What's New in
Intel® Advisor 2023.0
Intel® Advisor 2022.1
- Performance metrics in GPU Roofline Source view in theIntel AdvisorGUIIn theGPU Roofline Insightsreport, you can switch toSource Viewand examine the source code of your application with performance metrics for each kernel, such as elapsed time and memory traffic.
- New panes in an interactive HTML Report: GPU Details in theGPU Roofline Insightsperspective and Data Transfer Estimations in theOffload ModelingperspectiveThe interactive HTML report, which combinesOffload ModelingandGPU Roofline Insightsresults, now includes two new panes, which are similar to the panes with the same name in theIntel AdvisorGUI report:
You can use the interactive HTML reports to analyzeIntel Advisorresults on a remote machine using your web browser or share the results. See Work with Standalone HTML Reports for details.
- GPU Roofline Insightsperspective includes theGPU Detailspane, which reports detailed code analytics for a selected kernel, such as Roofline guidance with the main limiting roof and estimated speedup after optimization, compute and memory bandwidth, memory usage metrics.
- Offload Modelingperspective includes theData Transfer Estimationspane, which reports estimated data transferred between host and target devices in each direction and a list of offloaded objects.
- :Offload Modeling
- Adjustable hardware parameters in an interactive HTML report and GUI reportOffload Modelingreport includes a newModeling Parameterspane, which shows available target devices for modeling and hardware configuration parameters for a selected device. Each parameter is a slider that you can adjust to a desired value to get a custom configuration for remodeling.The pane is available in the interactive HTML report andIntel AdvisorGUI report and has the same functionality. You can use it to:
See Model Application Performance on a Custom Target GPU Device for more information about how to work with the pane.
- Examine device parameters that the application performance was modeled on to understand how they affect the estimated performance.
- Change the target device to compare the new configuration with the current modeled device.
- Adjust the parameters and remodel performance for a custom device. You can experiment with parameters to see how they affect the application performance or adjust the configuration to model performance for a future or a specific device not listed in the target devices. See the sections below for a full workflow.For CPU-to-GPU modeling, you can remodel performance usingIntel AdvisorCLI only.
- New recommendation to optimize data transfer costs with data reuse when porting your application from a CPU to a GPUOffload Modelingperspective introduces a new actionable recommendation for optimizing data transfer costs with data reuse before porting your application from a CPU to a GPU. Data reuse can help you improve the application performance on the GPU by optimizing data transfer efficiency.The recommendation is reported in a Recommendations pane of the Accelerated Regions tab. The recommendation includes estimated performance characteristics and data reuse gain, as well as code snippet examples for applying data reuse techniques.See Examine Data Transfers for Modeled Regions for details.
- Sample-based scenario for theOffload Modelingperspective in the Get Started withIntel AdvisordocumentIdentify High-impact Opportunities to Offload to GPU topic in the get started guide now uses a sample to introduce the mainOffload Modelingfeatures. You can download the sample or use your own application to follow this topic instructions and understand the basicOffload Modelingworkflow with theIntel Advisor.The following topics in the get started guide with a sample-based scenario are also available:
Intel® Advisor 2022.0
- GPU Roofline:
- New recommendation to optimize GPU general purpose register file (GRF) usage and improve performance.TheGPU Roofline Insightsperspective introduces actionable recommendations for improving your application performance on GPU by optimizing GRF usage. The recommendations are reported in aRecommendationspane in theGPU Roofline Regionsreport. See Get Recommendations for details.
- New GPU memory and compute metrics.TheGPUpane in theGPU Roofline Regionstab introduces several new metrics. Some of the new metrics are:Memory metrics:Compute metrics:
- Command-line cheat sheet for quick referenceIntroduced a new downloadableIntel Advisorcommand-line cheat sheet, which lists the most useful command-line interface (CLI) options. You can use this print-friendly PDF for quick reference on theIntel AdvisorCLI.