Stream HPC

IWOCL 2019

On Monday May 13, 2019 at 09:30 the latest edition of IWOCL starts, not taking into account any pre-events that might be spontaneously organized. This is the biggest OpenCL-focused event that discusses everything that would make any GPGPU-programmer, DSP-programmer and FPGA-programmer enthusiastic.

What’s new since last year, is that it’s actually also more interesting place for CUDA-developers who like to learn and discuss new GPU-programming techniques. This is because Nvidia’s GTC has moved more to AI, where it used to be mostly GPGPU for years.

Since it’s now the last week of the early-bird pricing, it’s a good time to make you think about buying your ticket and book the trip.

Where

Last year was in Europe, and this year’s edition is back in the USA. Northeastern University is hosting the conference spanning three days. It includes tutorials, many speakers and an always entertaining social event. For those who fly from Europe, look what https://flysmarter.de/ is suggesting, as they have some surprising suggestions for long flights. Another one that works for me well is https://skiplagged.com/flights/ams/bos/2019-05-12 that is quite strong with flights within the USA. Please share in the comments what you suggest other IWOCL-travellers!

## The talks

The talks are very diverse, as are the speakers. Personally I’ve gotten some very good insights from IWOCL talks.

  • Profiling OpenCL Kernels Using Wavefront Occupancy with Radeon GPU Profiler
  • Advances in the OpenCL Offload Support in GROMACS
  • Comparative Performance Analysis of Vulkan Implementations of Computational Applications
  • Developing Performance-Portable OpenCL Code via Multi-Dimensional Homomorphisms
  • Evaluating Portability and Performance of OpenCL FPGA Kernels on Intel HARPv2
  • Khronos Update – OpenCL, SYCL and SPIR – The Next Steps
  • The Landscape of C++ Heterogeneous Computing and Safety Critical API
  • Khronos Panel Discussion
  • Blurring the Boundary between CPU and GPU
  • Accelerated Neural Networks on OpenCL Devices Using SYCL-DNN
  • How to Deploy AI Software to Self Driving Cars
  • Breaking the Last Line of Performance Border
  • Performance Evaluation of OpenCL Standard Support (and Beyond)
  • OpenCL vs: Accelerated Finite-Difference Digital Synthesis
  • The Challenge of Targeting Scratch-pad Memory Devices with OpenCL
  • Exploring Integer Sum Reduction using Atomics on Intel CPU
  • MGSim: a Flexible High-Performance Simulator for Multi-GPU Systems

One thing they all have in common: they are about sharing practical experience and giving useful technical insights. More detailed information can be found on the IWOCL program page.

The tutorials

The first day is full of tutorials

  • Advanced Hands-On-OpenCL: don’t know the difference between OpenGL and OpenCL? Start here.
  • Optimizing OpenCL for Intel FPGAs: for those who want to apply their OpenCL knowledge to FPGAs
  • DHPCC++ 2019: a mini-conference on how C++ in the future (and SYCL now) can be used to program GPUs.

The meeting others

Probably the most interesting thing in this conference is meeting others. You’ll find writers of books (be sure to get your copy of “Heterogeneous Computing with OpenCL 2.0” signed, or buy it at the conference), makers of the tools who can answer why that one feature is not in there and very experienced developers who like to learn from you as much as you would like to learn from them.

Want to know more? Go to the IWOCL homepage now.

Buy tickets

Use the below EventBrite ticket selection or go the IWOCL-page.

var exampleCallback = function() {
    console.log('Order complete!');
};
window.EBWidgets.createWidget({
    // Required
    widgetType: 'checkout',
    eventId: '51714142392',
    iframeContainerId: 'eventbrite-widget-container-51714142392',
    // Optional
    iframeContainerHeight: 625,  // Widget height in pixels. Defaults to a minimum of 425px if not provided
    onOrderComplete: exampleCallback  // Method called when an order has successfully completed
});

Interest rates for GBP: