Capitalizing on multi-GPU resources

Contend with the challenge of systems with multiple GPUs.

Explore expert techniques for programming with SYCL to develop optimized multi-GPU applications. Get equipped with the latest Intel technology, thanks to Intel® Tiber™ Developer Cloud (ITDC) running 4th Gen Intel® Xeon® Scalable processors and Intel® Data Center GPU Max 1100. This workshop is geared to intermediate to advanced programmers who want to take maximum advantage of the GPU resources available in a system.

Topics covered in the workshop include:

Determining available GPUs for offloading compute tasks
Assigning compute kernels to multiple GPUs with SYCL code
Using SYCL code to split workloads across multiple GPUs
Writing portable SYCL code that taps available GPUs resources
Optimizing SYCL code to execute kernels concurrently across the full range of GPUs

Examples and hands-on demonstrations on ITDC give a practical view of the techniques available to efficiently harness the GPUs in a system. An ITDC account is required to participate in hands-on activities. If you don’t have one, get one here.

Join us at this workshop to advance your understanding of SYCL programming techniques and distributing GPU resources.

Welcome back Not you?

First Name

Please enter a first name.

First name must be at least 2 characters long.

First name must be less than 250 characters long.

Please enter a first name.

Last Name

Please enter a last name.

Last name must be at least 2 characters long.

Last name must be less than 250 characters long.

Please enter a last name.

Business Email Address

Please enter an email address.

Please enter a valid email address.

Email Address must be less than 250 characters.

Country/Region

Please select a country/region.

Your registration cannot proceed. The materials on this site are subject to U.S. and other applicable export control laws and are not accessible from all locations.

Profession

Please select a profession.

Business Phone

Please enter a business phone.

Business phone must be at least 2 characters long.

Business phone must be less than 250 characters long.

Please enter a business phone.

Please enter a valid business phone.

Company

Please enter a company name.

Company name must be at least 2 characters long.

Company name must be less than 250 characters long.

Please enter a company name.

What type of developer are you?*

Please select a developer role.

Development Language (select all that apply)*

Please select a development language.

Which hardware and accelerator architectures are you developing for? (select all that apply)*

Please select at least one option.

Industry *

Please select an industry.

What operating systems do you develop for/on? (select all that apply)*

Please select at least one operating system.

Intel strives to provide you with a great, personalized experience, and your data helps us to accomplish this.

I consent to Intel collecting and using my personal information as described below.

Above consent required for submission.

I expressly consent to Intel transferring my Personal Data outside of China to Intel U.S. headquarters as described in the Intel Privacy Notice Supplement for Users in China.

Above consent required for submission.

Intel may contact you for marketing-related communications. You can opt out at any time.

By submitting this form, you are confirming you are age 18 years or older. Intel may contact you for marketing-related communications. You can opt out at any time. To learn more about Intel's practices, including how to manage your preferences and settings, visit Intel's Privacy Notice.

By submitting this form, you are confirming you are age 18 years or older. Intel will process your Personal Data for the purpose of this business request. To learn more about Intel's practices, including how to manage your preferences and settings, visit Intel's Privacy Notice.

Programming and Optimizing Multi-GPU Applications with SYCL

Contend with the challenge of systems with multiple GPUs.

Speakers

Rakshith Krishnappa

Praveen Kundurthy