导航|地址|刷新
Automatic Performance Profiling (APP)

Skip to Main Content
Funded bythe European Union

Sprite SVG Defs and Gradients

About

Project Timeline

Project Map

Team Members

Job Opportunities

Work Packages

WP1 - Support to effective applications

WP2 - Develop community tools

WP3 - Tackling the data challenge

WP4 - HPC Services to enchance Weather and Climate applications

WP5 - Training and capacity building

WP6 - Community engagement, dissemination and exploitation

WP7 - Project Management

Service

Services

What We Offer

Testimonials

Success Stories

Training

Training Events

Training Materials

Media

Videos

Logos & Templates

News

Events

Events

Training Events

Tools

HPCW

Data Compression Lab

AUTO-RPE

APP

Kernel Tuner

PSyclone

Results

Publications

Key Exploitable Results (KERs)

Contact

This link will open in a new window

This link will open in a new window

This link will open in a new window

This link will open in a new window

Search the site

About
Project Timeline

Project Map

Team Members

Job Opportunities

Work Packages
WP1 - Support to effective applications

WP2 - Develop community tools

WP3 - Tackling the data challenge

WP4 - HPC Services to enchance Weather and Climate applications

WP5 - Training and capacity building

WP6 - Community engagement, dissemination and exploitation

WP7 - Project Management

Service
Services

What We Offer

Testimonials

Success Stories

Training
Training Events

Training Materials

Media
Videos

Logos & Templates

News

Events
Events

Training Events

Tools
HPCW

Data Compression Lab

AUTO-RPE

APP

Kernel Tuner

PSyclone

Results
Publications

Key Exploitable Results (KERs)

Automatic Performance Profiling (APP)

The Automatic Performance Profiling tool generates performance reports of climate models automatically.

DocumentationCodeWifi

Automatic Performance Profiling (APP)

The rise in spatial and temporal resolution of Earth System Models (ESMs) enhances physical process representation but increases computational demands. This strains scalability and efficiency on modern HPC architectures.

Identifying and addressing parallel performance bottlenecks in large climate models is complex and time-consuming, requiring specialized expertise. The Automatic Performance Profiling (APP) tool addresses this by providing an automated workflow for performance analysis. APP runs end-to-end profiling experiments, generating comprehensive reports that combine high-level metrics with detailed insights into MPI communication, cache behavior, and function profiling.

The rational

------

The continuous increase in spatial and temporal resolution of Earth System Models (ESMs) is essential to better represent physical processes and extreme events. However, these advances come at a rapidly growing computational cost, pushing simulations towards unprecedented levels of parallelism on modern High Performance Computing (HPC) architectures. As a result, inefficiencies in load balance, communication, I/O, and memory usage increasingly limit scalability and scientific throughput. Identifying and addressing parallel performance bottlenecks in large, multi-component climate models remains a complex and time-consuming task, often requiring specialized HPC expertise and manual profiling workflows. This represents a significant barrier for model developers aiming to efficiently exploit current and future exascale systems. The Automatic Performance Profiling (APP) tool addresses this by providing an automated workflow for performance analysis. APP runs end-to-end profiling experiments, generating comprehensive reports that combine high-level metrics with detailed insights into MPI communication, cache behavior, and function profiling.

Key features

------

Automated scaling analysis

Automated model tracing and advanced performance metrics extraction

HPC platform and hardware diagnostics

Broad model and platform support

Detailed performance report generation: includes resources (plots, table, timelines…) and insights to help developers find performance bottlenecks

Models and platforms support

------

The tool currently supports the following climate models: EC-Earth 4, NEMO 4.2.1 and NEMO 5 in HPCW 3.0.

And it has been ported and tested to Marenostrum 5 (BSC) and HPC2020 (ECMWF).

PagePagetrueAutomatic Performance Profiling (APP)1775051279Apr 01, 20262026-04-01automatic-performance-profiling-app-video

About
Project Timeline

Project Map

Team Members

Job Opportunities

Work Packages
WP1 - Support to effective applications

WP2 - Develop community tools

WP3 - Tackling the data challenge

WP4 - HPC Services to enchance Weather and Climate applications

WP5 - Training and capacity building

WP6 - Community engagement, dissemination and exploitation

WP7 - Project Management

Service
Services

What We Offer

Testimonials

Success Stories

Training
Training Events

Training Materials

Media
Videos

Logos & Templates

News

Events
Events

Training Events

Tools
HPCW

Data Compression Lab

AUTO-RPE

APP

Kernel Tuner

PSyclone

Results
Publications

Key Exploitable Results (KERs)

This link will open in a new window

This link will open in a new window

This link will open in a new window

This link will open in a new window

------

ESIWACE3 has received funding from the European High Performance Computing Joint Undertaking (EuroHPC JU) and the European Union (EU) under grant agreement No 101093054.

Terms

Privacy

Cookies

© 2026 Barcelona Supercomputing Center - Centro Nacional de Supercomputación

------
导航页打开网址