Vampir meets SC23
We would like to welcome you at SC23 in Denver! Our performance visualizer for parallel programs provides graphical visualization of massively parallel applications. Learn how we walk the road to exascale at our booth #1553 from November 13 to November 16. Additionally, you can engage with our experts in various activities of the SC23 technical program. We showcase the latest version of our tool suite which now includes support for TensorFlow- and PyTorch-applications technology that enables to analysis also large trace data not possible with browser based visualization. Finally, we also demonstrate an advanced prototype for workflow analysis based on the wfcommons format.
At SC23 we unveil Vampir 10.4 that provides the ability to visualize Chrome Trace Event files.
Vampir Website
Score-P is the primary code instrumentation and run-time measurement framework for Vampir 10, and also works natively with Scalasca and TAU.
It supports an extensive set of events such as function and library calls, communication events, and hardware counters. Score-P supports various instrumentation methods, including instrumentation at source level and at compile/link time. Vampir and Score-P provide a performance tool framework with special focus on highly-parallel applications. Performance data is collected from multi-process (MPI, SHMEM), thread-parallel (OpenMP, Pthreads), as well as accelerator-based paradigms (CUDA, HIP, OpenCL, OpenACC).
Score-P Website
At SC23 we unveil Vampir 10.4 that provides the ability to visualize Chrome Trace Event files.
Vampir Website
Score-P is the primary code instrumentation and run-time measurement framework for Vampir 10, and also works natively with Scalasca and TAU.
It supports an extensive set of events such as function and library calls, communication events, and hardware counters. Score-P supports various instrumentation methods, including instrumentation at source level and at compile/link time. Vampir and Score-P provide a performance tool framework with special focus on highly-parallel applications. Performance data is collected from multi-process (MPI, SHMEM), thread-parallel (OpenMP, Pthreads), as well as accelerator-based paradigms (CUDA, HIP, OpenCL, OpenACC).
Score-P Website
Our events on SC23
| Time | Room | Type | Title |
|---|---|---|---|
| Sun, 12th November 09:00 AM - 12:30 PM | 710 | Workshop | FROOM: A Framework of Operators for OTF2 Modification |
| Mon, 13th November 08:30 AM - 05:00 PM | 402 | Tutorial | Hands-On Practical Hybrid Parallel Application Performance Engineering |
| Wed, 15th November 05:15 PM - 06:45 PM | 501-502 | Birds-of-a-Feather | The Green500: Trends in Energy-Efficient Supercomputing |
| Wed, 15th November 12:15 PM - 01:15 PM | 708 | Birds-of-a-Feather | Updates from the HPC Certification Forum |
| Thu, 16th November 02:00 PM - 02:15 PM | 505 | Doctoral Showcase Poster | Interactive In-Situ Visualization of Large Distributed Volume Data |
