Join Khronos at Supercomputing for a look at how OpenCL along with SYCL, SPIR, and Vulkan are playing their parts in HPC today.
Bookmark this web page as your information hub to everything Khronos at SC’16.
Visit the Khronos Booth #304
Visit us in the Khronos booth!
We will have people in the booth from the Khronos working groups who can answer your technical questions about OpenCL, SYCL, and SPIR.
Get your free Khronos Stuff
We're giving away more than a place to sit and interesting talk about our favorite technologies. Get your free HPC t-shirt, OpenCL sticker, and reference guides for OpenCL and SYCL at the Khronos booth.
Booth Talks and Beer
Join us in the booth at 4pm on Tuesday and Wednesday to have a free beer and talk with Khronos members.
Also, Khronos members Xilinx and Codeplay will be in the booth to answer questions, give talks, and show demos:
This year at SC we want to show where OpenCL fits in with the larger pantheon of open standards for HPC. This panel includes a range of standards body members and vendors to discuss the topic of open standards for HPC. Our panelists are experts with a diverse point of view, not only on where HPC is today, but where we should go from here.
Moderator: Andrew Richards OpenCL: Tim Mattson OpenMP: Bronis R. de Supinski MPI: Martin Schulz HSA: Greg Stoner OpenACC: Michael Wolfe ISO C++: Michael Wong ISO Fortran: Kelvin Li
Khronos-related Courses, Papers, and Sessions
Harnessing the Power of FPGAs with Altera’s SDK for OpenCL
In this tutorial, you will learn why Field Programmable Gate Arrays have become so popular in HPC and have been outpacing the overall semiconductor industry in terms of adoption and growth. Furthermore, we will cover architectural features, such as hardened floating point DSPs and on-chip memory, of FPGAs that make them well suited to many applications traditionally run on multicore CPUs and GPUs at much higher performance per watt. In addition, we will introduce programming FPGAs using Altera’s SDK for OpenCL and how specific OpenCL coding techniques can lead to efficient circuits implemented on the FPGA. Finally, we will go over several case studies where FPGAs have shown very competitive performance when programmed using OpenCL, including convolutional neural nets, FFTs, and astronomy de-dispersion algorithms.