Essentials of SYCL*

Introduction to JupyterLab* and a Jupyter* Notebook

Use a Jupyter Notebook to modify and run code as part of learning exercises.

To begin, open Introduction_to_Jupyter.ipnyb.

Introduction to SYCL

• Articulate how oneAPI can help to solve the challenges of programming in a heterogeneous world.
• Use oneAPI solutions to enable your workflows.
• Understand SYCL standards and features.
• Become familiar with using Jupyter Notebooks for training throughout the course.

Program Structure

• Articulate the SYCL fundamental classes.
• Use device selection to offload kernel workloads.
• Decide when to use basic parallel kernels and ND Range Kernels.
• Create a host accessor.
• Build a sample SYCL application through hands-on lab exercises.

Unified Shared Memory

• Use new SYCL features like Unified Shared Memory (USM) to simplify programming.
• Understand implicit and explicit ways of moving memory using USM.
• Solve data dependency between kernel tasks in an optimal way.

Sub-Groups

• Understand advantages of using Sub-groups in SYCL.
• Take advantage of Sub-group collectives in ND-Range kernel implementation.
• Use Sub-group Shuffle operations to avoid explicit memory operations.

Demonstration of Intel® Advisor

• See how  Offload Advisor¹ identifies and ranks parallelization opportunities for offload.
• Run Offload Advisor using command line syntax.
• Use performance models and analyze generated reports.

¹Offload Advisor is a feature of Intel® Advisor installed as part of the Intel® oneAPI Base Toolkit (Base Kit).

Intel® VTune™ Profiler on Intel® Tiber™ AI Cloud

• Profile a DPC++ application using Intel® VTune™ Profiler on Intel Tiber AI Cloud.
• Understand the basics of command line options in Intel VTune Profiler to collect data and generate reports.

Introduction to oneDPL: A Set of oneDPC++ Libraries

• Simplify SYCL programming using Intel® oneAPI DPC++ Library (oneDPL).
• Use SYCL Library algorithms for heterogeneous computing.
• Implement oneDPL algorithms using buffers and unified shared memory.

Reductions in SYCL

• Understand how reductions can be performed with parallel kernels.
• Take advantage of the reduce function to do reductions at the sub_group and work_group level.
• Use the SYCL reduction extension to simplify reduction with parallel kernels.

Explore Buffers and Accessors in Depth

• Explain Buffers and Accessors in depth.
• Understand the Sub buffers and how to create and use Sub buffers
• Explain buffers properties and when to use host_ptr, set_final_data, and set_write_data
• Explain Accessors and the modes of accessor creation
• Explain host accessors and the different use cases of host accessors