Visible to Intel only — GUID: GUID-FF6CA42D-009A-48D5-AF34-D2DFBC599110
Visible to Intel only — GUID: GUID-FF6CA42D-009A-48D5-AF34-D2DFBC599110
Intel® Advisor User Guide
This document provides a detailed overview of the Intel® Advisor functionality, workflows, and instructions.
Intel® Advisor is composed of a set of tools, or perspectives, to help ensure your Fortran, C, C++, SYCL , OpenMP*, Intel® oneAPI Level Zero (Level Zero), and OpenCL™ applications realize full performance potential on modern processors:
Vectorization and Code Insights: Identify high-impact, under-optimized loops, what is blocking vectorization, and where it is safe to force vectorization. It also provides code-specific how-can-I-fix-this-issue recommendations. For details, see Analyze Vectorization Perspective[/topic/body/ul/li/p/xref/desc {"- topic/desc "}) Improve your application performance, get code-specific recommendations for how to fix vectorization issues and quick visibility into source code and assembly code by running the Vectorization and Code Insights perspective. (desc].
CPU / Memory Roofline Insights and GPU Roofline Insights: Visualize actual performance against hardware-imposed performance ceilings (rooflines). They provide insights into where the bottlenecks are, which loops are worth optimizing for performance, what are the likely causes of bottlenecks and what should be the next optimization steps. For details, see Analyze CPU Roofline[/topic/body/ul/li/p/xref/desc {"- topic/desc "}) Visualize actual performance against hardware-imposed performance ceilings by running the CPU / Memory Roofline Insights perspective. It helps you determine the main limiting factor (memory bandwidth or compute capacity) and provides an ideal roadmap of potential optimization steps. (desc] or Analyze GPU Roofline[/topic/body/ul/li/p/xref/desc {"- topic/desc "}) Measure and visualize the actual performance of GPU kernels using benchmarks and hardware metric profiling against hardware-imposed performance ceilings, as well as determine the main limiting factor, by running the GPU Roofline Insights perspective. (desc].
Offload Modeling: Identify high-impact opportunities to offload to GPU as well as the areas that are not advantageous to offload. It provides performance speedup projection on accelerators along with offload overhead estimation and pinpoints accelerator performance bottlenecks. For details, see the Model Offloading to a GPU[/topic/body/ul/li/p/xref/desc {"- topic/desc "}) Find high-impact opportunities to offload/run your code and identify potential performance bottlenecks on a target graphics processing unit (GPU) by running the Offload Modeling perspective. (desc].
Threading: Analyze, design, tune, and check threading design options without disrupting your normal development. For details, see Model Threading Designs[/topic/body/ul/li/p/xref/desc {"- topic/desc "}) Analyze, design, tune, and check threading design options without disrupting your normal development by running the Threading Perspective. (desc].
Flow Graph Analyzer is a part of the Intel® Advisor installation. Use it to visualize and analyze performance for applications that use the Intel® oneAPI Threading Building Blocks (oneTBB) flow graph interfaces. For details, see Flow Graph Analyzer.
Intel® Advisor is available as a standalone product and as part of the Intel® oneAPI Base Toolkit.
Documentation for older versions of Intel® Advisor is available for download only. For a list of available documentation downloads by product version, see these pages: