CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit 11.6 is now available

Developer Tools CUPTI – CUDA Profiler Tools Interface
1

CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit 11.6 is now available for download in the NVIDIA Registered Developer Program.

The NVIDIA® CUDA Profiling Tools Interface (CUPTI) 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, and
  • the Checkpoint API

Using these CUPTI APIs, independent software developers can create profiling tools that provide low and deterministic profiling overhead on the target system, while giving insight into the CPU and GPU behavior of CUDA applications.

CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit 11.6 includes these improvements and updates:

New Features

    CUPTI has made the following changes as part of the CUDA Toolkit 11.6 release:
    • Two new fields channelID and channelType are added in the activity records for kernel, memcpy, peer-to-peer memcpy and memset to output the ID and type of the hardware channel on which these activities happen. Activity records CUpti_ActivityKernel6, CUpti_ActivityMemcpy4, CUpti_ActivityMemcpyPtoP3 and CUpti_ActivityMemset3 are deprecated and replaced by new activity records CUpti_ActivityKernel7, CUpti_ActivityMemcpy5, CUpti_ActivityMemcpyPtoP4 and CUpti_ActivityMemset4.
    • New fields isMigEnabled, gpuInstanceId, computeInstanceId and migUuid are added in the device activity record to provide MIG information for the MIG enabled GPU. Activity record CUpti__ActivityDevice3 is deprecated and replaced by a new activity record CUpti__ActivityDevice4.
    • A new field utilizedSize is added in the memory pool activity record to provide the utilized size of the memory pool. Activity record CUpti_ActivityMemoryPool is deprecated and replaced by a new activity record CUpti_ActivityMemoryPool2.
    • API cuptiActivityRegisterTimestampCallback and callback function CUpti_TimestampCallbackFunc are added to register a callback function to obtain timestamp of user's choice instead of using CUPTI provided timestamp in activity records.
    • Profiling API supports profiling of the OptiX application.

Requirements

For more information on CUPTI for CUDA Toolkit 11.6, including features, requirements, documentation and support, please visit the CUPTI Overview page.

To download this version, get it as part of the CUDA Toolkit CUDA Profiler Tools Interface (CUPTI) for CUDA Toolkit 11.6 .