7th GPU Day 2017 - The Future of Many-Core Computing in Science

27 March 2017

Just like the previous years, the Wigner GPU Lab again organizes the annual conference on massively parallel technologies and their applications in different fields, where researchers and developers can share experiences, ideas and results.

This year, the conference will be between 22-23 June 2017, Thursday-Friday, in the Wigner Datacenter, as usual. Further information, abstract submission and registration is here

Lectures on Modern Scientific Programming 2016

26 October 2016

Just like last year, the Wigner GPU Lab organizes a three day seminar series on modern scientific programming. The main topics this time revolve around CPU parallelism in C++, usage of algorithms, GPU programming with the new SYCL / ComputeCpp API and introduction to the Python language.

Again, a special session will be dedicated to newcomers to C++.

The lectures will be held between 14-16. November 2016.

For further details and registration, continue reading here.

CODEPLAY releases its SYCL implementation

20 Septeber 2016

CODEPLAY released "ComputeCpp" the first GPU accelerated implementation of SYCL, the high-level parallel standard created by Khronos.

The compiler is still in beta and only released for linux, but it makes possible to generate host and device code from singe source C++11 utilizing massively parallel and hierarchically parallel constructs.

The OpenCL 1.2 based technology runs on AMD and Intel devices at the moment, and provides acceleration support for the Eigen linear algebra, the VisionCpp machine vision and the C++17 parallel STL libraries.

The compiler will be available for windows soon, and will be available for commercial and non-commercial users. As a next step, it will build upon OpenCL 2.2 and will support the now provisional SYCL 2.2 specification in an upcoming version.

The compiler is available after registration from the webpage of CODEPLAY.

Accelerated projects and useful information are also available on the website.

Xeon Phi (KNC) Workshop

13 September 2016

NIIF Programme is announcing Xeon Phi (Knights Corner) Workshop, sponsored by Intel and HPE. This workshop is held by Bayncore, expert trainers of HPC Technologies.

This hands-on experience will introduce the audience into Tools and Techniques programming Xeon Phis in HPC environment, allowing attendees to try those out during the time of the Workshop.

Make sure to bring your notebook with your favourite ssh client installed, and a public/private keypair generated, if not having accounts on our servers. We can help you generating and installing keys onsite, if you arrive at 8:30.

This event has a really high value, and is exepctional of its kind in the region. Consume less core hours on NIIF HPCs by utilizing Xeon Phis by just using simple tools and simple programming techniques. Gain experience of using one of the trending technologies, and became an expert of using Phis to boost computations on your scientific field.

The event is free to attend thanks to our sponsors.

Details and registration:

Meet You There!