![](https://csdnimg.cn/release/download_crawler_static/87885850/bg11.jpg)
GPU metric information in the Summary tab of the HPC Performance Characterization view have been
enhanced to better represent data collected from multiple GPUs.
• Support for Unified Shared Memory extension of OpenCL
™
API
When you use the GPU Offload analysis type to profile OpenCL
™
applications, you can now profile the
CPU-side stacks for GPU computing tasks and identify bottlenecks related to Unified Shared Memory
(USM) for the OpenCL
™
API .
• Support for DirectML API
This release also extends profiling support in the GPU Offload and GPU Compute/Media Hotspots
analysis types for Microsoft
®
DirectX* applications to include support for the DirectML API.
• Application Performance Snapshot
• Updated Metrics for Multiple GPUs
GPU metric information in the Application Performance Snapshot HTML reports have been enhanced to
better represent data collected from multiple GPUs.
• Histograms in Metric Tooltips
The metric tooltips in Application Performance Snapshot HTML reports were enhanced with histograms
that clearly visualize the distribution of metric values observed during analysis.
• High Performance Computing
• Better Hardware Observability
This release adds the Platform Diagram to the Summary tab of the HPC Performance
Characterization analysis result. The Platform Diagram reveals system topology, utilization metrics
for physical cores, DRAM, and Intel
®
Ultra Path Interconnect (Intel
®
UPI) links.
The Platform diagram is available for server platforms based on Intel
®
microarchitecture code named
Skylake and newer architectures.
• Input and Output Analysis
• Intel
®
VT-d Observability
Intel
®
Virtualization Technology for Directed I/O (Intel
®
VT-d) observability is introduced in the Input
and Output analysis for server platforms based on 3rd Gen Intel
®
Xeon
®
Scalable processors (code
named Ice Lake), the Intel Atom
®
P5900 Processor Family (code named Snow Ridge), and newer. New
performance metrics reveal efficiency of hardware-driven DMA addresses remapping and penalties for
sub-optimal Intel VT-d utilization.
• VTune Profiler Server
• New Command-Line Options for Convenience
The vtune-backend binary that launches VTune Profiler Server now has new command-line options to
make setup in certain environments more convenient. You can now specify a base URL that VTune
Profiler Server will use as the basis for URL generation. Additionally, new options were added to
suppress automatic help tours on startup and to provide/decline consent to collect usage information
right from the command line.
These new options can be especially useful if you are running VTune Profiler Server inside a container.
• More Information on Windows*
• Support for Debug Information For Inline Functions
VTune Profiler is now capable of reading debugging information for inline functions from PDB symbol
files on Windows* OS. VTune Profiler can now display names and source code for inline functions in
your workload.
• Managed Code Targets
• .NET 6 Support
Introduction
2
17