Introduction to SYCL Essentials
Module 1: oneAPI Intro
Module 2: DPCPP Program Structure
Module 3: DPCPP Unified Shared Memory
Module 4: DPCPP Sub-Groups
Module 5: Intel® Advisor
Learning Objectives
Module 6: VTune™ Profiler
Module 7: DPCPP Library
Module 8: DPCPP Reduction
Module 9: DPCPP Buffers And Accessors In Depth
Module 10: DPCPP Graphs Scheduling Data Management
Module 11: Intel® Distribution for GDB
Module 12: DPCPP Local Memory And Atomics
Module 5: Intel® Advisor
This module demonstrates various aspects of Intel® Advisor. The first uses Intel Advisor to show performance offload opportunities found in a sample application, followed by additional command-line options for getting offload advisor results. The second gives an example of roofline analysis and command-line options for getting Advisor results.
Learning Objectives
Show how Intel Advisor can help you decide which part of the code should or should not be offloaded to the accelerator.
Run Offload Advisor and generate an HTML report.
Read and understand the metrics in the report.
Get a performance estimation of your application on the target hardware.
Decide which loops are good candidates for accelerator offload.