT.cc │ │ ├── Case_study_RCA.ipynb │ │ ├── rca_reconstruction.py │ │ └── rca_utils.py │ └── Case_study_SWE │ │ ├── Case_study_SWE.ipynb │ │ ├── correlation.cc │ │ ├── phase_shift.cc │ │ └── utils.py └── numba │ ├── 1_CUDA_programming_model.ipynb │ ├── 2_CUDA_memory_model.ipynb │ └── 3_CUDA_performance_guidelines.ipynb ├── figs └── Lab4US-banner-EN-800.png ├── slides ├── IUS-GPU-0-INTRO.pdf ├── IUS-GPU-1-CUDA.pdf ├── IUS-GPU-2-CUDA-Memory-Performance.pdf ├── IUS-GPU-3-US-Systems.pdf ├── US-GPU-short-course-info.pdf ├── ius-2023 │ ├── IUS-2023-US-GPU-CUDA-refresher.pdf │ ├── IUS-2023-US-GPU.pdf │ └── cuda_by_example_delay_and_sum.pdf └── ius-2024 │ ├── IUS-2024-CUDA-Delay-and-Sum.pdf │ ├── IUS-2024-GPU-CUDA-Streams.pdf │ ├── IUS-2024-US-GPU-CUDA-refresher.pdf │ ├── IUS-2024-US-GPU.pdf │ └── src │ └── gpu_cuda_streams │ ├── imgs │ ├── concurrent_streams.png │ ├── concurrent_streams_sync.png │ ├── concurrent_streams_sync_too_long.png │ ├── cuda_graphs_execution_model.png │ ├── cuda_graphs_kernel_invocation_overhead_reduction.png │ ├── cuda_graphs_streams_and_graphs.png │ ├── events.png │ ├── holoscan_application.png │ ├── holoscan_operator.png │ ├── producer_consumer.png │ ├── producer_consumer_lock_based.png │ ├── single_stream.png │ ├── stream_queue.drawio │ ├── stream_queue.png │ └── tf_graph.png │ └── main.tex └── utils ├── gpu_short_course ├── __init__.py ├── beamformer.cc ├── flow_imaging.py ├── tests.py ├── tools.py └── ultrasound_imaging.py └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/.gitignore -------------------------------------------------------------------------------- /2023-IUS-US-GPU.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/2023-IUS-US-GPU.md -------------------------------------------------------------------------------- /2023-TIB-DSP-GPU.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/2023-TIB-DSP-GPU.md -------------------------------------------------------------------------------- /2024-IUS-US-GPU.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/2024-IUS-US-GPU.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/README.md -------------------------------------------------------------------------------- /cfg/conda-requirements-linux.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/conda-requirements-linux.yml -------------------------------------------------------------------------------- /cfg/conda-requirements-windows.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/conda-requirements-windows.yml -------------------------------------------------------------------------------- /cfg/docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/docker/Dockerfile -------------------------------------------------------------------------------- /cfg/docker/utils/fix-permissions: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/docker/utils/fix-permissions -------------------------------------------------------------------------------- /cfg/docker/utils/jupyter_notebook_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/docker/utils/jupyter_notebook_config.py -------------------------------------------------------------------------------- /cfg/docker/utils/start-notebook.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/docker/utils/start-notebook.sh -------------------------------------------------------------------------------- /cfg/docker/utils/start.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/docker/utils/start.sh -------------------------------------------------------------------------------- /cfg/pip-requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/cfg/pip-requirements.txt -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.sln: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.sln -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.vcxproj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.vcxproj -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.vcxproj.user: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/TensorRT_ONNX_MNIST.vcxproj.user -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/logger.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/logger.cpp -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/main - Copy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/main - Copy.cpp -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/main.cpp -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/output_example.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/TensorRT_ONNXMNIST/output_example.txt -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/0.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/0.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/1.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/1.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/2.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/2.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/3.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/3.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/4.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/4.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/5.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/5.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/6.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/6.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/7.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/7.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/8.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/8.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/9.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/9.pgm -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/simple_nn.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Cpp/sample_mnist_data/simple_nn.onnx -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Python/simple_nn/keras_metadata.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Python/simple_nn/keras_metadata.pb -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Python/simple_nn/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Python/simple_nn/saved_model.pb -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Python/simple_nn/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Python/simple_nn/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Python/simple_nn/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Python/simple_nn/variables/variables.index -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/Python/train_onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/Python/train_onnx.py -------------------------------------------------------------------------------- /demos/TensorFlow2TensorRTDemo/README.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/demos/TensorFlow2TensorRTDemo/README.txt -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_1_first_kernel.cc: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_2_add_matrices.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_2_add_matrices.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_2_add_vectors.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_2_add_vectors.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_2_increment.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_2_increment.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_3_add_vectors_invalid.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_3_add_vectors_invalid.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_3_decrement.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_3_decrement.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/1_CUDA_programming_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/1_CUDA_programming_model.ipynb -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_1_first_kernel.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_1_first_kernel.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_2_add_matrices.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_2_add_matrices.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_2_add_vectors.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_2_add_vectors.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_2_increment.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_2_increment.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_3_add_vectors_invalid.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_3_add_vectors_invalid.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_3_decrement.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_3_decrement.cc -------------------------------------------------------------------------------- /exercises/cupy/1_CUDA_programming_model/solutions/1_CUDA_programming_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/1_CUDA_programming_model/solutions/1_CUDA_programming_model.ipynb -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_1_convolve1d.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_1_convolve1d.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_2_convolve1d_shared_memory.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_2_convolve1d_shared_memory.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_3_convolve1d_shared_const_memory.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_3_convolve1d_shared_const_memory.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_4_beamform.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_4_beamform.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_4_beamform_const.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_4_beamform_const.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/2_CUDA_memory_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/2_CUDA_memory_model.ipynb -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_1_convolve1d.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_1_convolve1d.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_2_convolve1d_shared_memory.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_2_convolve1d_shared_memory.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_3_convolve1d_shared_const_memory.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_3_convolve1d_shared_const_memory.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_4_beamform.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_4_beamform.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_4_beamform_const.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_4_beamform_const.cc -------------------------------------------------------------------------------- /exercises/cupy/2_CUDA_memory_model/solutions/2_CUDA_memory_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/2_CUDA_memory_model/solutions/2_CUDA_memory_model.ipynb -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_CUDA_performance_guidelines.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_CUDA_performance_guidelines.ipynb -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors.cc -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors_mod8_overcomplicated.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors_mod8_overcomplicated.cc -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors_mod8_simple.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_add_vectors_mod8_simple.cc -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_convolve1d_axis0.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_convolve1d_axis0.cc -------------------------------------------------------------------------------- /exercises/cupy/3_CUDA_performance_guidelines/3_convolve1d_axis1.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/3_CUDA_performance_guidelines/3_convolve1d_axis1.cc -------------------------------------------------------------------------------- /exercises/cupy/4_CUDA_streams_and_processing/4_1_add_vectors.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/4_CUDA_streams_and_processing/4_1_add_vectors.cc -------------------------------------------------------------------------------- /exercises/cupy/4_CUDA_streams_and_processing/4_CUDA_streams_and_processing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/4_CUDA_streams_and_processing/4_CUDA_streams_and_processing.ipynb -------------------------------------------------------------------------------- /exercises/cupy/Case_study_Color_Doppler/Case_study_Color_Doppler.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_Color_Doppler/Case_study_Color_Doppler.ipynb -------------------------------------------------------------------------------- /exercises/cupy/Case_study_Color_Doppler/doppler.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_Color_Doppler/doppler.cc -------------------------------------------------------------------------------- /exercises/cupy/Case_study_RCA/1_delayAndSumLUT.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_RCA/1_delayAndSumLUT.cc -------------------------------------------------------------------------------- /exercises/cupy/Case_study_RCA/Case_study_RCA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_RCA/Case_study_RCA.ipynb -------------------------------------------------------------------------------- /exercises/cupy/Case_study_RCA/rca_reconstruction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_RCA/rca_reconstruction.py -------------------------------------------------------------------------------- /exercises/cupy/Case_study_RCA/rca_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_RCA/rca_utils.py -------------------------------------------------------------------------------- /exercises/cupy/Case_study_SWE/Case_study_SWE.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_SWE/Case_study_SWE.ipynb -------------------------------------------------------------------------------- /exercises/cupy/Case_study_SWE/correlation.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_SWE/correlation.cc -------------------------------------------------------------------------------- /exercises/cupy/Case_study_SWE/phase_shift.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_SWE/phase_shift.cc -------------------------------------------------------------------------------- /exercises/cupy/Case_study_SWE/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/cupy/Case_study_SWE/utils.py -------------------------------------------------------------------------------- /exercises/numba/1_CUDA_programming_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/numba/1_CUDA_programming_model.ipynb -------------------------------------------------------------------------------- /exercises/numba/2_CUDA_memory_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/numba/2_CUDA_memory_model.ipynb -------------------------------------------------------------------------------- /exercises/numba/3_CUDA_performance_guidelines.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/exercises/numba/3_CUDA_performance_guidelines.ipynb -------------------------------------------------------------------------------- /figs/Lab4US-banner-EN-800.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/figs/Lab4US-banner-EN-800.png -------------------------------------------------------------------------------- /slides/IUS-GPU-0-INTRO.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/IUS-GPU-0-INTRO.pdf -------------------------------------------------------------------------------- /slides/IUS-GPU-1-CUDA.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/IUS-GPU-1-CUDA.pdf -------------------------------------------------------------------------------- /slides/IUS-GPU-2-CUDA-Memory-Performance.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/IUS-GPU-2-CUDA-Memory-Performance.pdf -------------------------------------------------------------------------------- /slides/IUS-GPU-3-US-Systems.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/IUS-GPU-3-US-Systems.pdf -------------------------------------------------------------------------------- /slides/US-GPU-short-course-info.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/US-GPU-short-course-info.pdf -------------------------------------------------------------------------------- /slides/ius-2023/IUS-2023-US-GPU-CUDA-refresher.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2023/IUS-2023-US-GPU-CUDA-refresher.pdf -------------------------------------------------------------------------------- /slides/ius-2023/IUS-2023-US-GPU.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2023/IUS-2023-US-GPU.pdf -------------------------------------------------------------------------------- /slides/ius-2023/cuda_by_example_delay_and_sum.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2023/cuda_by_example_delay_and_sum.pdf -------------------------------------------------------------------------------- /slides/ius-2024/IUS-2024-CUDA-Delay-and-Sum.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/IUS-2024-CUDA-Delay-and-Sum.pdf -------------------------------------------------------------------------------- /slides/ius-2024/IUS-2024-GPU-CUDA-Streams.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/IUS-2024-GPU-CUDA-Streams.pdf -------------------------------------------------------------------------------- /slides/ius-2024/IUS-2024-US-GPU-CUDA-refresher.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/IUS-2024-US-GPU-CUDA-refresher.pdf -------------------------------------------------------------------------------- /slides/ius-2024/IUS-2024-US-GPU.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/IUS-2024-US-GPU.pdf -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams_sync.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams_sync.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams_sync_too_long.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/concurrent_streams_sync_too_long.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_execution_model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_execution_model.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_kernel_invocation_overhead_reduction.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_kernel_invocation_overhead_reduction.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_streams_and_graphs.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/cuda_graphs_streams_and_graphs.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/events.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/events.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/holoscan_application.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/holoscan_application.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/holoscan_operator.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/holoscan_operator.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/producer_consumer.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/producer_consumer.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/producer_consumer_lock_based.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/producer_consumer_lock_based.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/single_stream.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/single_stream.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/stream_queue.drawio: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/stream_queue.drawio -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/stream_queue.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/stream_queue.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/imgs/tf_graph.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/imgs/tf_graph.png -------------------------------------------------------------------------------- /slides/ius-2024/src/gpu_cuda_streams/main.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/slides/ius-2024/src/gpu_cuda_streams/main.tex -------------------------------------------------------------------------------- /utils/gpu_short_course/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/__init__.py -------------------------------------------------------------------------------- /utils/gpu_short_course/beamformer.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/beamformer.cc -------------------------------------------------------------------------------- /utils/gpu_short_course/flow_imaging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/flow_imaging.py -------------------------------------------------------------------------------- /utils/gpu_short_course/tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/tests.py -------------------------------------------------------------------------------- /utils/gpu_short_course/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/tools.py -------------------------------------------------------------------------------- /utils/gpu_short_course/ultrasound_imaging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/gpu_short_course/ultrasound_imaging.py -------------------------------------------------------------------------------- /utils/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Lab4US/gpu-short-course/HEAD/utils/setup.py --------------------------------------------------------------------------------