Interested in hosting our trainig course? Contact us.

KernelGen -- A prototype of auto-parallelizing Fortran/C compiler for NVIDIA GPUs

The KernelGen project aims to develop Fortran and C compilers based on the state-of-art open-source technologies for automatic GPU kernels generation from unmodified CPU source code, significantly improving the code porting experiences. Parallelism detection is based on LLVM/Polly and CLooG extended with mapping of loops onto GPU compute grid, and assisted with runtime alias analysis. PTX assembly code is generated with NVPTX backend. Thanks to integration with GCC frontend by means of DragonEgg plugin, and customized linker, KernelGen is able to compile complex applications into GPU-enabled binaries. The session will consist of three parts: the KernelGen programming model and its motivation, an overview of compiler design based on frontend-LLVM-NVPTX chain, and the end-user look onto performance results both for small tests (in comparison to OpenACC compilers), and for complex applications with large portion of parallelizable PDE stencil codes: WRF and COSMO models. Presented by Dmitry Mikushin (Doctoral assistant, University of Lugano), Nikolay Likhogrud (Engineer, Applied Parallel Computing LLC), Sergey Kovylov (Tesla & Quadro Solution Architect, Russia & CIS, NVIDIA).

Formats: Video

Date:

Advanced GPU computing: GPU architecture, CUDA shared memory

In this excellent talk Mr. Juraj Kardos explains advanced CUDA programming topics.

Formats: Video

Date:

Advanced GPU computing: Efficient CPU-GPU memory transfers, CUDA streams

In this excellent talk Mr. Juraj Kardos explains advanced CUDA programming topics.

Formats: Video

Date:

Introduction to GPU computing

Formats: Video

Date:

Introduction to CUDA

Formats: Video

Date:

Generic approach to Legacy Fortran code porting on GPU

In this seminar we will present our experience with porting 200K line Fortran codebase onto GPU: SixTrack model - the LHC Accelerator Beam Dynamics. We will present the steps of source code transformation, modifications into crlibm and cernlib, compilation and execution.

Formats: Video

Date:

Adopting Fortran legacy code for ensemble simulations on GPU: the experience with Sixtrack

In this seminar we will present our experience with porting 200K line Fortran codebase onto GPU: SixTrack model - the LHC Accelerator Beam Dynamics. We present the steps of source code transformation, compilation and execution.

Formats: Video

Date:

Introduction au calcul par le GPU et à son architecture

Introduction to GPU computing and architecture in French by Dr. Flavio Calvo

Formats: Video

Date:

Introduction à CUDA

Introduction to CUDA in French by Dr. Flavio Calvo

Formats: Video

Date:

Advanced aspects of CUDA

Advanced aspects of CUDA programming presented by Juraj Kardos

Formats: Video

Date:

Introduction à CUDA

Introduction to CUDA in French by Dr. Gabriel Noaje

Formats: Video

Date:

Introducción a CUDA (parte 1)

Introduction to CUDA in Spanish by Dr. Mario Martinez-Zarzuela

Formats: Video

Date:

Introducción a CUDA (parte 2)

Introduction to CUDA in Spanish by Dr. Mario Martinez-Zarzuela

Formats: Video

Date:

Introducción a CUDA (parte 3)

Introduction to CUDA in Spanish by Dr. Mario Martinez-Zarzuela

Formats: Video

Date:

Introducción a CUDA (parte 4)

Introduction to CUDA in Spanish by Dr. Mario Martinez-Zarzuela

Formats: Video

Date: