2021 Joint NHR@ZIB - INTEL oneAPI Workshop

09:00

09:10

(presentation recording)

Edmund Preiss (Intel),
Thomas Steinke (ZIB)

09:10

09:40

- Concept and oneAPI Standardization initiative
- Intel’s Tools Implementation – Intel oneAPI Toolkits and libs
- Transition from Intel Parallel Studio XE to Intel oneAPI toolkits

(presentation recording)

Edmund Preiss (Intel)

09:40

10:10

- Purpose: Demoing, testing and porting applications
- Hardware and Software offerings
- How to onboard & how to get an DevCloud account

(presentation recording)

Michael Steyer (Intel)

10:10

10:15

Bio Break

10:15

12:15

- Intro to DPC++ heterogenous programming model and SYCL 2020
- Fortran and offloading with OpenMP5.0
- DPC++ features and examples
   o  “Hello World” Example
   o  Device Selection
   o  Compilation and Execution Flow
   o  Execution Model
   o  Memory Model; Buffers, Unified Shared Memory (USM)
   o  Kernel Model

(presentation recording)

Igor Vorobtsov (Intel)

12:15

13:15

Lunch Break

13:15

14:15

            
- Migration Cuda based GPU Applications to oneAPI (DPC++)

(presentation recording)

Igor Vorobtsov (Intel)

14:15

15:00

- Performance optimized libraries for AI, numerical simulations and other purposes

(presentation recording)

Gennady Fedorov (Intel)

15:00

15:05

Bio Break

15:05

15:30

- Questions and Answers
- Wrap up 

Intel / ZIB

09:00

09:10

(presentation recording)

Edmund Preiss (Intel),
Thomas Steinke (ZIB)

09:10

10:10

       
- 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:  
(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)

(presentation recording)

Steffen Christgau (ZIB)
(Marius Knaust, ZIB)

10:10

10:50

- Parallelizing heterogenous applications with Intel OpenMP and OpenMP offloading

(presentation recording)

Michael Steyer (Intel)

10:50

11:00

Bio Break

11:00

11:45

- Server CPUs
- Client CPUs (i.e., Tigerlake; iCore with integrated graphics)
- Intel hardware accelerators GPUs (DG1, SG1, ATS)  and Intel FPGAs

(presentation recording)

Jean-Laurent Philippe (Intel)

11:45

12:15

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 

(presentation recording)

Hartwig Anzt (KIT)
 (Y. Tsai, T. Cojean, KIT)

12:15

13:15

Lunch Break

13:15

14:30

- Profile DPC++ and GPU Workload VTune Profiler and VTune Offload
- Share experiences/key findings  with Gromacs related porting and optimization efforts 

(presentation recording)

Heinrich Bockhorst (Intel)

14:30

14:35

Bio Break

14:35

15:35

- Profile DPC++ and GPU Workload with Advisor include and Roofline analyser
- Estimate performance potential gains with Offload Advisor ( CPU -> HW Accelerator)

(presentation recording)

Klaus-Dieter Oertel (Intel)

15:35

16:00

- Questions and Answers
- Wrap up 

Intel / ZIB

10:00

10:10

Welcome to Follow-Up Meeting

Edmund Preiss (Intel),
Thomas Steinke (ZIB)

10:10

10:30

Recent Updates on Intel oneAPI Development Toolkits
- Intel oneAPI 2021 / Update 2
- Selected new technicial features of Update 2

Public News about 3rd Gen Intel® Xeon® Scalable Processor (Ice Lake)

Edmund Preiss (Intel),
Igor Vorobtsov (Intel),


Jean-Laurent Philippe (Intel)

10:30

12:00

Q&A