Skip to main content

AutoRPE is a tool designed to help with the optimization of numerical precision of Computational Science models writen in FORTRAN.

Project description

AutoRPE

AutoRPE Logo (Automatic Reduced Precision Emulator)

AutoRPE is a tool designed to optimize the numerical precision of computational science models written in Fortran. Originally developed to enable the use of a Reduced Precision Emulator (RPE) ( Dawson, A. and Düben, P. D.: 2017) in large-scale codes such as NEMO, AutoRPE has since evolved into a framework for streamlining code modifications, managing precision experiments, and facilitating precision sensitivity analysis.

Features

  • Automatic Code Manipulation:

Modifies Fortran source code to implement reduced precision emulation, reducing manual effort.

  • Precision Sensitivity Analysis:

Identifies sensitive variables requiring higher precision using algorithms like binary search.

  • Workflow Management:

Automates precision testing workflows to minimize manual intervention and ensure reproducibility.

  • Code Coherency Assurance:

Detects and resolves inconsistencies in variable types to ensure code correctness.

Background

Global warming and climate change pose significant challenges to humanity due to their social, economic, and environmental impacts. Better understanding and improved capacity to forecast climate evolution can support the development of ambitious adaptation policies. Earth system models (ESMs) are crucial for simulating and predicting climate behavior, but their computational demands continue to grow with advancements such as higher resolution and ensemble forecasting. Efficient use of computational resources has become essential, and mixed-precision approaches are emerging as a way to enhance performance by reducing memory and computational costs. However, identifying variables that can safely operate at reduced precision without compromising model accuracy is complex. AutoRPE was developed to automate this process, enabling the exploration of mixed-precision configurations in full-scale models and facilitating performance improvements in computationally intensive simulations.

Documentation

For detailed documentation on installation, usage, and workflows, visit the AutoRPE Documentation.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

autorpe-1.0.1.tar.gz (139.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

AutoRPE-1.0.1-py3-none-any.whl (170.5 kB view details)

Uploaded Python 3

File details

Details for the file autorpe-1.0.1.tar.gz.

File metadata

  • Download URL: autorpe-1.0.1.tar.gz
  • Upload date:
  • Size: 139.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for autorpe-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2e108f59d13a0001401a0d20d4475c5a6d766b0179b506acb93db19503fd4954
MD5 101d070c7b4c8dd67ff9f71977e8be05
BLAKE2b-256 686c5289024491d736bc0cf056bc3bfecdd3c3ac46fbed18165daf4b82da45cc

See more details on using hashes here.

File details

Details for the file AutoRPE-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: AutoRPE-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 170.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for AutoRPE-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b57943d95a06ef4f5fdb28b576716140b126c509da8e681f001e2af7c8eda30c
MD5 e4b0ff8e5cd7b1eac1e49f001cf0a7fe
BLAKE2b-256 540e067d146c7438526dbaf5010f7058fa48eee106522ca8f21fee93b1adc18f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page