Sycl Academy LogoSycl Academy Logo
listShow Lessons List
  1. What is SYCL
  2. Enqueueing a Kernel
  3. Managing Data
  4. Handling Errors
  5. Device Discovery
  6. Data Parallelism
  7. Introduction to USM
  8. Using USM
  9. Asynchronous Execution
  10. Data and Dependencies
  11. In Order Queue
  12. Advanced Data Flow
  13. Multiple Devices
  14. ND Range Kernels
  15. Image Convolution
  16. Coalesced Global Memory
  17. Vectors
  18. Local Memory Tiling
  19. Further Optimisations
  20. Matrix Transpose
  21. More SYCL Features
  22. Functors
Lesson
Source
Solution
GitHub Iconedit

Data Parallelism

In this exercise you will learn how add the values in two arrays and write the results to another array in parallel using parallel_for.

1.) Create your queue

Create a queue to enqueue your kernel function to, remember to handle errors.

2. ) Create buffers

Create buffers to manage the data of the two input arrays and output array.

Remember to ensure the range provided to the buffer is the size of the arrays.

3. ) Create accessors

Create accessors to each of the buffers within the command group function.

4. ) Write the kernel function

Now enqueue parallel kernel function by calling parallel_for on the handler.

This function takes a range specifying the number of iterations of the kernel function to invoke and the kernel function itself must take an id which represents the current iteration.

The id can be used in the accessor subscript operator to access or assign to the corresponding element of data that the accessor represents.

Build And Execution Hints

For DevCloud via JupiterLab follow these instructions.

For DPC++: instructions.

For AdaptiveCpp: instructions.