CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit 12.3 is now available for download in the NVIDIA Registered Developer Program.The NVIDIA CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit is a dynamic 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,
- the Profiler API,
- the PC Sampling API,
- the SASS Metric API, and
- the Checkpoint API
Updates in CUDA Toolkit 12.3 Update 1
- To provide normalized timestamps for all activities, CUPTI uses linear interpolation for conversion from GPU timestamps to CPU timestamps. This was broken with CUDA 12.3 causing spurious gaps or overlap on Tegra platforms. Fixed the issue.
Updates in CUDA Toolkit 12.3
- New attributes:
CUPTI_ACTIVITY_OVERHEAD_LAZY_FUNCTION_LOADINGare added in the activity overhead enum
CUpti_ActivityOverheadKindto provide the overhead information for CUDA runtime triggered module loading and lazy function loading respectively.
- New API
cuptiGetGraphExecIdprovides the unique ID of the executable graph.
- Added support for collecting graph level trace for device launched graphs. A new
cuptiActivityEnableDeviceGraphis added to enable the collection of records for device launched graphs.
- CUDA Graphs can be executed on multiple devices i.e. the root node could
be launched on one device and the leaf node could be launched on the
another device. New fields
endContextIdare added to identify the ids of device and context respectively which are used to execute the last node of the graph. To accomodate this change, activity record
CUpti_ActivityGraphTraceis deprecated and it is replaced by a new activity record
- Added WSL profiling support on Windows 10 WSL with OS build version 19044 and greater. WSL profiling is not supported on Windows 10 WSL for systems that exceed 1 TB of system memory.
- Several performance improvements are done in the tracing path. One of the key
improvements is to allow clients to request CUPTI to maintain the activity buffers
at the thread level instead of global buffers. This can be achieved by setting the
CUPTI_ACTIVITY_ATTR_PER_THREAD_ACTIVITY_BUFFERof the enum
CUpti_ActivityAttribute. This can help in reducing the collection overhead for applications which launch CUDA activities from multiple host threads.
- Frame pointers are enabled for Linux x86_64 libraries.
- The deprecated Activity APIs and structures have been moved to a new header cupti_activity_deprecated.h, which is included in the header cupti_activity.h. Header cupti_activity.h contains only the latest version of APIs and structures.
- CUPTI no longer uses profiling semaphore pool to
store the profiling data. Coresponding attributes
CUPTI_ACTIVITY_ATTR_PROFILING_SEMAPHORE_PRE_ALLOCATE_VALUEhave been deprecated.
- Fixed SASS metric profiling for cuda graph.
- Fixed race condition in the API
cuptiSetThreadIdTypefor late subscription
For more information on CUPTI for CUDA Toolkit 12.3 , including features, requirements, documentation and support, please visit the CUPTI Overview page.
To download this version, get it as part of the CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit for CUDA Toolkit 12.3.