Intel® VTune™ Profiler

Cookbook

Download PDF
ID 766316
Date 3/22/2024
Public
Document Table of Contents
Document Table of Contents x
Cookbook
Cookbook x
Methodologies Configuration Recipes Tuning Recipes Notices and Disclaimers
Methodologies x
Analyzing Uncore Perfmon Events for Use of Intel® Data Direct I/O Technology in Intel® Xeon® Processors (NEW) Top-down Microarchitecture Analysis Method OpenMP* Code Analysis Method Custom Data Collection for Performance Analysis (NEW) Software Optimization for Intel® GPUs (NEW) Core Utilization in DPDK Apps PCIe Traffic in DPDK Apps DPDK Event Device Profiling Effective Utilization of Intel® Data Direct I/O Technology Compile a Portable Optimized Binary with the Latest Instruction Set
Configuration Recipes x
Profiling High Bandwidth Memory Performance on Intel® Xeon® CPU Max Series (NEW) Profiling Windows* Applications for Hybrid CPU Platforms (NEW) Viewing Analysis Results on a Web Browser (NEW) Profiling Machine Learning Applications (NEW) Profiling Single-Node Kubernetes* Applications (NEW) Analyzing Hot Code Paths Using Flame Graphs (NEW) Improving Hotspot Observability in a C++ Application Using Flame Graphs Measuring Performance Impact of NUMA in Multi-Processor Systems Profiling Games built with Unity* (NEW) Profiling Games built with Unreal Engine* (NEW) Profiling Java Applications as a Remote User (NEW) Profiling JavaScript* Code in Node.js* Analyzing CPU and FPGA (Intel® Arria® 10 GX) Interaction Profiling a .NET* Core Application Profiling Applications in Amazon Web Services* (AWS) EC2 Instances Enabling Performance Profiling in GitLab* CI Configuring a Hyper-V* Virtual Machine for Hardware-Based Hotspots Analysis Profiling an Application for Performance Anomalies (NEW) Profiling an OpenMP* Offload Application running on a GPU Profiling a SYCL* Application running on a GPU Profiling an FPGA-driven SYCL* Application Profiling Hardware Without Intel Sampling Drivers Profiling MPI Applications Profiling Docker* Containers Profiling a Remote Target Through a Proxy Server (NEW) Profiling in an Apptainer* Container Profiling Linux*, Android*, and QNX* System Boot Time Using Intel® VTune™ Profiler Server with Visual Studio Code and Intel® DevCloud for oneAPI (NEW) Using Intel® VTune™ Profiler Server in HPC Clusters Using the Command-Line Interface to Analyze the Performance of a SYCL* Application running on a GPU (NEW)
Tuning Recipes x
Cache-Related Latency Issues in Segmented Cache Environment False Sharing Frequent DRAM Accesses Poor Port Utilization Page Faults Instruction Cache Misses Ingredients Run Microarchitecture Exploration Analysis Identify Hardware Hotspots Compile Your Code Again with Profile Guided Optimization Verify Optimization See Also OS Thread Migration OpenMP* Imbalance and Scheduling Overhead Processor Cores Underutilization: OpenMP* Serial Time Scheduling Overhead in an Intel® oneAPI Threading Building Blocks Application PMDK Application Overhead
Cookbook

Instruction Cache Misses

Profile an application bound on the front-end and reduce ICache misses using the Microarchitecture Exploration analysis with the PGO option.

Ingredients

This section lists the hardware and software tools used for the performance analysis scenario.

  • Application: A test sample based on the sqlite database. The application is used as a demo and not available for download.

  • Tools:

    • Intel® VTune™ Profiler version 2018 or newer - Microarchitecture Exploration analysis

    • Intel® DPC++/C++ Compiler

  • CPU: Intel® microarchitecture code named Skylake

Run Microarchitecture Exploration Analysis

Get an overall assessment of potential performance bottlenecks in the application. Run the Microarchitecture Exploration analysis:

  1. In the Intel® VTune™ Profiler UI, click the New Project button on the toolbar. Specify a name for the new project, for example: sqlite.

  2. In the Analysis Target window, select the local host target system type for the host-based analysis.

  3. Select the Launch Application target type and specify an application for analysis.

  4. In the Analysis Tree, select Microarchitecture > Microarchitecture Exploration.

  5. Click Start.

Intel® VTune™ Profiler launches the application and collects data. When the collection completes, Intel® VTune™ Profiler finalizes the result and resolves symbol information. This is necessary for proper source analysis.

Identify Hardware Hotspots

The Microarchitecture Exploration analysis helps you identify dominant performance bottlenecks in your code. Start your analysis with the Summary view. Here, you see application-level statistics for each hardware metric. Focus on the performance issues that have been flagged:

In this example, the sample application is front-end bound (29.3% of Pipeline Slots) with the instruction cache misses as a dominant bottleneck (7.1% of Clockticks).

Next, locate the issue in the code by switching to the Bottom-up window. Click the Customize Grouping button, next to the Grouping toolbar. Create a new custom grouping called Module/Source File:

When we apply the new grouping to the collected results, we see that sqlite3.c file is the main hotspot which takes the most CPU cycles to execute:

The ICache Misses metric displays the highest value for the sqlite3.c file:

Compile Your Code Again with Profile Guided Optimization

Use the Intel® DPC++/C++ Compiler to apply Profile Guided Optimization (PGO) to the sqlite library:

  1. Compile your code once again with the /Qprof-gen option.

  2. Run the benchmark.

  3. Again, compile your code with the /Qprof-use option.

For more information on PGO, see the Profile-Guided Optimizations overview.

Verify Optimization

Repeat the Microarchitecture Exploration analysis on the optimized code. The new result shows 30.3 seconds of Elapsed time, which is almost 4% better than the original 31.5 seconds:

The number of clockticks stalled due to ICache Misses for the sqlite library has also reduced to 6.4% from 9.3%:

Parent topic: Tuning Recipes
Level Two Title