gpufl 0.1.2__tar.gz → 0.1.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {gpufl-0.1.2 → gpufl-0.1.4}/CMakeLists.txt +1 -1
- {gpufl-0.1.2 → gpufl-0.1.4}/PKG-INFO +1 -1
- {gpufl-0.1.2 → gpufl-0.1.4}/pyproject.toml +1 -1
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/__init__.py +1 -1
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/analyzer/analyzer.py +14 -2
- {gpufl-0.1.2 → gpufl-0.1.4}/.clang-format +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/.dockerignore +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/.github/pull_request_template.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/.github/workflows/build.yml +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/.github/workflows/release.yml +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/.gitignore +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/CONTRIBUTING.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/Dockerfile.demo +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/Dockerfile.monitor +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/Dockerfile.monitor.amd +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/Dockerfile.monitor.supervisord.conf +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/LICENSE +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/README.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/benchmark/README.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/benchmark/cuda_gemm.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/benchmark/pytorch_train.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/benchmark/run_benchmark.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/build.sh +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/daemon/README.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/daemon/monitor/CMakeLists.txt +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/daemon/monitor/main.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/docker-compose.monitor.amd.yml +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/docker-compose.monitor.yml +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/amd/CMakeLists.txt +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/amd/README.md +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/amd/check_device.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/amd/gpufl_scope_demo.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/amd/vector_add_benchmark.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/CMakeLists.txt +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/block_style_example.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/check_conflict.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/check_device.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/cupti_basic.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/cupti_pc_sampling.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/list_sass_metrics.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/memory_coalescing_demo.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/occupancy_demo.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/sass_divergence_demo.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/system_monitor.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/test_occupancy.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/cuda/vector_add_benchmark.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/01_basic.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/02_numba_cuda.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/03_pytorch_benchmark.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/analyzer/01_analyzer_sample.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/requirements.txt +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/viz/01_plot_memory_timeline.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/example/python/viz/02_plot_stress_timeline.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/images/Screenshot1.png +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/engine/amd_profiling_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/engine/dispatch_counter_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/engine/dispatch_counter_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/hip_static_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/hip_static_collector.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/monitor_adapter_amd.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/monitor_adapter_amd.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/rocm_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/rocm_collector.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/rocprofiler_backend.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/amd/rocprofiler_backend.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/host_collector.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cuda_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cuda_collector.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cupti_backend.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cupti_backend.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cupti_common.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cupti_utils.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/cupti_utils.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_with_sass_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_with_sass_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/profiling_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/range_profiler_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/range_profiler_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/sass_metrics_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/sass_metrics_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/kernel_launch_handler.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/kernel_launch_handler.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/mem_transfer_handler.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/mem_transfer_handler.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/monitor_adapter_nvidia.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/monitor_adapter_nvidia.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/nvml_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/nvml_collector.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/resource_handler.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/resource_handler.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/sampler/cupti_sass.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/sampler/cupti_sass.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/synchronization_handler.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/synchronization_handler.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/activity_record.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/backend_factory.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/backend_factory.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/backend_interfaces.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/batch_buffer.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/common.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/common.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/config_file_loader.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/config_file_loader.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/debug_logger.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/debug_logger.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/dictionary_manager.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/dictionary_manager.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/events.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/gpufl.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/host_info.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/host_info.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/itanium_demangle.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/itanium_demangle.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/json/json.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/json/json.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/file_compressor.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/file_compressor.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/file_log_sink.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/file_log_sink.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/http_log_sink.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/http_log_sink.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/log_rotator.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/log_rotator.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/log_sink.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/logger.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/logger/logger.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/batch_models.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/batch_models.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/graph_launch_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/graph_launch_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/kernel_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/kernel_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/lifecycle_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/lifecycle_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/memcpy_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/memcpy_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/memory_alloc_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/memory_alloc_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/model_utils.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/nvtx_marker_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/nvtx_marker_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/perf_metric_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/perf_metric_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/profile_sample_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/profile_sample_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/scope_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/scope_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/serializable.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/synchronization_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/synchronization_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/system_event_model.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/model/system_event_model.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/monitor.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/monitor.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/monitor_adapter.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/monitor_adapter.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/monitor_backend.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/remote_config.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/remote_config.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/ring_buffer.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/runtime.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/runtime.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/sampler.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/sampler.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/sass_compressor.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/sass_compressor.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/scope_registry.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/scope_registry.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/stack_registry.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/stack_trace.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/stack_trace.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/stream_handle.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/trace_type.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/core/version.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/gpufl.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/report/hint_engine.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/report/hint_engine.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/report/text_report.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/report/text_report.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/bindings.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/.gitignore +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/analyzer/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/cupy/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/jax/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/numba/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/report/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/report/text_report.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/torch/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/torch/dispatch.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/torch/profile.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/torch/stack.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/torch/trace_import.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/triton/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/utils.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/viz/__init__.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/viz/reader.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/viz/timeline.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/python/gpufl/viz/visualizer.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/scripts/docker-demo-loop.sh +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/scripts/windows/run-monitor-local.bat +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/CMakeLists.txt +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/backends/amd/test_rocm_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/backends/nvidia/test_cuda_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/backends/nvidia/test_engine_coverage.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/backends/nvidia/test_nvidia_backend.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/backends/nvidia/test_nvml_collector.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/common/log_utils.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/common/log_utils.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/common/test_kernel.cu +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/common/test_kernel.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/common/test_utils.hpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_analyzer.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_api_path_routing.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_batch_models.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_http_log_sink.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_itanium_demangle.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_monitor.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/core/test_wire_contract.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/main_test_runner.cpp +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/python/conftest.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/python/test_analyzer.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/python/test_bindings.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/python/test_remote_upload_smoke.py +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/run_engine_coverage.ps1 +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/run_engine_coverage.sh +0 -0
- {gpufl-0.1.2 → gpufl-0.1.4}/tests/verify_pipeline.py +0 -0
|
@@ -128,7 +128,7 @@ except Exception as e:
|
|
|
128
128
|
print(f"[FATAL] Unexpected error importing _gpufl_client: {e}", file=sys.stderr)
|
|
129
129
|
raise e
|
|
130
130
|
|
|
131
|
-
__version__ = "0.1.
|
|
131
|
+
__version__ = "0.1.4"
|
|
132
132
|
|
|
133
133
|
# ── Remote Configuration ──────────────────────────────────────────────────────
|
|
134
134
|
#
|
|
@@ -695,7 +695,7 @@ class GpuFlightSession:
|
|
|
695
695
|
table.add_column("Total Time", justify="right", style="green")
|
|
696
696
|
table.add_column("Occupancy", justify="right", style="magenta")
|
|
697
697
|
table.add_column("Grid/Block", justify="center")
|
|
698
|
-
table.add_column("Resources (Reg/SMem/
|
|
698
|
+
table.add_column("Resources (Reg/SMem/LMem/CMem/Spill)", justify="left")
|
|
699
699
|
|
|
700
700
|
for (name, *rest), row in summary.iterrows():
|
|
701
701
|
stack_trace = rest[0] if rest else None
|
|
@@ -743,10 +743,22 @@ class GpuFlightSession:
|
|
|
743
743
|
grid_val = row['grid'] if 'grid' in row.index and pd.notna(row.get('grid')) else "n/a"
|
|
744
744
|
block_val = row['block'] if 'block' in row.index and pd.notna(row.get('block')) else "n/a"
|
|
745
745
|
|
|
746
|
+
# Shared memory: `static` is compile-time __shared__ arrays;
|
|
747
|
+
# `dyn` is the third launch arg <<<grid,block,dyn_shared>>>.
|
|
748
|
+
# Both live in the same physical SM shared-memory space and
|
|
749
|
+
# together drive smem_occupancy — so we display the SUM as
|
|
750
|
+
# `SMem` (matching what the occupancy % is computed against)
|
|
751
|
+
# with the static/dyn breakdown in parentheses for users
|
|
752
|
+
# tuning either piece. Previously this row showed two
|
|
753
|
+
# separate `SMem`/`DMem` values which read as "static
|
|
754
|
+
# shared" vs "device memory" (wrong: it's dyn-shared, not
|
|
755
|
+
# device global memory) and didn't visually reconcile with
|
|
756
|
+
# the smem occupancy % above.
|
|
757
|
+
smem_total = (static_b or 0) + (dyn_b or 0)
|
|
746
758
|
resource_str = (
|
|
747
759
|
f"{num_regs} regs"
|
|
748
760
|
+ (f" ({occ_breakdown})" if occ_breakdown else "")
|
|
749
|
-
+ f"\nSMem {
|
|
761
|
+
+ f"\nSMem {smem_total} B ({static_b} static + {dyn_b} dyn)"
|
|
750
762
|
+ f"\nLMem {local_b} B · CMem {const_b} B"
|
|
751
763
|
+ spill_str
|
|
752
764
|
+ bottleneck_str
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_with_sass_engine.cpp
RENAMED
|
File without changes
|
{gpufl-0.1.2 → gpufl-0.1.4}/include/gpufl/backends/nvidia/engine/pc_sampling_with_sass_engine.hpp
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|