Versionen im Vergleich

Schlüssel

  • Diese Zeile wurde hinzugefügt.
  • Diese Zeile wurde entfernt.
  • Formatierung wurde geändert.

...

Day 2 (Wednesday; March 3rd, 2021)



TOPICPresenter
09:0009:10

Welcome and Introduction to Day 2 

(presentation recording)

Edmund Preiss (Intel),
Thomas Steinke (ZIB)
09:1010:10

A oneAPI Case Study: easyWave - A Tsunami Simulations Application
with demos ZIB's experiences with Intel oneAPI       
- Porting a tsunami application from CUDA to DPC++
- Running DPC++ code on GPU
- From CUDA to DPC++ back to Nvidia GPUs... and FPGAs
- A oneAPI case study with the tsunami simulation easyWave

Live Demos:  Christgau_playbook.tar.gz
(1) overview on CUDA code,
(2) CUDA code execution
(3) guided transformation with Compatibility Tool,
(4) presentation/analysis of generated DPC++ code,
(5) execution on different architectures (Intel CPU + GPU, Nvidia GPU)

Steffen Christgau (ZIB)
(Marius Knaust, ZIB)
10:1010:50Intel OpenMP – with Demos
- Parallelizing heterogenous applications with Intel OpenMP and OpenMP offloading
Michael Steyer (Intel)
10:5011:00Bio Break
11:0011:45Intel HW (public) roadmap/XPU and architecture specifics
- Server CPUs
- Client CPUs (i.e., Tigerlake; iCore with integrated graphics)
- Intel hardware accelerators GPUs (DG1, SG1, ATS)  and Intel FPGAs
Jean-Laurent Philippe (Intel)
11:4512:15A oneAPI Case Study: Ginkgo – a sparse linear algebra library for OneAPI Hardware
Experience and potential of using oneAPI for the Ginkgo sparse linear algebra library       
- Porting of numerical linear algebra kernels from Cuda to DPC++
- Pitfalls and solutions in the OneAPI Compatibility Tool
- Performance of Ginkgo’s DPC++ backend on Intel GPU
- Live demo running Ginkgo in the Intel DevCloud 
Hartwig Anzt (KIT)
 (Y. Tsai, T. Cojean, KIT)
12:1513:15Lunch Break
13:1514:30Application profiling for heterogenous hardware - Demos
- Profile DPC++ and GPU Workload VTune Profiler and VTune Offload
- Share experiences/key findings  with Gromacs related porting and optimization efforts 
Heinrich Bockhorst (Intel)
14:3014:35Bio Break
14:3515:35

Application profiling for heterogenous hardware - Demos
- Profile DPC++ and GPU Workload with Advisor include and Roofline analyser
- Estimate performance potential gains with Offload Advisor ( CPU -> HW Accelerator)

Playbook_Advisor_GPU_NBody.txt

Klaus-Dieter Oertel (Intel)
15:3516:00- Questions and Answers
- Wrap up 
Intel / ZIB

...