Home

Berkeley Lab is Leading the Charge to Superfacility

The aim is no less than an integrated and automated system for gathering, transporting, and analyzing scientific data in real time.

Artistic representation of a neural network

Training for Scientific Machine Learning

Neural networks can be difficult to train and employ on large-scale science problems. That's why Berkeley Lab researchers are devising new training methods tailored to scientific machine learning.

WarpX Goes Exascale

The ECP-funded WarpX Project has spent the last six years creating a novel, highly parallel, and highly optimized single-source simulation code for modeling plasma-based particle colliders on cutting-edge exascale supercomputers.

EQSIM will be sharing its simulations with the general public.

EQSIM to Publicly Release Most Accurate Earthquake Simulations to Date

The collaboration involves scientists and computing resources from Berkeley Lab.

3D rendering of six regions obtained via the machine learning pipeline

Machine Learning Helps Process Large Bioimaging Datasets

Berkeley Lab scientists used several machine learning techniques in a pipeline to segment and identify cryo-ET cell membrane structures.

'Fair Universe' Project Targets Supercomputer-Scale AI Benchmarks

A Berkeley Lab-led team aims to build an open-science supercomputer-scale platform where researchers can train and fine-tune AI models for HEP.

Divisions & Facilities

Careers

Fellowships

Berkeley Lab Computing Sciences fields two highly selective named fellowships for graduates. Both the Luis W. Alvarez Fellowship in Computing and the Admiral Grace Hopper Fellowship in Computing offer exceptional opportunities for post-doctoral research. We also offer many other fellowship opportunities. Read More »
Current Openings

Computing Sciences is looking for smart, motivated people from all walks of life and at all stages of their careers to work in our leading research programs and national user facilities. Read More »
Summer Student & Faculty Employment in Computing Sciences

Our summer program offers college students and faculty/student teams research experience in computational science, high-performance computing, and high-speed networking in collaboration with Berkeley Lab staff. Read More »

News

New Math Methods and Perlmutter HPC Combine to Deliver Record-Breaking ML Algorithm

March 13, 2023: Using the Perlmutter supercomputer at NERSC, researchers at Berkeley Lab have devised a new mathematical method for analyzing extremely large datasets—and, in the process, demonstrated proof of principle on a record-breaking dataset of more than five million points. Read More »
Improving Training for Scientific Machine Learning

March 3, 2023: In the world of scientific machine learning (SciML), scientists are beginning to embrace the use of neural networks as a way to accelerate simulations. At the heart of deep learning algorithms, neural networks provide a mechanism to encode complex dependency structures, using many connected node layers to transform data into learned features to be used for a wide range of scientific tasks. Read More »
Berkeley Lab Works Toward a Connected Future for Science

February 27, 2023: Superfacility is a conceptual model of seamless connection between experimental facilities and high performance computing resources—an integrated and automated system for gathering, transporting, and analyzing scientific data in real time. Berkeley Lab is working to standardize, automate, and scale up the processes needed for superfacility onsite, across the U.S. Department of Energy (DOE), and beyond. Read More »