The NVIDIA® CUDA Profiler Tools Interface (CUPTI) is a library that enables the creation of profiling and tracing tools that target CUDA applications. CUPTI provides a set of APIs targeted at ISVs creating profilers and other performance optimization tools:
- the Activity API,
- the Callback API,
- the Event API,
- the Metric API, and
- the Profiler API
Using these CUPTI APIs, independent software developers can create profiling tools which give insight into the CPU and GPU behavior of CUDA applications.
CUPTI version 2019.1.0 was provided as part of the CUDA Toolkit 10.1 release, with improvements:
- This release is focused on bug fixes and performance improvements.
- Event collection mode CUPTI_EVENT_COLLECTION_MODE_CONTINUOUS is now supported on all device classes including Geforce and Quadro.
- Support for NVTX string registration API nvtxDomainRegisterStringA().
- Added enum CUpti_PcieGen to list PCIE generations.
CUPTI version 2019.1.1 is stand alone update including fixes for
- Metric smsp__inst_executed.sum incorrectly reported as zero
- Extra triggers/records reported when profiling in a multi-context environment
For more information on CUPTI 2019.1, including features, requirements, documentation and support, please visit https://developer.nvidia.com/CUPTI.
To download this version, visit https://developer.nvidia.com/gameworksdownload#?nsight-compute-2019-1
or get it as part of the CUDA Toolkit 10.1 from https://developer.nvidia.com/cuda-toolkit.