# CUDA Profiler Tools Interface (CUPTI) 13.0 is now available **URL:** \ **Category:** CUPTI – CUDA Profiler Tools Interface\ **Created:** [August 5, 2025, 2:40pm UTC](https://forums.developer.nvidia.com/t/cuda-profiler-tools-interface-cupti-13-0-is-now-available/341320 "2025-08-05T14:40:28Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![rbischof](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/rbischof/32/14043_2.png) [@rbischof](https://forums.developer.nvidia.com/u/rbischof)\ **Post date:** [August 5, 2025, 2:40pm UTC](https://forums.developer.nvidia.com/t/cuda-profiler-tools-interface-cupti-13-0-is-now-available/341320/1 "2025-08-05T14:40:28Z")
#### CUDA Profiler Tools Interface (CUPTI) 13.0 is now available for download in the NVIDIA Registered Developer Program. The **NVIDIA CUDA Profiler Tools Interface (CUPTI)**, distributed as part of the **CUDA Toolkit** , 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 Host Profiling API, - the Range Profiling API, - the PC Sampling API, - the SASS Metric API, - the PM Sampling API, - the Checkpoint API, - the Profiling API, - the Python API (available [separately](https://pypi.org/project/cupti-python/)) 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. ### Updates in CUDA Toolkit 13.0 Update 1 **Resolved Issues** - Fixed the issue where synchronization records were not generated for the CUDA APIs `cudaDeviceSynchronize()` and `cuCtxSynchronize_v2()`. - Fixed a potential deadlock that could occur while disabling the activity kind `CUPTI_ACTIVITY_KIND_CONCURRENT_KERNEL` using the API cuptiActivityDisable. - Fixed a potential crash in the API `cuptiActivityFlushAll`. - Discarded Unified Memory counter records that could not be completed before disabling Unified Memory profiling. - Fixed the crash when NVTX API is called before the CUPTI API. This issue was introduced in the CUDA 13.0 GA release. - Fixed a segmentation fault issue while initializing the device buffer for storing profiling data. This segmentation fault occurs for long running applications using CUDA graphs when the attribute `CUPTI_ACTIVITY_ATTR_MEM_ALLOCATION_TYPE_HOST_PINNED` is set to 0. ### Updates in CUDA Toolkit 13.0 **New Features** - Added support for NVLOG, a configurable logging and error-reporting library, enabling detailed logging with various severity levels (Info, Warning, Error, Fatal) and output options including files and stdout. For more details, refer to the section [Logging Using NVLOG](https://docs.nvidia.com/cupti/main/main.html#cupti-logging-using-nvlog). - Introduced a new subscriber API, `cuptiSubscribe_v2`, which includes additional parameters for the current and previous subscriber s names (if applicable). This enhancement allows for easier identification of the previous subscriber in cases where the current subscription fails. - Added new callbacks `CUPTI_CBID_RESOURCE_GRAPH_NODE_UPDATED` for updates to CUDA Graph node and `CUPTI_CBID_RESOURCE_GRAPH_NODE_SET_PARAMS` for when Graph parameters are set via the `cuGraphExecNodeSetParams()` API. - A new field `isDeviceLaunched` is added in the activity records for kernel, memcpy and memset operations to indicate whether operation is a part of the device launched graph. To accommodate this change, activity record `CUpti_ActivityKernel9` is deprecated and replaced by a new activity record `CUpti_ActivityKernel10`. With this change, collection of records for device launched graph is enabled by default if HES trace is enabled. - A new field, `isManagedPool`, has been added to the memory pool record to indicate whether the pool uses managed memory or pinned memory allocation. The `CUpti_ActivityMemoryPool2` activity record is deprecated and replaced by the new `CUpti_ActivityMemoryPool3` activity record. - Initial support for parsing and decoding NVTX extended payloads via activity records. This enables tools to extract extended payload information from NVTX activity records. Libraries such as NCCL, which emit NVTX annotations using extended payloads, are now decodable via CUPTI. For more information, refer to the section [NVIDIA Tools Extension (NVTX) Support](https://docs.nvidia.com/cupti/main/main.html#nvtx-cupti-support). - Added an API `cuptiActivityEnableCudaEventDeviceTimestamps` to control collection of device timestamp for the `CUPTI_ACTIVITY_KIND_CUDA_EVENT` record. By default, the collection of CUDA event device timestamps is disabled. - Starting with CUDA Toolkit 13.0, CUPTI API versions follow the format xxyyzz, where: - xx : Major CUDA Toolkit version - yy : Minor CUDA Toolkit version - zz : CUPTI-specific patch or update version (Note: This does not necessarily align with CUDA Toolkit update versions) - For example, version 130000 indicates CUDA Toolkit 13.0. - Ported the following samples from Profiling APIs to the new Range Profiler APIs: cupti\_metric\_properties, profiling\_injection, callback\_profiling and concurrent\_profiling. - Added a new error code `CUPTI_ERROR_INVALID_CHIP_NAME` for invalid chip name passed in the Profiler Host APIs. **Deprecated and dropped features** - The [CUPTI Profiling API](https://docs.nvidia.com/cupti/main/main.html#cupti-profiling-api) from the header `cupti_profiler_target.h` and the [Perfworks Metric API](https://docs.nvidia.com/cupti/main/main.html#perfworks-metric-api) from the header `nvperf_host.h` are deprecated in the CUDA 13.0 release and will be removed in a future CUDA release. It is recommended to use the [CUPTI Range Profiling API](https://docs.nvidia.com/cupti/main/main.html#range-profiling-api) as an alternative. For more information, refer to the section \