Intel® Analyzers 2025.1 Available!

[yuzhang3_intel]

--------- VTune Profiler ----------

Release notes and new features in Intel® VTune Profiler 2025.1

New Language Support

• Pinpoint the most time-consuming code sections and critical code paths for Python 3.12.

Performance Improvement

• Improved result finalization speed for AI specific workloads and multi-GPU systems.

XPU Profiling

• Identify performance bottlenecks of AI workloads that are calling DirectML or WinML APIs.
• Understand the overall accelerator performance by seeing GPU and NPU offload bottlenecks in one view.

Usage Consideration

• To open profiling results collected with an older version of VTune Profiler, use the same version of VTune Profiler that was used for data collection, or one version newer. VTune Profiler does not offer backward compatibility for profiling results beyond the version used to collect the profiling data. For example, if you used the 2024.0 version of VTune Profiler to collect results, use the 2024.* or 2025 version of VTune Profiler to open the results at a later time.

Deprecation

• Linux Kernel Version
  • Intel VTune Profiler does not support the 2.6.32 version of Linux Kernel anymore.
  • The oldest version of Linux Kernel supported by VTune Profiler is 4.18.
• Embedded Linux targets
  • Support for WinRiver, QNX and Android OS targets is deprecated with the 2025.1 release.
  • Support for Yocto has been removed.
• Analysis Type

  • The CPU/FPGA Interaction Analysis is deprecated in the 2025.1 release of Intel VTune Profiler. This analysis type will be removed in a future release. To collect profiling information about your FPGA hardware, contact oneapi@altera.com for help.

Download - https://www.intel.com/content/www/us/en/developer/tools/oneapi/vtune-profiler-download.html

User Guide - https://www.intel.com/content/www/us/en/docs/vtune-profiler/user-guide/2025-1/overview.html

--------- Advisor ----------

Release notes and new features in Intel® Advisor 2025.0

New Language Support 

• Added profiling support for Python 3.12

XPU Profiling

• Profile AI workload performance more accurately in GPU roofline analysis with the added support for Xe Matrix Extensions (XMX) for Intel® Arc™ Graphics
• Faster GPU survey with reduced data collection overhead and more accurate GPU profiling data

Usage Consideration

• To open profiling results collected with an older version of VTune Advisor, use the same version of VTune Advisor that was used for data collection, or one version newer. VTune Advisor does not offer backward compatibility for profiling results beyond the version used to collect the profiling data. For example, if you used the 2024.0 version of VTune Advisor to collect results, use the 2024.* or 2025 version of VTune Advisor to open the results at a later time.

Download - https://www.intel.com/content/www/us/en/developer/tools/oneapi/advisor-download.html

User Guide - https://www.intel.com/content/www/us/en/docs/advisor/user-guide/2025-1/overview.html