Intel® VTune™

Profiler

2021.8.0

Analysis Targets
Extended Support for .NET5 Workloads
You can now analyze .NET5 workloads in the
Attach to Process
mode when you use Hardware Event-Based Sampling.
Support for Unified Shared Memory Workloads
Starting with the 2021.8 release, you can profile OpenCL, SYCL, and DPC++ applications that use Unified Shared Memory (USM) workloads. For OpenCL applications, this release also supports explicit data transfer of the buffer as Unified Shared Memory.
Input and Output Analysis on FreeBSD* OS
You can now run the Input and Output analysis on remote FreeBSD targets. Analysis scope is limited to platform-level metrics.
GPU Accelerators
Hottest CPU Tasks in GPU Offload Analysis
The
Summary
view in the GPU Offload analysis now includes the
Hottest Host Tasks
table, which displays the most active tasks running on the CPU. Use this table to examine the overhead on the host. Click on a performance-critical task to see more information in the Graphics window, where results are grouped by host Task Type.
Support for Affinity Mask
If you use the
ZE_AFFINITY_MASK
variable to bind your workload to a single tile,
VTune Profiler
can then attribute kernels to the correct tile and also display relevant metrics per kernel.
Code Annotations
New Instrumentation and Tracing Technology API Capabilities
A new Histogram API was added to ITT API. This API enables you to collect arbitrary histogram data without extra overhead. The Summary tab of the Input and Output analysis automatically displays this data in the form of a histogram.
Documentation
New Cookbook Recipe on Analyzing Hot Code Paths Using Flame Graphs
The
VTune Profiler
Performance Analysis Cookbook features a new recipe that demonstrates how you can analyze hot code paths in your application using flame graphs.

Intel® VTune™

Profiler

2021.7.0

Algorithm Group
Flame Graph View in Hotspots Analysis
This version of
VTune Profiler
introduces support for
Flame Graphs
in the
Hotspots
analysis type. The Hotspots by CPU Utilization viewpoint has been enhanced with a Flame Graph window that displays a graphical view of hot code paths. Use flame graphs to analyze the time spent on each function and its callee functions.
GPU Accelerators
CPU Context for GPU Execution in GPU Offload Analysis
The GPU Offload analysis now presents a richer set of information about execution on the GPU by including context from the CPU. This includes stack information on:
Execution
Data transfer from host to device
Data transfer from device to host
The viewpoint for the GPU Offload Analysis now includes the Call Stack pane with a new grouping by
GPU Computing Task/Host Call Stack
. Navigate through transfer data contained in these panes to identify inefficient code paths in your application.
Analysis of Multiple GPUs
When you have multiple GPUs connected to your system, you can now analyze all of the GPUs collectively with the GPU Offload and GPU Compute/Media Hotspots analyses. Previously, you could analyze a single GPU at a time after
VTune Profiler
identified all the GPUs connected to the system. When you run these analyses on all connected GPUs, see analysis information about each GPU in the
Summary
window. Full compute set in
Characterization
mode is not available in multi-adapter and multi-tile analysis.
Debug Formats
Support for DWARF5 Debug Format
VTune Profiler
now supports version 5 of the DWARF debug format. You can now use debug information in DWARF 5 format to resolve function names and source locations for binaries.

Intel® VTune™

Profiler

2021.6.0

GPU Accelerators
Occupancy Report in GPU Hotspots Analysis
The GPU Compute/Media Hotspots analysis has been enhanced to display occupancy information in the
Summary
section. Use this data to understand the architectural limitations of the GPU that affect occupancy.
Microarchitecture Analyses
Platform Diagram in Memory Usage View
This release introduces the
Platform diagram
in the Memory Usage viewpoint of the Memory Access analysis type. Use this diagram to understand:
System topology
Utilization metrics for DRAM
Intel® UPI links
Physical cores
The platform diagram is available for:
All client platforms
Server platforms based on Intel® microarchitecture code name Skylake, with up to four sockets.
Command Line Analysis
Perf Tool Parameters for All Analysis Types
You can now use the target-system command to get parameters on the command line for the native
perf
tool for all CPU hardware-based analysis types, including custom analyses. Use the
get-perf-cmd
argument for this purpose. You can collect the
perf
trace on a target with the Linux Perf tool and then import the trace to the VTune Profiler UI.

Intel® VTune™

Profiler

2021.5.0

Intel® VTune™
Profiler
– Platform Profiler Integration
VTune
Profiler
- Platform Profiler as Analysis Type
VTune
Profiler
– Platform Profiler has been completely integrated into
VTune
Profiler
as an analysis type. Platform Profiler is now fully available as an analysis from the GUI or command line of
VTune
Profiler
. For more information, see Platform Profiler Analysis.
Application Performance Snapshot
Outlier Detection
This release introduces a mechanism for the detection of outliers, or individual metric values contributing to an average metric that differ significantly from the overall distribution or break a certain threshold. Outliers can cause imbalance and distort average metric values. You can now see outliers in both HTML and CLI reports, with attribution to specific rank or node where an outlier occurred.
Metric Tooltip Enhancements
Metric tooltips now visualize ranges of average metrics, with their minimum, maximum, and average contributing values.
MPI Support
Support for MPI applications in GPU and IO analyses
The GPU Offload, GPU Compute/Media Hotspots, and Input and Output analyses now support profiling of MPI applications, as described in the MPI Code Analysis topic.
Documentation
New CLI Cheat Sheet for quick reference
Added a new downloadable document, the
VTune
Profiler
CLI Cheat Sheet. You can use this print-friendly PDF for quick reference on the
VTune
Profiler
command-line interface.

Intel® VTune™

Profiler

2021.4.0

User Interface
Enhanced Project Navigator User Experience
The Project Navigator pane now features menu options to open a new or existing project to better facilitate your
VTune
Profiler
experience.
Code Parallelism
Improvements to Vectorization Information
The Vectorization sections of Performance Snapshot and HPC Performance Characterization analyses have been enriched to provide a clearer picture of the state of vectorization in your application. Quickly see if your code is not vectorized at all, if your code does not use the latest vector instruction set extension, or if your code has too many scalar instructions. This version of
VTune
Profiler
also features improved recommendations to resolve vectorization issues.
Hardware Support
Support for the 3rd Gen Intel® Xeon® Scalable processors (code named Ice Lake Server)
This release introduces full support for the Ice Lake Server architecture in the Input and Output analysis.
GPU Accelerators
Advanced Data Transfer Information in GPU Offload Analysis
The following additions to the Graphics window clarify better the data transfer between CPU host and GPU device when you run GPU profiling analyses:
Allocation time information displays as part of total time by device operation.
Data Transferred table has been renamed as Transfer Size table. Columns under Transfer Size feature new names for data transferred between host and device.
Highlights and tool tips for workloads with sub-optimal offload schemes direct your attention to improve offload schema where necessary.
Improved Tool tips for Occupancy Metrics in GPU Analysis
The GPU Compute/Media Hotspots Analysis has been enhanced to detect factors that limit peak achievable occupancy for the hottest computing tasks that make the EU array idle when waiting for the scheduler. Improved tooltips for occupancy metrics now provide information about peak occupancy and bounding reasons for existing computing task launch configuration.
GPU Analysis Coverage for Self-Check
Coverage of checks by the self-check functionality in VTune Profiler now includes GPU analyses as well. Run vtune-self-checker.sh script on Windows and Linux systems to check for the GPU Compute/Media Hotspots Analysis in source analysis and characterization modes when you run DPC++ applications on an Intel GPU. You must install the Intel® oneAPI Base Toolkit for this purpose.

Intel® VTune™

Profiler

2021.3.0

Application Performance Snapshot
Metric tooltips in HTML reports
Metric tooltips in APS HTML reports now present a more holistic view of metrics and their properties. The new tooltips present a compact yet comprehensive overview of a metric, which helps you to better understand the importance of metrics in performance analysis. This change includes a visual bar that indicates where the metric value stands in terms of current performance and tuning potential.
PCIe bandwidth info in CLI reports
APS command line reports now include PCIe bandwidth metrics. This data is only available on server platforms when using the Sampling Driver.
New reports and filters
APS now features the following new types of reports and filters:
Node topology report: view relations between ranks, nodes, and PCIe devices.
Metrics report: get a configurable table that displays any collected metric for each rank, node, or device.
Ability to filter data by node.
Managed Code Targets
This release introduces support for running the Hotspots analysis on .NET 5 targets in Launch Application mode when using hardware event-based sampling.
Hardware Support
Support for 3rd Gen Intel® Xeon® Scalable Processor Architecture
This releases supports the 3rd Gen Intel® Xeon® Scalable processor architecture (code named Ice Lake Server) .

Intel® VTune™

Profiler

2021.2.0

User Interface
This release introduces a new main vertical toolbar to enhance your user experience. All controls previously located in the main horizontal toolbar are now located on this toolbar. The vertical toolbar is designed to enhance your experience with clear, bright controls.
Hardware Support
This version includes support for Intel Atom® Processor P Series code named Snow Ridge, including Hotspots, Microarchitecture Exploration, Memory Access, and Input and Output analyses.
GPU Accelerators
Source-level analysis for DPC++ and OpenMP applications running on GPU over Level Zero
The following modes in GPU Compute/Media Hotspots analysis are now available when profiling Level Zero applications:
Dynamic Instruction Count
Basic Block Latency
Memory Latency
Support also includes full-scale analysis of the kernel source per code line, including Source/Assembly mapping.
Input and Output Analysis
New major features in Input and Output analysis
This release introduces the
Platform Diagram
, a new starting point for the Input and Output analysis. It reveals system topology and high-level utilization metrics for hardware resources including PCIe devices, Intel® Ultra Path Interconnect, and memory. It enables you to examine the utilization of your hardware at a glance.
This feature is enabled for 1st and 2nd Generation Intel® Xeon® Scalable Processors in up to four-socket configurations, excluding the Intel® Xeon® Platinum 9200 series processors code named Cascade Lake AP. This feature is also supported on Intel Atom® Processors P Series code named Snow Ridge.
Intel® Data Direct I/O (Intel DDIO) utilization efficiency metrics
are extended with average Inbound PCIe read/write latency and core/IO contention indicator.
It is now possible to perform
Linux perf-based data collection
without root access on 1st and 2nd Generation Intel Xeon® Scalable Processors on Linux kernel versions 5.10 and newer.

Intel® VTune™

Profiler

2021.1.2

Software Enhancement
Fix for an issue where Command line analysis based on User-Mode Sampling does not work when using a non-root account
If
VTune
Profiler
was installed by a root/sudo user, some executable files were requiring only root permissions to run an analysis based on the User-Mode Sampling collector, such as the Hotspots analysis. This issue has been rectified in this release.
Documentation
Guidance resource on GPU-profiling features in
Intel® VTune™
Profiler
A new article captures learning pathways to profile GPUs and illustrates techniques to Optimize Applications for Intel® GPUs with
Intel® VTune™
Profiler
. Use this article to understand the
Intel® VTune™
Profiler
workflow to profile and optimize GPUs. The article also informs about several key resources including procedural topics, cookbook recipes, and webinars that explain GPU compute profiling and graphics profiling with Intel software analyzer products.

Intel® VTune™

Profiler

2021

GPU Accelerators
GPU Adapter Selection for Profiling Analyses in Multi-GPU Systems
When you have multiple Intel GPUs connected to your system, you can now select a specific GPU adapter directly in the user interface for your GPU Offload Analysis or GPU Compute/Media Hotspots Analysis. The
Target GPU
pulldown menu appears in the
HOW
pane of the analysis configuration when
VTune
Profiler
detects multiple Intel GPUs on your system. The menu lists available GPU adapters with their Bus/Device/Function (BDF) values.
Energy Consumption Metrics in GPU Compute/Media Hotspots Analysis
When you run the GPU Compute/Media Hotspots Analysis on an Intel® Iris® X
e
MAX graphics discrete GPU in a Linux environment, you can now use the
Analyze power usage
option to collect information about energy consumed by the GPU. The analysis results display energy consumption metrics over time and per discrete GPU kernel. Use this data to better monitor power usage with processing time and optimize for either purpose.
Data Transfer Information in GPU Offload Analysis
Kernel information in the GPU Offload Analysis combines data transfer times to and from the GPU kernel with the execution time. In the
Summary
window, you can now see the total time for computing tasks along with the execution time. Previously, this display included only the execution time. In the
Graphics
window, the total time for computing task by kernel now combines the data transfer time between device and host as well as the actual execution time. The
Graphics
window also displays now information about the size of data transfer between the host (CPU) and GPU (device).
Support for oneAPI Level Zero Specification for DPC++ Applications
Intel® VTune™
Profiler
now supports version 1.0.4 of the oneAPI Level Zero API when you run GPU analyses (GPU Offload analysis and GPU Compute/Media Hotspots) on DPC++ applications in Windows and Linux environments.
Update to IP Architecture diagram
The IP Architecture Diagram of the GPU Compute/Media Hotspots analysis is renamed as the
Memory Hierarchy Diagram
. The diagram features a new design that can help make the understanding of metrics more intuitive. The diagram also displays the same markers to highlight metrics as the ones used to indicate performance or data issues in the Summary and Grid displays. This provides a consistent look and feel to the diagram and helps you correlate metrics between both displays.
SIMD utilization metrics at kernel level.
The GPU Compute/Media Hotspots analysis in the Dynamic Instruction Count mode now includes SIMD utilization metrics at the kernel and instruction level. These metrics help identify instructions in the OpenCL kernel that utilize SIMD poorly.
GPU metrics in APS and HPC Analysis type.
The GPU utilization analysis in Application Performance Snapshot (APS) and the HPC Performance Characterization analysis now includes these GPU computation metrics:
GPU Time
GPU IPC
GPU Utilization
Percentage of stalled and idle EUs
The GPU Compute metric set of Application Performance Snapshot has been enhanced with OpenMP Offload Efficiency metrics, including offload region overhead. These metrics are available for binaries compiled with the Intel® C/C++ Compiler included in several Intel® oneAPI Toolkits 2021.1-beta05 or newer.
Simplified dependency on Intel® Metrics Discovery API library
There is now a simplified dependency on the Intel® Metrics Discovery API library to collect GPU hardware statistics on Linux* systems.
Intel® VTune™
Profiler
now automatically selects the latest
libstdc++
available in runtime to satisfy the GPU analysis requirements. For older versions of the product, follow procedures to enable manual configuration.
GPU Compute/Media Hotspots analysis extended with GPU in-kernel analysis for OpenCL™ code and an option to filter by a kernel of interest
Extension to Command Line Analysis
The report generated when you run
hotspots
analysis from the command line now includes GPU analysis data. Apply the
computing-task
and
computing-instance
groupings to your collected data to focus on time-consuming computing tasks.
Dynamic Instruction Count Collection in GPU Compute/Media Hotspots Analysis
The GPU Compute/Media Hotspots analysis has been improved to include Dynamic instruction count collection. The analysis results provide better accuracy for basic block Assembly analysis
FPGA Accelerators
Multiple enhancements to CPU/FPGA Interaction Analysis
The CPU/FPGA Interaction analysis type features several new additions to enhance your FPGA profiling experience.
Analysis results now display
Activity percentage
and
Idle percentage
metrics to describe the proportion of cycles when a channel instruction was enabled or absent.
The analysis type can now profile loops and display occupancy information for them.
You can now adjust the depth of channels using
Average depth
and
Maximum depth
information that displays in the analysis results.
Performance Summary:
Performance Snapshot Analysis Type for Quick Summary
Use Performance Snapshot as the starting point for your performance analysis. Get a quick overview of issues that affect your application performance. Performance Snapshot provides recommendations for next steps to help you select other analyses for deeper profiling. It also characterizes the workload on the system.
Algorithm Group
Anomaly Detection Analysis for Performance Anomalies
Use the Anomaly Detection analysis type in the
Algorithm
group to detect performance anomalies in frequently recurring code intervals including loop iterations. Anomaly Detection uses Intel® Processor Trace (Intel® PT) technology to perform detailed analysis at the microsecond level. These are some metrics that get highlighted in analysis results when
Intel® VTune™
Profiler
identifies a performance anomaly:
Instructions Retired
Kernel CPU Time
User CPU Time
Inactive/Wait Time
CPU Frequency
Anomaly Detection can also detect hypervisors that do not have support for processor trace virtualization through Intel® Processor Trace (Intel® PT).
Parallelism:
Support for OpenMP Offload in HPC Analysis
The HPC Performance Characterization analysis type supports the offload of OpenMP regions. The summary pane now includes a breakdown of OpenMP offload time by
Compute
,
Data Transfer
, and
Overhead
. The bottom-up pane now allows grouping by
OpenMP Offload Region
. With this grouping active, the grid displays several new columns. The timeline shows scale markers that indicate the span of OpenMP offload regions and OpenMP operations internal to those regions.
I/O Analysis
Improvements and Changes to Input and Output Analysis
The Input and Output analysis type features a new methodology for locating sources of reads and writes targeting Memory-Mapped I/O (MMIO) address space regions to which I/O devices are mapped. Such
MMIO reads and writes
are expensive loads and stores resulting in
Outbound PCIe traffic
.
The collection of source-level Memory Mapped I/O (MMIO) data in the Input and Output analysis supports InfiniBand* devices.
Platform I/O metrics can now be attributed to individual devices managed by Intel® VMD technology.
Per-device metrics are now available when running Input and Output analysis as a non-root user, as long as the sampling driver is loaded.
Enhanced profiling for servers based on Intel® processor microarchitectures codenamed Skylake and Cascade Lake by highlighting code that potentially performs MMIO reads.
This analysis type features
Inbound PCIe Read/Write L3 Hit/Miss Ratio
metrics that show the utilization efficiency of Intel® Data Direct I/O (Intel® DDIO) hardware technology. There are new metrics for Intel® Xeon® Scalable processors that allow data break down by PCIe devices. Input and Output analysis is deprecated in the Windows version of
Intel® VTune™
Profiler
.
Energy Analysis
Rootless Data Collection on Linux Systems
You do not require root privileges to run energy analysis using
Intel® VTune™
Profiler
in a Linux environment. You can run this analysis without root privileges once your system administrator installs sampling drivers for
Intel® VTune™
Profiler
and configures relevant permissions for the drivers. Administrator privileges are required to collect energy data in Windows machines.
Processor Package Energy Consumption
Options for Energy analysis, based on the Intel SoC Watch data collector, have been extended to monitor processor package energy consumption over time and identify how it correlates with CPU throttling
Platform Analysis:
Enhancements to System Overview Analysis
Use the System Overview analysis as an entry point to platform analysis. Assess your system (IO, accelerators and CPU) performance and get guidance for further analysis steps.
The System Overview analysis can display energy consumption data. Enable the
Analyze energy usage
option to get energy consumption characterization on the
Summary
tab with the total energy consumed by CPU packages and DRAM, as well as overtime energy consumption data on the
Platform
tab.
The Hardware Tracing mode in the System Overview analysis enables application analysis at the micro-second level and helps you to identify causes for latency. These are some metrics you can collect:
User/kernel metrics
OS Kernel Activity
OS Scheduling
Thread/Hardware grouping
Module entry points
The metrics help identify anomaly issues caused by unexpected kernel activity or preemptions.
Improvements to Platform Profiler:
Overview and Memory views are extended with new metrics to analyze Non-Uniform Memory Access (NUMA) behavior
User authentication and authorization has been added to enable access control to your data
There is a new option to choose or modify the location of Platform Profiler data files
VTune
Profiler
Server for HPC Environment
A quality-of-life improvement was added to
VTune
Profiler
Server. If you use
VTune
Profiler
CLI to run data collection using a scheduler in an HPC cluster and put the results into a mounted shared location, you can now point
VTune
Profiler
Server to an arbitrarily structured folder in this shared location.
VTune
Profiler
now discovers all results in a directory and allows you to seamlessly navigate your arbitrary folder structure and open any result.
HPC Analysis
Application Performance Snapshot includes
Max
and
Bound
Bandwidth metrics to better estimate the efficiency of the DRAM, MCDRAM, Intel Persistent Memory and Intel® Omni-Path usage
Cloud and Containerization
Use Containerization support to install and run
VTune
Profiler
in a Docker* container and profile targets both inside the same container as well as outside the container
This release extends container profiling capabilities to display the container name instead of its ID for ease of identification.
You can profile applications running in Amazon Web Services* (AWS) EC2 Instances based on Intel microarchitecture code name Cascade Lake X.
Connection Types
New TCP/IP Communication Agent
Use the TCP/IP communication agent as a connection type to profile embedded systems running real-time operating systems. You can profile the kernel of an arbitrary real-time operating system and the applications running on it. This requires the development of a custom agent (Analysis Communication Agent). A reference solution based on Linux OS is available through the Analysis Communication Agent GitHub* repository. Detailed information on developing an agent for a specific real-time operating system is available in the ACA documentation.
Remote Linux (SSH) Connection Type
The Remote Linux (SSH) connection type has been improved to make automated target package deployment more transparent. Now
VTune
Profiler
checks for the presence of the target package on the remote system and offers to deploy the package automatically with a single click of a button if the package is not found.
Quality and Usability
Symbol resolution for effective source-level analysis enabled for crossgen (Ahead-of-JIT compilation) functions on Linux* systems
Interactive
Help Tour
available from the Welcome page and guiding you through the product interface using a sample project
The third-party components updated to the most recent versions to include functional and security changes. You are recommended to update your product to the latest version.
Profiling Support for OpenSHMEM Applications
Use the Fabric Profiler feature in VTune Profiler to identify detailed characteristics of the runtime behavior for an OpenSHMEM application.
Profiling Support for Applications Annotated with ITT API
Average Task Time
and
Average Frame Time
metrics are now included in analysis results when you profile applications annotated with ITT API .
Profiling Remote Amazon Web Services* Instances
There exists support for remote profiling of applications running in Amazon Web Services* (AWS) EC2 instances.
Support for DPC++ Applications
Demangling of Lambda Functions
This release implements the demangling of DPC++ lambda function names, which are used as DPC++ kernel names.
Analysis Configuration:
Wrapper Script Option for Quick Profiling Environment Setup
Use the Wrapper script to run a custom set of commands to prepare the profiling environment before you start analysis in the environment. For example, you can create a script with a custom set of commands that sets environment variables. Include the custom set in the
WHAT
pane when you configure the analysis. The commands get executed on the target system before the analysis begins. You can also provide the wrapper script through the command-line interface by using the
--wrapper-script-path
option.
Documentation:
PDF version of User Guide
The
Intel® VTune™
Profiler
User Guide is available in PDF format as well as HTML. If you are viewing this content online, click
Download as PDF
at the top of this page to use the PDF version.

Support for Data Parallel C++ (DPC++) code profiling added across CPUs and multiple accelerator architectures, including GPUs and FPGAs
GPU Offload and GPU Compute/Media Hotspots types extended to support profiling DPC++ code and OpenMP* code offloaded to the GPU
CPU/FPGA Interaction analysis extended with FPGA device-side metrics, like Stalls, Global Bandwidth and Occupancy, and mapping FPGA kernel performance data to the source code
GPU Time and Utilization metrics added to Application Performance Snapshot to help you triage your performance issues and identify whether your code is CPU or GPU bound